Luno MCP Server
OfficialThis server integrates with the Luno cryptocurrency exchange via the Model Context Protocol, allowing AI assistants (like Claude Code, VS Code, Cursor, and Windsurf) to query market data, manage accounts, and execute trades.
Market Data (no auth required):
get_ticker/get_tickers– latest prices, best bid/ask, and 24h volume for one or all trading pairsget_order_book– top 100 bids and asks to assess liquidity and slippagelist_trades– recent public trades with price, volume, side, and timestampget_candles– OHLCV candlestick data for charting or backtestingget_markets_info– all supported markets and their trading parameters (min/max volume, tick sizes, fee tiers, etc.)
Account Information (API key required):
get_balances– available, reserved, and unconfirmed amounts across all accountslist_transactions/get_transaction– paginated ledger entries and full transaction detailslist_orders– view open orders
Trading (API key required + explicit opt-in):
create_order– place a GTC limit buy or sell ordercancel_order– cancel an existing working order by IDconvert– instantly convert funds between two currency accounts
Security: Write operations (create_order, cancel_order, convert) are disabled by default and must be explicitly enabled via ALLOW_WRITE_OPERATIONS=true or the --allow-write-operations flag. Supports Docker, Homebrew, and source builds.
Provides access to cryptocurrency trading data and functionality through the Luno exchange, including viewing wallet balances, creating buy/sell orders, checking prices, and viewing transaction history for Bitcoin and other cryptocurrencies.
Enables running the MCP server in a containerized environment, with configuration options for passing API credentials and environment variables to the Docker container.
Supports loading API credentials and configuration options from environment variables or .env files for local development and testing.
Provides integration with GitHub for issue tracking, repository access, and package distribution through GitHub Container Registry (ghcr.io).
Integrates with SonarCloud for code quality metrics, displaying badges for quality gate status, coverage, bugs, security rating, vulnerabilities, and duplicated lines.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Luno MCP Serverget my current account balances"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Luno MCP Server
A Model Context Protocol (MCP) server that provides access to the Luno cryptocurrency exchange API.
This server enables integration with Claude Code/VSCode/Cursor (and other MCP-compatible clients), providing contextual information and functionality related to the Luno cryptocurrency exchange.
Getting started
Some tools require your Luno API key and secret. Get these from your Luno account settings.
Standard config (Docker) works with most MCP clients:
{
"mcpServers": {
"luno": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "LUNO_API_KEY_ID=YOUR_API_KEY_ID",
"-e", "LUNO_API_SECRET=YOUR_API_SECRET",
"ghcr.io/luno/luno-mcp:latest"
]
}
}
}Using Docker:
claude mcp add luno -- docker run --rm -i -e LUNO_API_KEY_ID=YOUR_API_KEY_ID -e LUNO_API_SECRET=YOUR_API_SECRET ghcr.io/luno/luno-mcp:latestOr if you've built from source:
claude mcp add luno -e LUNO_API_KEY_ID=YOUR_API_KEY_ID -e LUNO_API_SECRET=YOUR_API_SECRET -- luno-mcpOne-line install and configure (macOS):
curl -fsSL https://raw.githubusercontent.com/luno/luno-mcp/main/claude-desktop-install.sh | \
LUNO_API_KEY_ID=<key> LUNO_API_SECRET=<secret> shOr add the standard config to your claude_desktop_config.json manually (setup guide).
Go to Cursor Settings → MCP → Add new MCP Server. Use command type with command docker and the args from the standard config above.
Or add the standard config to your .cursor/mcp.json.
Follow the Windsurf MCP documentation. Use the standard config above.
Click the badges above for one-click Docker install, or add the following to your VS Code settings.json or .vscode/mcp.json:
With Docker
{
"inputs": [
{"id": "luno_api_key_id", "type": "promptString", "description": "Luno API Key ID", "password": true},
{"id": "luno_api_secret", "type": "promptString", "description": "Luno API Secret", "password": true}
],
"servers": {
"luno": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "LUNO_API_KEY_ID=${input:luno_api_key_id}",
"-e", "LUNO_API_SECRET=${input:luno_api_secret}",
"ghcr.io/luno/luno-mcp:latest"
]
}
}
}From source
{
"inputs": [
{"id": "luno_api_key_id", "type": "promptString", "description": "Luno API Key ID", "password": true},
{"id": "luno_api_secret", "type": "promptString", "description": "Luno API Secret", "password": true}
],
"servers": {
"luno": {
"command": "luno-mcp",
"env": {
"LUNO_API_KEY_ID": "${input:luno_api_key_id}",
"LUNO_API_SECRET": "${input:luno_api_secret}"
}
}
}
}SSE transport
{
"servers": {
"luno": {
"type": "sse",
"url": "http://localhost:8080/sse"
}
}
}Requires Go 1.25 or later.
