A read-only MCP server that lets AI assistants query live data from the Tegro Finance DEX on the TON blockchain — no API keys, wallets, or transaction signing required.
List all liquidity pools (tegro_dex_pools): Retrieve all DEX liquidity pools with reserves, fees, LP supply, USD TVL, and APYs.
Find pools for a specific token (tegro_dex_pools_for_token): Look up all liquidity pools containing a given token by its jetton master address.
Browse the token registry (tegro_dex_assets): Get the full list of tradable tokens, including symbols, decimals, contract addresses, and flags.
Get token market data (tegro_dex_token): Fetch price, holder count, liquidity, market cap, and trust score for any individual token.
Quote a swap (tegro_dex_quote_swap): Simulate an exact-input swap to see how much of a target token you'd receive for a given offer amount, with configurable slippage tolerance — no transaction is built or signed.
List liquid staking pools (tegro_staking_pools): View all Tegro liquid-staking pools (e.g., stgTON) with APY, minimum stake, and active status.
Get live staking rate (tegro_staking_rate): Retrieve the live stgTON→TON exchange rate for a specific staking pool (returned as a 1e9 fixed-point value).
Allows an AI assistant to read liquidity pools, token prices, swap quotes, and liquid-staking (stgTON) rates from the Tegro Finance DEX on the TON blockchain.
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., "@Tegro Finance DEX MCP Server Quote 100 TON to USDT on Tegro"
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.
Tegro Finance MCP — a TON DeFi / DEX Model Context Protocol server. It lets an AI assistant (Claude, Cursor, ChatGPT, …) read live Tegro Finance DEX data on TON — pools, token prices, swap quotes and liquid‑staking (stgTON) rates — in plain language. AI access to live Tegro TON DEX data, with no wallet permissions.
Read‑only & non‑custodial. No API keys, no wallet, no signing — nothing that can move funds. It only reads the public Tegro Finance API. Just run it.
Tool | What it does |
| All liquidity pools — reserves, fees, TVL, APYs |
| Pools that contain a given token |
| The tradable‑token registry |
| Price / holders / liquidity / trust score for a token |
| Quote an exact‑in swap (read‑only; no tx built) |
| Liquid‑staking pools (stgTON & others) + APY |
| Live stgTON→TON rate for a pool |
Related MCP server: TON BLOCKCHAIN MCP
Requires Node.js ≥ 18. No account, no keys, no env — the
whole command is just:
npx -y @tegroton/tegro-finance-mcpWire that into any MCP client:
claude_desktop_config.json (macOS:
~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"tegro-finance": { "command": "npx", "args": ["-y", "@tegroton/tegro-finance-mcp"] }
}
}claude mcp add tegro-finance -- npx -y @tegroton/tegro-finance-mcp.cursor/mcp.json (project) or Settings → MCP → Add:
{
"mcpServers": {
"tegro-finance": { "command": "npx", "args": ["-y", "@tegroton/tegro-finance-mcp"] }
}
}Same entry — command: "npx", args: ["-y", "@tegroton/tegro-finance-mcp"], no
env. Add it to the client's MCP-servers list (Windsurf: Cascade MCP config;
VS Code: Cline → MCP Servers; ChatGPT: Developer mode / MCP). For a ChatGPT
custom GPT instead, see integrations/chatgpt-gpt.md.
"What are the top Tegro Finance pools by TVL right now?"
"Quote 100 TON → USDT on Tegro and show the price impact."
"What's the current stgTON liquid-staking APY and rate?"
"Show price, holders and liquidity for token <address>."
"Which Tegro pools include <token>?"
Thin wrapper over the official @tegroton/tegro-finance
SDK, which reads the public Tegro Finance API. The SDK is non‑custodial: building
or signing a real swap happens in the user's own wallet and is intentionally
not part of this read‑only server.
SDK — tegro-finance-sdk · @tegroton/tegro-finance — typed read/quote/build client + TON Connect adapter (powers this server)
DEX API — API-DEX-TON-Blockchain — the public DEX REST API
Liquid staking — ton-gram-staking-docs — stgTON docs, contracts & API
App — tegro.finance · Docs — docs.tegro.finance
Same read-only API, every assistant — see integrations/: llms.txt, an agent guide, a curated OpenAPI, a ChatGPT custom-GPT recipe, and Hermes/function-calling tools. llms.txt is live at https://tegro.finance/llms.txt.
