The DeFi Rates MCP Server provides AI agents with real-time access to DeFi lending data, rates, and on-chain events across 14+ protocols and multiple blockchains (Ethereum, Arbitrum, Base, BSC, Solana, HyperEVM, Optimism, Polygon, Avalanche, Gnosis).
Key capabilities:
Query real-time lending rates - Get current borrowing and supply rates across major protocols (Aave, Morpho, Compound, Venus, Lista, Spark, Euler, Drift, Jupiter, HypurrFi, and more)
Find best rates - Search for lowest borrow rates or highest supply yields for specific assets across all platforms and chains
Search earn/vault products - Access single-asset yield products like Spark stUSDS, Morpho Vaults, and other deposit-only markets that earn yield without borrowing
Compare platforms - Side-by-side comparison of borrow/supply rates across different protocols for the same asset-collateral pair
Calculate leverage strategies - Compute looping strategy metrics including leverage multiplier, liquidation price, and interest costs for collateralized positions
Monitor on-chain events - Track real-time lending activities including borrows, deposits, withdrawals, repays, liquidations, and flashloans
Track whale activity - Identify significant lending events (over $100K USD) across protocols
Get DeFi Borrow Index (DBI) - Access weighted average of stablecoin borrow rates as a market benchmark
Flexible filtering - Filter and sort results by chain, protocol, asset, collateral, event type, or minimum amounts
Usage analytics - View server usage statistics including call volumes, success rates, and unique clients
Provides access to real-time DeFi lending rates and earn markets across Ethereum-based protocols including Aave, Morpho, Compound, Spark, Fluid, and Euler, with tools for querying rates, comparing platforms, and calculating leverage strategies.
Provides access to DeFi lending rates on Optimism through Aave and Compound V3 protocols, enabling rate queries and platform comparisons.
Provides access to DeFi lending rates on Polygon through Aave and Compound V3 protocols, enabling rate queries and platform comparisons.
Provides access to real-time DeFi lending rates and earn markets on Solana through Drift, Jupiter, and Felix protocols, with tools for querying rates and comparing platforms.
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., "@DeFi Rates MCP Server show me the best USDC supply rates across all platforms"
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.
Remote MCP server providing real-time DeFi lending data for AI agents.
Give Claude and other AI assistants the power to query DeFi rates, monitor whale activity, and track on-chain lending events in real-time!
https://defiborrow.loan/mcpNo installation required - just configure your MCP client to use the HTTP endpoint.
Related MCP server: Aave Liquidation MCP Server
14+ Protocols: Aave, Morpho, Compound, Venus, Lista, Spark, Felix, Euler, Drift, Jupiter, HypurrFi & more
Real-time Data: Updated hourly from production DeFi protocols
8 Powerful Tools: Query rates, track whales, monitor liquidations, find best yields
Multi-Chain: Ethereum, Arbitrum, Base, BSC, Solana, HyperEVM
On-chain Events: Real-time lending event monitoring (borrows, deposits, liquidations)
Usage Stats: Built-in analytics at /mcp/stats
get_recent_eventsGet recent on-chain lending events (borrows, deposits, liquidations, repays).
Parameter | Type | Description |
| number | Number of events (default: 20, max: 100) |
| string | Filter by blockchain |
| string | Filter by protocol |
get_events_by_typeGet lending events filtered by event type.
Parameter | Type | Description |
| string | Required. One of: |
| number | Number of events (default: 20) |
| string | Filter by blockchain |
get_whale_activityGet large lending events (whale activity >$100K USD).
Parameter | Type | Description |
| number | Minimum USD amount (default: 100000) |
| number | Number of events (default: 20) |
| string | Filter by blockchain |
| string | Filter by event type |
get_liquidationsGet recent liquidation events across all protocols.
Parameter | Type | Description |
| number | Number of events (default: 20) |
| string | Filter by blockchain |
| string | Filter by protocol |
get_lending_ratesGet current lending/borrowing rates across DeFi protocols.
Parameter | Type | Description |
| string | Filter by blockchain |
| string | Filter by platform (AAVE, Morpho, Compound, etc.) |
| string | Filter by borrow asset (USDC, USDT, ETH, etc.) |
| string | Filter by collateral asset |
| number | Number of results (default: 50) |
get_earn_marketsGet earn/yield markets (single-asset deposits like Spark stUSDS, Morpho Vaults).