Install directly:
go install github.com/luno/luno-mcp/cmd/server@latestOr clone and build:
git clone https://github.com/luno/luno-mcp
cd luno-mcp
go build -o luno-mcp ./cmd/serverOptionally make it available system-wide:
sudo mv luno-mcp /usr/local/bin/Install via Homebrew using the luno/homebrew-luno-mcp tap:
brew tap luno/luno-mcp
brew install luno-mcpThen configure your MCP client:
{
"mcpServers": {
"luno": {
"command": "luno-mcp",
"args": ["--transport", "stdio"],
"env": {
"LUNO_API_KEY_ID": "YOUR_API_KEY_ID",
"LUNO_API_SECRET": "YOUR_API_SECRET"
}
}
}
}Or with Claude Code:
claude mcp add luno -e LUNO_API_KEY_ID=YOUR_API_KEY_ID -e LUNO_API_SECRET=YOUR_API_SECRET -- luno-mcpUse the standard config above, or run directly:
docker run --rm -i \
-e LUNO_API_KEY_ID=YOUR_API_KEY_ID \
-e LUNO_API_SECRET=YOUR_API_SECRET \
ghcr.io/luno/luno-mcp:latestFor SSE mode:
docker run --rm \
-e LUNO_API_KEY_ID=YOUR_API_KEY_ID \
-e LUNO_API_SECRET=YOUR_API_SECRET \
-p 8080:8080 \
ghcr.io/luno/luno-mcp:latest \
--transport sse --sse-address 0.0.0.0:8080Optional environment variables:
LUNO_API_DEBUG=true— Enable debug loggingLUNO_API_DOMAIN=api.staging.luno.com— Override API domainALLOW_WRITE_OPERATIONS=true— Enable write operations (create_order,cancel_order,convert)
Standard config (Docker) works with most MCP clients:
{
"mcpServers": {
"luno": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "LUNO_API_KEY_ID=YOUR_API_KEY_ID",
"-e", "LUNO_API_SECRET=YOUR_API_SECRET",
"ghcr.io/luno/luno-mcp:latest"
]
}
}
}Using Docker:
claude mcp add luno -- docker run --rm -i -e LUNO_API_KEY_ID=YOUR_API_KEY_ID -e LUNO_API_SECRET=YOUR_API_SECRET ghcr.io/luno/luno-mcp:latestOr if you've built from source:
claude mcp add luno -e LUNO_API_KEY_ID=YOUR_API_KEY_ID -e LUNO_API_SECRET=YOUR_API_SECRET -- luno-mcpOne-line install and configure (macOS):
curl -fsSL https://raw.githubusercontent.com/luno/luno-mcp/main/claude-desktop-install.sh | \
LUNO_API_KEY_ID=<key> LUNO_API_SECRET=<secret> shOr add the standard config to your claude_desktop_config.json manually (setup guide).
Go to Cursor Settings → MCP → Add new MCP Server. Use command type with command docker and the args from the standard config above.
Or add the standard config to your .cursor/mcp.json.
Follow the Windsurf MCP documentation. Use the standard config above.
Click the badge above for one-click Docker install, or add the following to your VS Code settings.json or .vscode/mcp.json:
With Docker
{
"servers": {
"luno": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "LUNO_API_KEY_ID=${input:luno_api_key_id}",
"-e", "LUNO_API_SECRET=${input:luno_api_secret}",
"ghcr.io/luno/luno-mcp:latest"
],
"inputs": [
{"id": "luno_api_key_id", "type": "promptString", "description": "Luno API Key ID", "password": true},
{"id": "luno_api_secret", "type": "promptString", "description": "Luno API Secret", "password": true}
]
}
}
}From source
{
"servers": {
"luno": {
"command": "luno-mcp",
"env": {
"LUNO_API_KEY_ID": "${input:luno_api_key_id}",
"LUNO_API_SECRET": "${input:luno_api_secret}"
},
"inputs": [
{"id": "luno_api_key_id", "type": "promptString", "description": "Luno API Key ID", "password": true},
{"id": "luno_api_secret", "type": "promptString", "description": "Luno API Secret", "password": true}
]
}
}
}SSE transport
{
"servers": {
"luno": {
"type": "sse",
"url": "http://localhost:8080/sse"
}
}
}Requires Go 1.25 or later.
Install directly:
go install github.com/luno/luno-mcp/cmd/server@latestOr clone and build:
git clone https://github.com/luno/luno-mcp
cd luno-mcp
go build -o luno-mcp ./cmd/serverOptionally make it available system-wide:
sudo mv luno-mcp /usr/local/bin/Use the standard config above, or run directly:
docker run --rm -i \
-e LUNO_API_KEY_ID=YOUR_API_KEY_ID \
-e LUNO_API_SECRET=YOUR_API_SECRET \
ghcr.io/luno/luno-mcp:latestFor SSE mode:
docker run --rm \
-e LUNO_API_KEY_ID=YOUR_API_KEY_ID \
-e LUNO_API_SECRET=YOUR_API_SECRET \
-p 8080:8080 \
ghcr.io/luno/luno-mcp:latest \
--transport sse --sse-address 0.0.0.0:8080Optional environment variables:
LUNO_API_DEBUG=true— Enable debug loggingLUNO_API_DOMAIN=api.staging.luno.com— Override API domainALLOW_WRITE_OPERATIONS=true— Enable write operations (create_order,cancel_order,convert)
Related MCP server: Xero MCP Server
Features
Resources: Access to account balances, transaction history, and more
Tools: Functionality for creating and managing orders, checking prices, and viewing transaction details
Security: Secure authentication using Luno API keys
VS Code Integration: Easy integration with VSCode, or other AI IDEs
Available Tools
Tool | Category | Description | Auth Required | Write |
| Market Data | Get current ticker information for a trading pair | ❌ | ❌ |
| Market Data | List tickers for given pairs (or all) | ❌ | ❌ |
| Market Data | Get the order book for a trading pair | ❌ | ❌ |
| Market Data | List recent trades for a currency pair | ❌ | ❌ |
| Market Data | Get candlestick market data for a currency pair | ❌ | ❌ |
| Market Data | List all supported markets parameter information | ❌ | ❌ |
| Account Information | Get balances for all accounts | ✅ | ❌ |
| Trading | Create a new buy or sell order | ✅ | ✅ |
| Trading | Cancel an existing order | ✅ | ✅ |
| Trading | List open orders | ✅ | ❌ |
| Transactions | List transactions for an account | ✅ | ❌ |
| Transactions | Get details of a specific transaction | ✅ | ❌ |
| Trading | Instantly convert between two currencies | ✅ | ✅ |
Command-line options
--transport: Transport type (stdio,sse, orstreamable-http; default:stdio)--sse-address: Address for SSE and Streamable HTTP transports (default:localhost:8080)--domain: Luno API domain (default:api.luno.com)--log-level: Log level (debug,info,warn,error, default:info)--allow-write-operations: Enable write operations (create_order,cancel_order,convert). Also configurable viaALLOW_WRITE_OPERATIONSenv var
Examples
Working with wallets
You can ask your LLM to show your wallet balances:
What are my current wallet balances on Luno?Trading
You can ask your LLM to help you trade:
Create a limit order to buy 0.001 BTC at 50000 ZARTransaction history
You can ask your LLM to show your transaction history:
Show me my recent Bitcoin transactionsMarket Data
You can ask your LLM to show market data:
Show me recent trades for XBTZARWhat's the latest price for Bitcoin in ZAR?Security Considerations
This tool requires API credentials that have access to your Luno account. Be cautious when using API keys, especially ones with withdrawal permissions. It's recommended to create API keys with only the permissions needed for your specific use case.