Telegram @tegrofinance · X @TegroDEX
Read‑only. No keys, no signing, no funds. Outbound HTTPS only to the Tegro Finance API. See SECURITY.md.
npm install
npm run build
node dist/index.js # stdio MCP serverMIT © TegroTON
The list of tradable tokens (symbol, decimals, contract address, flags).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only states output structure without behavioral details (e.g., pagination, rate limits). Adequate but minimal.
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?
Single sentence, no wasted words. Efficient and 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?
Description is sufficient for a simple list tool with no parameters. Could mention if result is paginated or contains all tokens, but not critical.
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?
Input schema has zero parameters (100% coverage). Description adds meaning by specifying output fields, which is useful for an agent.
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 lists tradable tokens with specific fields (symbol, decimals, contract address, flags). Distinguishes from sibling tools like tegro_dex_token which likely retrieves a single token.
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?
No guidance on when to use this tool vs alternatives like tegro_dex_token. Lacks context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
All liquidity pools with reserves, fees, LP supply, USD TVL and APYs. The TON sentinel address is EQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAM9c.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only states 'All liquidity pools' and a sentinel address. Lacks disclosure of rate limits, pagination, or data freshness. Mutation behavior not applicable, but still minimal transparency.
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 with no redundancy. First sentence clearly lists output contents; second sentence provides a sentinel address, which may be extraneous but not harmful.
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?
No output schema, so description must detail return values. Lists fields but does not specify structure (e.g., array vs object) or pagination. Adequate for a simple list but missing some context.
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 in input schema (0 params), so schema coverage is 100% trivially. Description adds value by listing returned data fields, compensating for lack of output 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 lists all liquidity pools and enumerates specific data fields (reserves, fees, LP supply, USD TVL, APYs). It is distinct from siblings like tegro_dex_pools_for_token but does not explicitly differentiate.
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?
No guidance on when to use this tool versus alternatives. Does not mention any prerequisites or intended use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Liquidity pools that contain the given token (by jetton master address).
| Name | Required | Description | Default |
|---|---|---|---|
| tokenAddress | Yes | Jetton master address (EQ…/UQ…) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description should disclose behavioral traits. However, it only states what the tool returns without mentioning permissions, rate limits, or safety. While it implies a read operation, this is not explicit.
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, efficient sentence with no wasted words. It is front-loaded with the key action and resource.
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 output schema and no annotations, the description is adequate for a simple parameter query. However, it lacks details on the structure of returned pools, which could be provided for completeness.
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?
The schema covers the single parameter with a description ('Jetton master address (EQ…/UQ…)'). The description adds context ('by jetton master address') but does not provide additional meaning beyond what the schema already offers.
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 retrieves liquidity pools containing a specific token, using the jetton master address. It distinguishes itself from sibling tools like 'tegro_dex_pools' (all pools) and 'tegro_dex_token' (token info) by specifying the token-specific filter.
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?
No explicit guidance on when to use this tool versus alternatives. The description implies usage for finding pools by token, but does not mention when to choose other tools like 'tegro_dex_pools' or 'tegro_dex_token'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Simulate an exact-in swap: how much of the ask token you'd receive for a given amount of the offer token. No transaction is built or signed.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Human amount of the offer token, e.g. 1.5 | |
| decimals | No | Offer token decimals (default 9) | |
| slippage | No | Slippage tolerance, e.g. 0.01 = 1% (default 0.01) | |
| askAddress | Yes | Token you want | |
| offerAddress | Yes | Token you give (use EQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAM9c for TON) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It conveys the simulation nature and lack of transaction execution, but doesn't disclose behavior around slippage handling, error responses, or whether it returns the best route. Adequate but not detailed.
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, clear sentence that front-loads the core purpose. No wasted words; every part 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?
No output schema exists, and the description only vaguely hints at the return value ('how much you'd receive') without specifying format (number vs object), additional fields (price impact, fee), or error behavior. This leaves agents guessing about the response structure.
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 the input schema already documents each parameter. The description adds no significant parameter-level detail beyond noting the TON address convention for offerAddress. 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 explicitly states 'Simulate an exact-in swap' and specifies the input/output relationship (how much ask token for offer amount). It clearly distinguishes from sibling tools like tegro_dex_assets or tegro_dex_pools by focusing on quoting a swap.
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 clearly states this is read-only ('No transaction is built or signed'), implying it's for estimation before execution. It doesn't explicitly exclude use cases or provide alternatives, but the context from sibling tools makes the purpose clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Price, holders, liquidity, market cap and trust score for one token.