Parameter | Type | Description |
| string | Filter by blockchain |
| string | Filter by platform |
| string | Filter by deposit asset |
| number | Minimum APY percentage |
| number | Number of results (default: 50) |
find_best_borrowFind the lowest borrowing rate for a specific asset across all platforms.
Parameter | Type | Description |
| string | Required. Asset to borrow (USDC, USDT, ETH, etc.) |
| string | Limit search to specific chain |
| number | Return top N results (default: 5) |
find_best_yieldFind the highest deposit/supply yield for a specific asset.
Parameter | Type | Description |
| string | Required. Asset to deposit |
| string | Limit search to specific chain |
| boolean | Include vaults/staking (default: true) |
| number | Return top N results (default: 5) |
Run this command to add the remote MCP server:
claude mcp add --transport http defi-lending-pro https://defiborrow.loan/mcpVerify configuration:
claude mcp listEdit your config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"defi-lending-pro": {
"type": "url",
"url": "https://defiborrow.loan/mcp"
}
}
}Save and restart Claude Desktop. Look for the plug icon to verify connection.
Use the HTTP transport with endpoint:
POST https://defiborrow.loan/mcp
Content-Type: application/json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list",
"params": {}
}After setup, try asking:
"What's the lowest USDC borrow rate right now?"
"Show me ETH lending rates on Ethereum"
"Compare USDC/WETH rates between Aave and Morpho"
"Where can I get the best yield on USDC?"
"What's the APY for Spark stUSDS?"
"Find the top 5 highest yield stablecoin products"
"Any recent whale lending activity?"
"Show me large borrows over $500K"
"What are the latest liquidations on Ethereum?"
"Show me recent flashloans"
"Get the latest deposit events on Aave"
"What lending activity happened in the last hour?"
The server implements Model Context Protocol (JSON-RPC 2.0 over HTTP).
Supported Methods:
initialize - Initialize connection
tools/list - List available tools
tools/call - Execute a tool
resources/list - List resources (empty)
prompts/list - List prompts (empty)
View usage stats at:
GET https://defiborrow.loan/mcp/stats?days=7Returns:
Total calls and success rate
Calls by method and tool
Unique clients
Daily breakdown
Average response time
Protocol | Chains | Type |
Aave | Ethereum, Arbitrum, Base, Optimism, Polygon, Avalanche, Gnosis | Lending |
Morpho | Ethereum, Base | Lending + Vaults |
Compound V3 | Ethereum, Arbitrum, Base, Optimism, Polygon | Lending |
Venus | BSC | Lending |
Lista | BSC | Lending + Earn |
Spark | Ethereum, Gnosis | Lending + Earn (stUSDS 12%+ APY) |
Fluid | Ethereum, Arbitrum, Base | Lending |
HyperLend | HyperEVM | Lending |
HypurrFi | HyperEVM | Lending |
Euler | Ethereum, Arbitrum, Base | Lending + Vaults |
Drift | Solana | Lending |
Jupiter | Solana | Lending |
Felix | Solana | Earn |
Update Frequency: Hourly
This service is registered as an ERC-8004 AI Agent:
Agent ID: #283
Network: Base Sepolia
Registry: View on BaseScan
Learn more about ERC-8004 - the AI Agent Trust Layer standard.
Website: https://defiborrow.loan
MCP Endpoint: https://defiborrow.loan/mcp
Usage Stats: https://defiborrow.loan/mcp/stats
ERC-8004 Page: https://defiborrow.loan/?type=erc8004
npm Package: @asahi001/defi-rates-mcp
MIT
Calculate the leverage looping strategy metrics including leverage multiplier, liquidation price, and interest costs.
| Name | Required | Description | Default |
|---|---|---|---|
| platform | Yes | The lending platform to use | |
| asset | Yes | The asset to borrow | |
| collateral | Yes | The collateral asset | |
| collateralAmount | Yes | Amount of collateral tokens | |
| collateralPrice | Yes | Current price of collateral in USD | |
| ltv | Yes | Target LTV ratio (percentage, e.g., 75 for 75%) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool calculates metrics but doesn't reveal whether this is a read-only operation, if it requires authentication, rate limits, computational cost, or what format the results take. For a financial calculation tool with 6 parameters and no annotations, this leaves significant behavioral gaps.