Write Operations Control
By default, the MCP server runs in read-only mode — create_order, cancel_order, and convert are not exposed. To enable them, set ALLOW_WRITE_OPERATIONS to true, 1, or yes. See the config examples above for where to add this flag.
Best Practices for API Credentials
Create Limited-Permission API Keys: Only grant the permissions absolutely necessary for your use case
Never Commit Credentials to Version Control: Ensure
.envfiles are always in your.gitignoreRotate API Keys Regularly: Periodically regenerate your API keys to limit the impact of potential leaks
Monitor API Usage: Regularly check your Luno account for any unauthorized activity
Use Read-Only Mode by Default: Only enable write operations when specifically needed
Contributing
If you'd like to contribute to the development of this project, please see the CONTRIBUTING.md file for guidelines.
License
Available Tools
13 toolscancel_orderADestructiveIdempotent
Cancel a working order by ID. Idempotent at the Luno API level: cancelling an already-cancelled or fully-filled order returns the current state without error. Use after list_orders to remove a specific working order. Write operation: requires the --allow-write-operations flag or ALLOW_WRITE_OPERATIONS=true.
| Name | Required | Description | Default |
|---|---|---|---|
| order_id | Yes | ID of the order to cancel, as returned by list_orders or create_order. |
Output Schema
| Name | Required | Description |
|---|---|---|
| success | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds context beyond annotations: idempotency detail and flag requirement. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise, front-loaded sentences with no redundant information. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, annotations present, output schema exists), the description covers all necessary behavioral and usage context completely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema coverage, the description adds minimal value (only reinforces usage context). Schema already explains parameter meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action ('Cancel a working order by ID'), uses a specific verb+resource pair, and distinguishes itself from siblings by referencing list_orders.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly explains idempotent behavior, when to use (after list_orders), and the required write-operation flag, providing comprehensive usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
convertADestructive
Instantly convert funds between two currency accounts on the authenticated profile via the Luno broker (e.g. ZAR to ZARU). The conversion is final and applies the broker quote at execution time. Pass idempotency_key to make retries safe; omitting it generates a fresh UUID per call, so retries on network error may double-convert. Write operation: requires the --allow-write-operations flag or ALLOW_WRITE_OPERATIONS=true.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Amount of the source currency to convert, as a decimal string (e.g. "100.00"). Must be positive. | |
| idempotency_key | No | Any unique string up to 255 chars. Reuse the same key to safely retry a failed call without double-converting. Auto-generated as a UUID when omitted. | |
| source_account_id | Yes | Numeric ID of the account to debit, as a string (from get_balances). | |
| target_account_id | Yes | Numeric ID of the account to credit, as a string (from get_balances). Must hold the target currency. |
Output Schema
| Name | Required | Description |
|---|---|---|
| converted_amount | Yes | |
| id | Yes | |
| source_account_balance | Yes | |
| source_currency | Yes | |
| target_account_balance | Yes | |
| target_currency | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate destructiveHint=true and idempotentHint=false. The description reinforces this by stating the conversion is final, warns about double-conversion, and clarifies the broker quote at execution time. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences plus a note about the write flag. It is front-loaded with the core purpose and uses minimal but essential words. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a destructive write with an output schema (not shown), the description covers key operational aspects: finality, quote timing, idempotency, and auth requirements. It does not detail failure modes or return values, but those are likely in the output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the description adds critical context: idempotency_key behavior (auto-generated UUID vs. user-supplied), amount must be positive decimal string, and account IDs come from get_balances. This significantly aids parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('convert funds between two currency accounts'), specifies the broker (Luno), and provides an example ('ZAR to ZARU'). This matches the sibling context: no other tool performs conversions, so it is well-differentiated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool (e.g., for instant conversions), the importance of idempotency_key for retry safety, and the required write flag. It does not explicitly mention alternatives but covers key usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create_orderA
Place a new GTC limit order on Luno. The order rests on the book and may fill partially, fully, or not at all; this tool does not wait for or report fills - use list_orders to inspect state, or cancel_order to withdraw a working order. Not idempotent: repeated calls create duplicate orders. Prefer get_markets_info first to validate the pair's tick size and minimum volume. Write operation: requires the --allow-write-operations flag or ALLOW_WRITE_OPERATIONS=true.