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | Jetton master address |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden; it explains what data is returned but lacks details on side effects, safety, or constraints like read-only nature or rate limits. It does not contradict any 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, efficient sentence that conveys core functionality without redundancy or 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?
Despite no output schema, the description lists key return fields. It is adequate for a simple read tool with one parameter, though it could elaborate on output structure or error handling.
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?
Input schema coverage is 100% with one parameter ('address') clearly described. The tool description adds no further semantic detail beyond the schema, warranting the baseline score.
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 provides 'Price, holders, liquidity, market cap and trust score for one token,' which is specific and distinguishes it from sibling tools like 'tegro_dex_assets' (listing) and 'tegro_dex_pools_for_token' (pools).
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 no guidance on when to use this tool versus alternatives, no instructions on prerequisites or conditions, and no explicit 'when not to use' advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tegro liquid-staking pools (stgTON and others): APY, min stake, active flag.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses that the tool returns APY, min stake, and active flag for pools. However, it does not mention data freshness, caching behavior, or whether the list is filtered (e.g., only active pools). For a simple read-only tool with no parameters, this is adequate but not fully transparent.
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 concise sentence that front-loads the resource ('Tegro liquid-staking pools') and immediately lists the key data points. No wasted words; every part 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?
The description is fairly complete for a simple listing tool with no parameters, but it lacks explicit mention that it returns a list of all pools (implied by 'pools' plural) and does not clarify if filtering by active status is possible. Without an output schema, the agent might need more detail about the response structure.
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?
The input schema has no parameters, so schema description coverage is 100%. The description adds meaning by specifying the output fields (APY, min stake, active flag), which is essential since the schema is empty. Given the 0-param baseline of 4, the description fulfills this role.
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 identifies the resource ('Tegro liquid-staking pools') and lists the key fields returned (APY, min stake, active flag). However, it lacks an explicit verb like 'list' or 'retrieve', and the phrase 'and others' is vague. It is distinct from sibling tools like 'tegro_staking_rate' which likely returns a single rate.
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?
No guidance is provided on when to use this tool versus alternatives. Sibling tools such as 'tegro_dex_pools' and 'tegro_staking_rate' exist, but the description does not clarify the intended use case or conditions for choosing this tool over others.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Live rate for a staking pool — price is the stgTON→TON rate (1e9 fixed point) and only appreciates.
| Name | Required | Description | Default |
|---|---|---|---|
| masterAddress | Yes | Staking master, e.g. stgTON EQC-DUl20SfQFVH34cky8N76la1K0Uu5UWjel5IEn7mjIrfc |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description mentions the rate 'only appreciates' and the fixed-point representation (1e9), providing some behavioral insight. However, without annotations, it omits details like authentication needs or safety implications.
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?
A single sentence delivers the core purpose and key detail ('price is the stgTON→TON rate and only appreciates') efficiently. No 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 low complexity (one param, no output schema), the description covers the essential meaning. However, it could mention the response format or additional fields for completeness.
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 a single parameter 'masterAddress' described. The description adds minor context ('Staking master, e.g. stgTON...') but does not significantly enhance 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 provides a 'Live rate for a staking pool' and specifies the price field meaning. It distinguishes from sibling tools like tegro_staking_pools (which lists pools) and DEX tools.
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?
No explicit guidance on when to use this tool vs alternatives. The description implies usage for getting a live rate, but fails to mention exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a distinct purpose: asset listing, pool listing, pool filtering by token, swap quoting, token details, staking pools, and staking rate. No overlap in functionality.
All tools follow the pattern tegro_{domain}_{descriptive_noun} (e.g., tegro_dex_assets, tegro_staking_pools). Consistent prefixing and naming convention.
With 7 tools covering both DEX and staking functionalities, the count is well-scoped. Each tool serves a clear purpose without redundancy or unnecessary bloat.
The tool set covers key informational aspects of a DEX (assets, pools, quotes, token info) and staking (pools, rates). Missing write/transaction capabilities, but that appears intentional for a read-only server.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Tenzro Network MCP server: wallet, identity, payments, inference, staking, bridges, verification.
Read-only THORChain swap quotes, liquidity pools, and network status.
MCP server giving AI agents one-connection access to crypto & DeFi data: DeFi protocol TVL, stableco
Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TegroTON/tegro-finance-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