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 clearly states the tool's purpose. Every word earns its place: 'calculate' (verb), 'leverage looping strategy metrics' (resource), and the three specific metrics calculated. There's no wasted text or unnecessary elaboration.
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?
For a financial calculation tool with 6 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain the return format, error conditions, or how the calculated metrics relate to the input parameters. While concise, it lacks necessary context for an agent to understand what to expect from invoking this 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?
The schema description coverage is 100%, so all parameters are documented in the schema. The description doesn't add any parameter-specific information beyond what's in the schema descriptions. It mentions the metrics calculated but doesn't explain how parameters like 'ltv' or 'collateralPrice' specifically affect those calculations. Baseline 3 is appropriate when schema does the heavy lifting.
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 purpose: calculating specific metrics (leverage multiplier, liquidation price, interest costs) for a leverage looping strategy. It uses specific verbs ('calculate') and identifies the resource ('leverage looping strategy metrics'), but doesn't explicitly differentiate from sibling tools like 'compare_platforms' or 'search_best_rates' which might overlap in financial analysis contexts.
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. It doesn't mention sibling tools like 'compare_platforms' or 'search_best_rates' that might be relevant for similar financial calculations, nor does it specify prerequisites or appropriate contexts for leverage looping strategy analysis versus other financial tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compare borrow/supply rates across different platforms for the same asset pair.
| Name | Required | Description | Default |
|---|---|---|---|
| asset | Yes | The borrow asset | |
| collateral | Yes | The collateral asset | |
| chain | No | Optional: filter by blockchain |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what the tool does but doesn't explain how it behaves: e.g., whether it fetches real-time or cached data, if there are rate limits, what the output format looks like, or any error conditions. For a tool with no annotation coverage, this leaves significant gaps in understanding its operation.
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 directly states the tool's purpose without any fluff. It's appropriately sized and front-loaded, making it easy to understand at a glance.
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 (comparing rates across platforms), lack of annotations, and no output schema, the description is incomplete. It doesn't cover behavioral aspects like data freshness, output format, or error handling, which are crucial for effective use. The description alone is insufficient for an agent to fully understand how to invoke and interpret results.
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%, so the schema already documents all three parameters (asset, collateral, chain) with descriptions. The description adds no additional parameter semantics beyond what's in the schema, such as format examples or constraints. Baseline 3 is appropriate when the schema does the heavy lifting.
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 purpose: 'Compare borrow/supply rates across different platforms for the same asset pair.' It specifies the action (compare), the data (borrow/supply rates), and the scope (different platforms, same asset pair). However, it doesn't explicitly differentiate from sibling tools like 'search_best_rates' or 'get_latest_rates', which prevents a perfect score.
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. It doesn't mention when this comparison is needed, what distinguishes it from 'search_best_rates' or 'get_latest_rates', or any prerequisites. The user must infer usage from the purpose alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the DBI (DeFi Borrow Index) - a weighted average of stablecoin borrow rates across major protocols.
| 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 carries the full burden of behavioral disclosure. It states the tool retrieves data ('Get'), implying a read-only operation, but does not specify if it requires authentication, has rate limits, or details about the return format (e.g., numeric value, timestamp, protocol breakdown). For a tool with zero annotation coverage, this is a significant gap in 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?
The description is a single, well-structured sentence that front-loads the purpose and provides essential context without any wasted words. It is appropriately sized for a no-parameter tool, making it highly concise and easy to parse.
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 (0 parameters, no output schema, no annotations), the description is complete enough to understand what the tool does. However, it lacks details on behavioral aspects like authentication or return format, which are important for an agent to use it effectively. This makes it adequate but with clear gaps in contextual information.
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 tool has 0 parameters, and schema description coverage is 100%, so no parameter documentation is needed. The description appropriately does not discuss parameters, which is efficient. A baseline of 4 is applied as it avoids unnecessary details while matching the schema's completeness.
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 specific action ('Get') and resource ('DBI (DeFi Borrow Index)'), with a precise definition of what the DBI represents ('a weighted average of stablecoin borrow rates across major protocols'). This distinguishes it from sibling tools like get_latest_rates or get_earn_markets by focusing on a specific composite index rather than raw rates or 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?