| Name | Required | Description | Default |
|---|---|---|---|
| pair | Yes | Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT. | |
| price | Yes | Limit price in the counter currency, as a decimal string (e.g. "500000"). Must align with the market's tick size; check get_markets_info. | |
| type | Yes | Side of the order. BUY = bid (buy the base currency with the counter currency); SELL = ask (sell the base currency for the counter currency). | |
| volume | Yes | Order volume in the base currency, as a decimal string (e.g. "0.001"). Must meet the market's minimum volume and step size; check get_markets_info. |
Output Schema
| Name | Required | Description |
|---|---|---|
| order_id | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral context beyond annotations: non-idempotence, fill behavior (partial/full/none), and write-operation requirement. It complements the readOnlyHint=false and idempotentHint=false annotations, without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is four sentences, front-loaded with the core purpose. Every sentence earns its place, covering behavior, guidance, and prerequisites without redundancy. Highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (limit order, non-idempotent, write operation), the description covers all critical aspects: order type, fill behavior, state inspection, cancellation, validation, and required flag. It is complete and self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds value by explaining the order type (GTC), pair rewrite rule (BTC to XBT), and validation hints (tick size, minimum volume). This extra context justifies a score above baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool places a new GTC limit order on Luno, distinguishing it from sibling tools like list_orders and cancel_order. The verb 'place' and resource 'limit order' are specific, and the detailed behavior of partial/full fills further clarifies purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use this tool (placing a limit order), when not to (use list_orders for state, cancel_order to withdraw), and suggests a prerequisite (get_markets_info for validation). It also notes the require write flag, providing complete usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_balancesARead-onlyIdempotent
Return balances for every account on the authenticated Luno profile, including available, reserved, and unconfirmed amounts per asset. Requires API credentials. Use this to check holdings before placing orders, conversions, or transfers; not for public market data (use get_ticker or get_tickers).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| balances | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, destructiveHint, idempotentHint, openWorldHint. The description adds value by specifying authentication requirement (API credentials) and details about balance types (available, reserved, unconfirmed), which are beyond annotation scope.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no unnecessary words. The first sentence describes the action and result; the second gives usage guidance. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and presence of output schema, the description fully covers purpose, usage, authentication requirements, and distinguishes from sibling tools. Nothing essential is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters defined; schema coverage is 100% (no params). The description does not need to add parameter info beyond the schema. Baseline for 0 params is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns balances for every account on the authenticated Luno profile, including specific amounts (available, reserved, unconfirmed). It distinguishes from siblings by explicitly contrasting with get_ticker/get_tickers for public market data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use ('check holdings before placing orders, conversions, or transfers') and when not to ('not for public market data'), with alternative tool names (get_ticker, get_tickers).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_candlesARead-onlyIdempotent
Return OHLCV candlestick data for a trading pair. Each candle contains timestamp (ms), open, high, low, close, and base-currency volume. Public endpoint, no auth required. Use for charts, indicators, or backtesting; not for live order-book state (use get_order_book) or trade-by-trade flow (use list_trades).
| Name | Required | Description | Default |
|---|---|---|---|
| duration | Yes | Candle duration in seconds. Common values: 60 (1m), 300 (5m), 900 (15m), 1800 (30m), 3600 (1h), 10800 (3h), 14400 (4h), 28800 (8h), 86400 (1d), 259200 (3d), 604800 (1w). The Luno API only accepts a fixed set of durations; passing an unsupported value will return an error. | |
| pair | Yes | Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT. | |
| since | No | Start of the window as Unix epoch milliseconds (UTC). Defaults to 24 hours ago when omitted or 0. |
Output Schema
| Name | Required | Description |
|---|---|---|
| candles | Yes | |
| duration | Yes | |
| pair | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, destructiveHint, idempotentHint, openWorldHint. Description adds 'Public endpoint, no auth required' and mentions base-currency volume, providing safety info beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with purpose, no redundant information. Every sentence is informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of output schema and rich annotations, the description fully covers purpose, usage, parameters, and behavior. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds context on common duration values and that Luno accepts a fixed set, plus automatic BTC rewrite. This adds meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it returns OHLCV candlestick data for a trading pair, specifies candle fields, and distinguishes from siblings get_order_book and list_trades.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit when to use (for charts, indicators, backtesting) and when not to (live order-book state or trade-by-trade flow), including specific alternative tool names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_markets_infoARead-onlyIdempotent
List supported Luno markets and their trading parameters: min/max base and counter volume, price/volume tick size, fee tiers, status, and base/counter currency. Public endpoint, no auth required. Use this before placing an order to validate price/volume against the market's tick and minimum constraints; not for live prices (use get_ticker).
| Name | Required | Description | Default |
|---|---|---|---|
| pair | No | Optional comma-separated list of pairs to filter to (e.g. "XBTZAR,ETHZAR"). Omit to return every supported market. |
Output Schema
| Name | Required | Description |
|---|---|---|
| markets | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. Description adds that it is a public endpoint with no auth required, enhancing transparency beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose and key information, zero waste. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given output schema exists and annotations are rich, the description covers purpose, usage, parameter, and sibling differentiation. Fully complete for a list endpoint.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage with description for the sole parameter 'pair'. Description explains it is optional, comma-separated, and filters results, adding value over the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'List supported Luno markets and their trading parameters', which is a specific verb+resource, and distinguishes from get_ticker for live prices.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this before placing an order to validate price/volume... not for live prices (use get_ticker)', providing clear when-to-use and alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_order_bookARead-onlyIdempotent
Return the top 100 bids and asks for a trading pair, aggregated by price level. Public endpoint, no auth required. Use this to assess available liquidity and likely slippage before sizing an order; use get_ticker for a simple price quote or list_trades for recent execution flow.
| Name | Required | Description | Default |
|---|---|---|---|
| pair | Yes | Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT. |
Output Schema
| Name | Required | Description |
|---|---|---|
| asks | Yes | |
| bids | Yes | |
| timestamp | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds that it is a 'public endpoint, no auth required,' which is additional behavioral context beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences front-load the core action and immediately provide usage guidance. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists (not shown but noted), the description does not need to detail return values. It covers purpose, usage context, and authentication needs adequately.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema already includes a detailed description of the 'pair' parameter, including symbol convention and BTC rewrite. The tool description adds no additional parameter information, so baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns the top 100 bids and asks for a trading pair, aggregated by price level. It uses a specific verb ('Return') and resource ('bids and asks for a trading pair'), distinguishing from siblings like get_ticker and list_trades.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this to assess available liquidity and likely slippage before sizing an order; use get_ticker for a simple price quote or list_trades for recent execution flow.' This provides clear when-to-use and alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_tickerARead-onlyIdempotent
Get the latest ticker (last trade price, best bid, best ask, 24h rolling volume) for a single Luno trading pair. Public endpoint, no auth required. Use this for a quick price snapshot of one market; use get_tickers for multiple markets at once, or get_order_book for depth-of-book.
| Name | Required | Description | Default |
|---|---|---|---|
| pair | Yes | Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT. |
Output Schema
| Name | Required | Description |
|---|---|---|
| ask | Yes | |
| bid | Yes | |
| last_trade | Yes | |
| pair | Yes | |
| rolling_24_hour_volume | Yes | |
| status | Yes | |
| timestamp | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds that it is a public endpoint with no auth required and lists the returned fields (price, bid, ask, volume). This provides useful context beyond annotations, warranting a 4.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of two concise sentences. The first sentence defines the tool, and the second provides usage guidance. No extraneous words, and the most important information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one required parameter, no nested objects, with output schema), the description covers the purpose, when to use, what it returns, and authentication status. Combined with annotations, it is fully complete for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the schema already describes the parameter thoroughly (e.g., 'Trading pair using Luno's symbol convention... BTC is automatically rewritten to XBT'). The description does not add further parameter semantics, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets the latest ticker (last trade price, best bid, best ask, 24h rolling volume) for a single Luno trading pair. It uses specific verbs ('Get the latest ticker') and resource ('Luno trading pair'), and differentiates from siblings like get_tickers and get_order_book.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says when to use this tool ('quick price snapshot of one market') and when to use alternatives ('use get_tickers for multiple markets at once, or get_order_book for depth-of-book'). This provides clear recommendations and exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_tickersARead-onlyIdempotent
List the latest tickers for all Luno trading pairs, or for a comma-separated subset. Each ticker has last trade price, best bid, best ask, and 24h volume. Public endpoint, no auth required. Use this to survey or compare multiple markets in one call; use get_ticker when you only need a single pair.
| Name | Required | Description | Default |
|---|---|---|---|
| pair | No | Optional comma-separated list of pairs to filter to (e.g. "XBTZAR,ETHZAR"). Omit to return every supported pair. |
Output Schema
| Name | Required | Description |
|---|---|---|
| tickers | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds that the endpoint is public and no auth required, and explains the fields included in each ticker (last trade price, best bid, best ask, 24h volume), providing beyond-annotation context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core functionality, and each sentence adds specific value: first states purpose, second covers output, use case, and alternative. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that an output schema exists and annotations are provided, the description covers input parameter usage, output fields, comparison with sibling, and authentication requirements, making it fully complete for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the only parameter 'pair'. The description elaborates on the format ('comma-separated list'), gives an example, and clarifies behavior when omitted ('return every supported pair'), adding value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists the latest tickers for all Luno trading pairs or a subset, using the specific verb 'list' and resource 'tickers'. It distinguishes from the sibling tool get_ticker by noting the use case for multiple vs. single pair.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use this tool ('survey or compare multiple markets in one call') and when to use the alternative get_ticker ('when you only need a single pair'). It also notes that it is a public endpoint with no auth required.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_transactionARead-onlyIdempotent
Return the full ledger entry for one transaction on the authenticated profile (amount, running balance, description, timestamp). Only finds transactions within the most recent 1000 rows of the account; for older entries, narrow the search with list_transactions first. Requires API credentials.
| Name | Required | Description | Default |
|---|---|---|---|
| account_id | Yes | Numeric account ID, as a string (from get_balances). | |
| transaction_id | Yes | Row index of the transaction within the account, as a string. Obtain from list_transactions (row_index field). |
Output Schema
| Name | Required | Description |
|---|---|---|
| account_id | Yes | |
| available | Yes | |
| available_delta | Yes | |
| balance | Yes | |
| balance_delta | Yes | |
| currency | Yes | |
| description | Yes | |
| detail_fields | Yes | |
| details | Yes | |
| kind | Yes | |
| reference | Yes | |
| row_index | Yes | |
| timestamp | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds valuable context: the row limit of 1000 and credential requirement. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no filler. First sentence states purpose and return fields; second provides constraint and prerequisite. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple lookup nature, full schema coverage, annotations, and presence of output schema, the description covers all needed context: return fields, limitations, prerequisites, and credentials.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with basic descriptions. The description adds context on how to obtain the IDs: account_id from get_balances, transaction_id from list_transactions (row_index field). This enriches the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns the full ledger entry for one transaction on the authenticated profile, listing specific fields (amount, running balance, description, timestamp). It distinguishes from sibling tools like list_transactions (which lists) and get_balances (which returns balances).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use ('return the full ledger entry for one transaction'), provides a constraint ('only finds transactions within the most recent 1000 rows'), and directs to use list_transactions first for older entries. Also notes requirement for API credentials.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_ordersARead-onlyIdempotent
List orders on the authenticated profile (open by default; recently completed orders may also appear depending on Luno API behaviour), optionally filtered by trading pair. Requires API credentials. Use this to inspect or audit working orders before cancelling them or placing new ones.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of orders to return (1-100). Defaults to 100. | |
| pair | No | Optional trading pair filter (e.g. "XBTZAR"). Omit to list orders across all pairs. |
Output Schema
| Name | Required | Description |
|---|---|---|
| orders | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds valuable behavioral context beyond annotations: open by default, possible inclusion of recently completed orders per Luno API behavior, and requirement for API credentials. Annotations already mark read-only, so no contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the core action. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema (not shown), the description adequately covers purpose, usage, behavior, and auth. No gaps for a listing tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters. The description merely echoes the pair filter option without adding new meaning, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'List orders on the authenticated profile' with optional pair filtering, clearly identifying the action and resource. It distinguishes from sibling tools like cancel_order or create_order by focusing on listing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'inspect or audit working orders before cancelling them or placing new ones.' Does not provide when-not-to-use or alternatives, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_tradesARead-onlyIdempotent
List recent public trades for a trading pair, with price, volume, side (BUY/SELL), and timestamp. Public endpoint, no auth required. Use for recent execution flow or tape analysis; not for your own trade history.
| Name | Required | Description | Default |
|---|---|---|---|
| pair | Yes | Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT. | |
| since | No | Optional lower bound as Unix epoch milliseconds (UTC), passed as a string. Only trades executed after this time are returned. Omit for the most recent trades. |
Output Schema
| Name | Required | Description |
|---|---|---|
| trades | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true. Description adds 'Public endpoint, no auth required' which is useful behavioral context beyond annotations. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences: purpose and data, public nature, and usage guidance. No wasted words, front-loaded with key info.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, return values are covered. Description covers purpose, usage, and data fields. Could mention ordering or limits, but sufficient for a simple list endpoint.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and both parameters are well-documented in the schema. The description adds no additional parameter guidance, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'List', resource 'recent public trades', and specifies returned fields (price, volume, side, timestamp). Distinguishes from siblings by noting it's public and not for own trade history.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells when to use: 'for recent execution flow or tape analysis' and importantly what not to use it for: 'not for your own trade history'. Provides clear context and exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_transactionsARead-onlyIdempotent
List ledger entries for a single account on the authenticated profile, paginated by row ID. min_row is inclusive, max_row is exclusive, and the API caps a single window at 1000 rows. Requires API credentials. Use for reconciliation, exports, or audit trails; iterate by advancing min_row to (last returned row + 1).
| Name | Required | Description | Default |
|---|---|---|---|
| account_id | Yes | Numeric account ID, as a string (from get_balances). | |
| max_row | No | Last row to return, exclusive. Defaults to 100 when omitted. The Luno API caps (max_row - min_row) at 1000. | |
| min_row | No | First row to return, inclusive (1-based). Defaults to 1 when omitted. |
Output Schema
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| transactions | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral details beyond annotations: pagination by row ID with inclusive/exclusive bounds, API cap of 1000 rows per window, and credential requirements. There is no contradiction with the readOnlyHint and other annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single paragraph with three sentences, each serving a purpose: stating the main function, explaining pagination mechanics, and suggesting usage. No redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core behavior, pagination constraints, and use cases. With an output schema assumed to exist, the description sufficiently prepares an agent for correct invocation without needing further external knowledge.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by explaining inclusivity/exclusivity of rows, the API cap, and default values. It also clarifies account_id as a numeric string from get_balances.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it lists ledger entries for a single account on the authenticated profile, paginated by row ID. This distinguishes it from siblings like list_orders or list_trades which target different resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit use cases: reconciliation, exports, or audit trails. It also explains the pagination iteration pattern. However, it does not explicitly state when not to use it or list alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
13 tool updates
v0.6.3- Added
cancel_order - Added
convert - Added
create_order - Added
get_balances - Added
get_candles - Added
get_markets_info - Added
get_order_book - Added
get_ticker - Added
get_tickers - Added
get_transaction - Added
list_orders - Added
list_trades - Added
list_transactions
13 tool updates
v0.6.2- Removed
cancel_order - Removed
convert - Removed
create_order - Removed
get_balances - Removed
get_candles - Removed
get_markets_info - Removed
get_order_book - Removed
get_ticker - Removed
get_tickers - Removed
get_transaction - Removed
list_orders - Removed
list_trades - Removed
list_transactions
13 tool updates
v0.6.1- Changed
cancel_order2 fields changed- changed
Input schema / properties / order_id / descriptionPrevious value: -"Order ID to cancel"New value: +"ID of the order to cancel, as returned by list_orders or create_order." - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "success": { + "type": "boolean" + } + }, + "required": [ + "success" + ], + "type": "object" +}
- Added
convert - Changed
create_order5 fields changed- changed
Input schema / properties / pair / descriptionPrevious value: -"Trading pair (e.g., XBTZAR)"New value: +"Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT." - changed
Input schema / properties / price / descriptionPrevious value: -"Limit price as a decimal string"New value: +"Limit price in the counter currency, as a decimal string (e.g. \"500000\"). Must align with the market's tick size; check get_markets_info." - changed
Input schema / properties / type / descriptionPrevious value: -"Order type (BUY or SELL)"New value: +"Side of the order. BUY = bid (buy the base currency with the counter currency); SELL = ask (sell the base currency for the counter currency)." - changed
Input schema / properties / volume / descriptionPrevious value: -"Order volume (amount of cryptocurrency to buy or sell)"New value: +"Order volume in the base currency, as a decimal string (e.g. \"0.001\"). Must meet the market's minimum volume and step size; check get_markets_info." - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "order_id": { + "type": "string" + } + }, + "required": [ + "order_id" + ], + "type": "object" +}
- Changed
get_balances3 fields changed- added
Input schema / propertiesAdded value: +{} - added
Input schema / requiredAdded value: +[] - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "balances": { + "items": { + "additionalProperties": false, + "properties": { + "account_id": { + "type": "string" + }, + "asset": { + "type": "string" + }, + "balance": { + "type": "string" + }, + "name": { + "type": "string" + }, + "reserved": { + "type": "string" + }, + "unconfirmed": { + "type": "string" + } + }, + "required": [ + "account_id", + "asset", + "balance", + "reserved", + "unconfirmed", + "name" + ], + "type": "object" + }, + "type": [ + "null", + "array" + ] + } + }, + "required": [ + "balances" + ], + "type": "object" +}
- Changed
get_candles6 fields changed- changed
Input schema / properties / duration / descriptionPrevious value: -"Candle duration in seconds (e.g., 60 for 1m, 300 for 5m, 3600 for 1h)"New value: +"Candle duration in seconds. Common values: 60 (1m), 300 (5m), 900 (15m), 1800 (30m), 3600 (1h), 10800 (3h), 14400 (4h), 28800 (8h), 86400 (1d), 259200 (3d), 604800 (1w). The Luno API only accepts a fixed set of durations; passing an unsupported value will return an error." - added
Input schema / properties / duration / minimumAdded value: +60 - changed
Input schema / properties / pair / descriptionPrevious value: -"Trading pair (e.g., XBTZAR)"New value: +"Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT." - changed
Input schema / properties / since / descriptionPrevious value: -"Filter to candles starting on or after this timestamp (Unix milliseconds). Defaults to 24 hours ago."New value: +"Start of the window as Unix epoch milliseconds (UTC). Defaults to 24 hours ago when omitted or 0." - added
Input schema / properties / since / minimumAdded value: +0 - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "candles": { + "items": { + "additionalProperties": false, + "properties": { + "close": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "high": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "low": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "open": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "timestamp": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "close", + "high", + "low", + "open", + "timestamp", + "volume" + ], + "type": "object" + }, + "type": [ + "null", + "array" + ] + }, + "duration": { + "type": "integer" + }, + "pair": { + "type": "string" + } + }, + "required": [ + "candles", + "duration", + "pair" + ], + "type": "object" +}
- Changed
get_markets_info3 fields changed- changed
Input schema / properties / pair / descriptionPrevious value: -"List of market pairs to return (e.g., XBTZAR,ETHZAR)"New value: +"Optional comma-separated list of pairs to filter to (e.g. \"XBTZAR,ETHZAR\"). Omit to return every supported market." - added
Input schema / requiredAdded value: +[] - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "markets": { + "items": { + "additionalProperties": false, + "properties": { + "base_currency": { + "type": "string" + }, + "counter_currency": { + "type": "string" + }, + "fee_scale": { + "type": "integer" + }, + "market_id": { + "type": "string" + }, + "max_price": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "max_volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "min_price": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "min_volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "price_scale": { + "type": "integer" + }, + "trading_status": { + "type": "string" + }, + "volume_scale": { + "type": "integer" + } + }, + "required": [ + "base_currency", + "counter_currency", + "fee_scale", + "market_id", + "max_price", + "max_volume", + "min_price", + "min_volume", + "price_scale", + "trading_status", + "volume_scale" + ], + "type": "object" + }, + "type": [ + "null", + "array" + ] + } + }, + "required": [ + "markets" + ], + "type": "object" +}
- Changed
get_order_book2 fields changed- changed
Input schema / properties / pair / descriptionPrevious value: -"Trading pair (e.g., XBTZAR)"New value: +"Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT." - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "asks": { + "items": { + "additionalProperties": false, + "properties": { + "price": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "price", + "volume" + ], + "type": "object" + }, + "type": [ + "null", + "array" + ] + }, + "bids": { + "items": { + "additionalProperties": false, + "properties": { + "price": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "price", + "volume" + ], + "type": "object" + }, + "type": [ + "null", + "array" + ] + }, + "timestamp": { + "type": "integer" + } + }, + "required": [ + "asks", + "bids", + "timestamp" + ], + "type": "object" +}
- Changed
get_ticker2 fields changed- changed
Input schema / properties / pair / descriptionPrevious value: -"Trading pair (e.g., XBTZAR)"New value: +"Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT." - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "ask": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "bid": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "last_trade": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "pair": { + "type": "string" + }, + "rolling_24_hour_volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "status": { + "type": "string" + }, + "timestamp": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "ask", + "bid", + "last_trade", + "pair", + "rolling_24_hour_volume", + "status", + "timestamp" + ], + "type": "object" +}
- Changed
get_tickers3 fields changed- changed
Input schema / properties / pair / descriptionPrevious value: -"Return tickers for multiple markets (e.g., XBTZAR,ETHZAR)"New value: +"Optional comma-separated list of pairs to filter to (e.g. \"XBTZAR,ETHZAR\"). Omit to return every supported pair." - added
Input schema / requiredAdded value: +[] - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "tickers": { + "items": { + "additionalProperties": false, + "properties": { + "ask": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "bid": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "last_trade": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "pair": { + "type": "string" + }, + "rolling_24_hour_volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "status": { + "type": "string" + }, + "timestamp": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "ask", + "bid", + "last_trade", + "pair", + "rolling_24_hour_volume", + "status", + "timestamp" + ], + "type": "object" + }, + "type": [ + "null", + "array" + ] + } + }, + "required": [ + "tickers" + ], + "type": "object" +}
- Changed
get_transaction3 fields changed- changed
Input schema / properties / account_id / descriptionPrevious value: -"Account ID"New value: +"Numeric account ID, as a string (from get_balances)." - changed
Input schema / properties / transaction_id / descriptionPrevious value: -"Transaction ID"New value: +"Row index of the transaction within the account, as a string. Obtain from list_transactions (row_index field)." - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "account_id": { + "type": "string" + }, + "available": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "available_delta": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "balance": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "balance_delta": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "currency": { + "type": "string" + }, + "description": { + "type": "string" + }, + "detail_fields": { + "additionalProperties": false, + "properties": { + "crypto_details": { + "additionalProperties": false, + "properties": { + "address": { + "type": "string" + }, + "txid": { + "type": "string" + } + }, + "required": [ + "address", + "txid" + ], + "type": "object" + }, + "trade_details": { + "additionalProperties": false, + "properties": { + "pair": { + "type": "string" + }, + "price": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "sequence": { + "type": "integer" + }, + "volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "pair", + "price", + "sequence", + "volume" + ], + "type": "object" + } + }, + "required": [ + "crypto_details", + "trade_details" + ], + "type": "object" + }, + "details": { + "additionalProperties": { + "type": "string" + }, + "type": "object" + }, + "kind": { + "type": "string" + }, + "reference": { + "type": "string" + }, + "row_index": { + "type": "integer" + }, + "timestamp": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "account_id", + "available", + "available_delta", + "balance", + "balance_delta", + "currency", + "description", + "detail_fields", + "details", + "kind", + "reference", + "row_index", + "timestamp" + ], + "type": "object" +}
- Changed
list_orders7 fields changed- added
Input schema / properties / limit / defaultAdded value: +100 - changed
Input schema / properties / limit / descriptionPrevious value: -"Maximum number of orders to return (default: 100)"New value: +"Maximum number of orders to return (1-100). Defaults to 100." - added
Input schema / properties / limit / maximumAdded value: +100 - added
Input schema / properties / limit / minimumAdded value: +1 - changed
Input schema / properties / pair / descriptionPrevious value: -"Trading pair (e.g., XBTZAR)"New value: +"Optional trading pair filter (e.g. \"XBTZAR\"). Omit to list orders across all pairs." - added
Input schema / requiredAdded value: +[] - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "orders": { + "items": { + "additionalProperties": false, + "properties": { + "base": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "completed_timestamp": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "counter": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "creation_timestamp": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "expiration_timestamp": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "fee_base": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "fee_counter": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "limit_price": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "limit_volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "order_id": { + "type": "string" + }, + "pair": { + "type": "string" + }, + "state": { + "type": "string" + }, + "time_in_force": { + "type": "string" + }, + "type": { + "type": "string" + } + }, + "required": [ + "base", + "completed_timestamp", + "counter", + "creation_timestamp", + "expiration_timestamp", + "fee_base", + "fee_counter", + "limit_price", + "limit_volume", + "order_id", + "pair", + "state", + "time_in_force", + "type" + ], + "type": "object" + }, + "type": [ + "null", + "array" + ] + } + }, + "required": [ + "orders" + ], + "type": "object" +}
- Changed
list_trades3 fields changed- changed
Input schema / properties / pair / descriptionPrevious value: -"Trading pair (e.g., XBTZAR)"New value: +"Trading pair using Luno's symbol convention (e.g. XBTZAR for BTC/ZAR, ETHZAR, XBTEUR). BTC is automatically rewritten to XBT." - changed
Input schema / properties / since / descriptionPrevious value: -"Fetch trades executed after this timestamp (Unix milliseconds)"New value: +"Optional lower bound as Unix epoch milliseconds (UTC), passed as a string. Only trades executed after this time are returned. Omit for the most recent trades." - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "trades": { + "items": { + "additionalProperties": false, + "properties": { + "is_buy": { + "type": "boolean" + }, + "price": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "sequence": { + "type": "integer" + }, + "timestamp": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "is_buy", + "price", + "sequence", + "timestamp", + "volume" + ], + "type": "object" + }, + "type": [ + "null", + "array" + ] + } + }, + "required": [ + "trades" + ], + "type": "object" +}
- Changed
list_transactions8 fields changed- changed
Input schema / properties / account_id / descriptionPrevious value: -"Account ID"New value: +"Numeric account ID, as a string (from get_balances)." - added
Input schema / properties / max_row / defaultAdded value: +100 - changed
Input schema / properties / max_row / descriptionPrevious value: -"Maximum row ID to return (for pagination, exclusive)"New value: +"Last row to return, exclusive. Defaults to 100 when omitted. The Luno API caps (max_row - min_row) at 1000." - added
Input schema / properties / max_row / minimumAdded value: +1 - added
Input schema / properties / min_row / defaultAdded value: +1 - changed
Input schema / properties / min_row / descriptionPrevious value: -"Minimum row ID to return (for pagination, inclusive)"New value: +"First row to return, inclusive (1-based). Defaults to 1 when omitted." - added
Input schema / properties / min_row / minimumAdded value: +1 - changed
Output schema / (root)Previous value: -nullNew value: +{ + "additionalProperties": false, + "properties": { + "id": { + "type": "string" + }, + "transactions": { + "items": { + "additionalProperties": false, + "properties": { + "account_id": { + "type": "string" + }, + "available": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "available_delta": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "balance": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "balance_delta": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "currency": { + "type": "string" + }, + "description": { + "type": "string" + }, + "detail_fields": { + "additionalProperties": false, + "properties": { + "crypto_details": { + "additionalProperties": false, + "properties": { + "address": { + "type": "string" + }, + "txid": { + "type": "string" + } + }, + "required": [ + "address", + "txid" + ], + "type": "object" + }, + "trade_details": { + "additionalProperties": false, + "properties": { + "pair": { + "type": "string" + }, + "price": { + "additionalProperties": false, + "properties": {}, + "type": "object" + }, + "sequence": { + "type": "integer" + }, + "volume": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "pair", + "price", + "sequence", + "volume" + ], + "type": "object" + } + }, + "required": [ + "crypto_details", + "trade_details" + ], + "type": "object" + }, + "details": { + "additionalProperties": { + "type": "string" + }, + "type": "object" + }, + "kind": { + "type": "string" + }, + "reference": { + "type": "string" + }, + "row_index": { + "type": "integer" + }, + "timestamp": { + "additionalProperties": false, + "properties": {}, + "type": "object" + } + }, + "required": [ + "account_id", + "available", + "available_delta", + "balance", + "balance_delta", + "currency", + "description", + "detail_fields", + "details", + "kind", + "reference", + "row_index", + "timestamp" + ], + "type": "object" + }, + "type": [ + "null", + "array" + ] + } + }, + "required": [ + "id", + "transactions" + ], + "type": "object" +}
1 tool update
v1.0.0- Changed
get_balances1 field changed- removed
Input schema / propertiesRemoved value: -{}
12 tool updates
- First observed
cancel_order - First observed
create_order - First observed
get_balances - First observed
get_candles - First observed
get_markets_info - First observed
get_order_book - First observed
get_ticker - First observed
get_tickers - First observed
get_transaction - First observed
list_orders - First observed
list_trades - First observed
list_transactions
TDQS
Each tool targets a distinct action or resource: orders (create, cancel, list), balances, candles, markets info, order book, tickers, trades, transactions. No overlapping purposes; descriptions clearly differentiate similar tools like get_ticker vs get_tickers and list_orders vs list_trades.
All tools follow a consistent verb_noun pattern using get, list, cancel, create, convert. The verbs are appropriately matched to the action (get for single items, list for collections), with no mixing of naming conventions.
13 tools is well-scoped for a crypto exchange API server, covering account management, market data, and trading operations without being overly numerous or sparse.
The tool set covers all essential operations for trading: account queries (balances, transactions), market data (tickers, order book, candles, trades, markets info), and order lifecycle (create, cancel, list) plus instant conversion. No obvious gaps for the intended trading use case.
Maintenance
Related MCP Connectors
MCP server for Hostinger API
A simple MCP server built with FastMCP and python
The official MCP Server for the Mux API
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides real-time cryptocurrency price data from OKX exchange through a Model Context Protocol interface, allowing access to historical candlestick data and current market prices for any trading instrument.21516MIT
- AlicenseBqualityAmaintenanceAn MCP server allowing Clients to interact with Xero Accounting Software1515521MIT
- FlicenseNot gradedqualityDmaintenanceConnects to the Coinbase Commerce API, allowing AI assistants like Claude to generate cryptocurrency payment links.-
- AlicenseBqualityCmaintenanceInteract with Upbit cryptocurrency exchange services to retrieve market data, manage accounts, and execute trades. Simplify your trading experience with tools for order management, deposits, withdrawals, and technical analysis.1017MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/luno/luno-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server