The description provides no guidance on when to use this tool versus alternatives like get_latest_rates or compare_platforms. It does not mention any prerequisites, contexts where it is preferred, or scenarios where other tools might be more appropriate, leaving the agent without usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get single-asset earn/vault products (no collateral required). Includes Morpho Vaults, Spark sUSDS/stUSDS, Compound cTokens, AAVE aTokens, etc. These are simple deposit products that earn yield without borrowing.
| Name | Required | Description | Default |
|---|---|---|---|
| platform | No | Filter by platform (e.g., Morpho, Spark, Compound, AAVE, Lista, Felix, Euler) | |
| chain | No | Filter by blockchain (e.g., ethereum, arbitrum, base, bsc, solana) | |
| asset | No | Filter by deposit asset (e.g., USDC, USDT, stUSDS, sUSDS, WETH, SOL) | |
| limit | No | Maximum number of results to return (default: 10) | |
| sort | No | Optional sorting (supply_highest for best APY, supply_lowest for lowest APY) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. While it mentions the product type and lack of collateral, it doesn't describe response format, pagination behavior, rate limits, authentication needs, or error conditions. For a data-fetching tool with 5 parameters, this leaves significant behavioral gaps.
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 efficiently structured in two sentences: the first states purpose and scope, the second clarifies the product type. Every word earns its place with zero redundancy, making it easy to parse while being information-dense.
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 5 parameters, no annotations, and no output schema, the description provides adequate purpose and product context but lacks sufficient behavioral and response information. It covers what the tool does but not how it behaves or what it returns, leaving gaps for a tool with filtering capabilities.
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%, providing good documentation for all 5 parameters. The description adds minimal parameter semantics by listing example platforms and assets, but doesn't provide additional context beyond what's in the schema. Baseline 3 is appropriate when schema does the heavy lifting.
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 purpose with specific verbs ('Get single-asset earn/vault products') and resources ('Morpho Vaults, Spark sUSDS/stUSDS, Compound cTokens, AAVE aTokens'), distinguishing it from siblings by focusing on deposit-only yield products without collateral requirements. It explicitly differentiates from borrowing-related tools that might exist elsewhere.
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 implies usage context by specifying 'simple deposit products that earn yield without borrowing,' suggesting this tool is for yield-seeking rather than borrowing/looping strategies. However, it doesn't explicitly state when to use it versus alternatives like 'search_best_rates' or 'get_latest_rates,' nor does it mention prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the latest DeFi lending rates (collateralized borrowing markets). You can filter by platform, chain, asset, or collateral.
| Name | Required | Description | Default |
|---|---|---|---|
| platform | No | Filter by platform (e.g., Aave, Morpho, Compound, Venus, Lista, HyperLend, Fluid, HypurrFi, Euler, Drift, Jupiter) | |
| chain | No | Filter by blockchain (e.g., ethereum, arbitrum, base, bsc, solana, hyperevm) | |
| asset | No | Filter by borrow asset (e.g., USDC, USDT, WETH, WBTC) | |
| collateral | No | Filter by collateral asset (e.g., ETH, WETH, WBTC, SOL) | |
| limit | No | Maximum number of results to return (default: 10) | |
| sort | No | Optional sorting for rates (e.g., borrow_lowest for cheapest borrow rates) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves 'latest' rates, implying real-time or recent data, but doesn't specify data freshness, rate limits, error handling, or authentication needs. For a read operation with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves in practice, such as whether it's idempotent or has performance constraints.
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 appropriately sized and front-loaded, consisting of two concise sentences. The first sentence states the core purpose, and the second explains filtering options without redundancy. Every sentence earns its place by adding value, making it efficient and easy to parse for an agent.
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 (6 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain what the tool returns (e.g., rate structures, timestamps), how results are formatted, or any limitations like pagination. For a data-fetching tool with multiple filters, more context on output and usage constraints is needed to guide the agent effectively.
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 description adds minimal value beyond the input schema, which has 100% coverage. It lists filterable attributes ('platform, chain, asset, or collateral') but doesn't provide additional context like examples or constraints beyond what's in the schema descriptions. With high schema coverage, the baseline is 3, as the description doesn't compensate with extra semantic details, such as explaining interactions between parameters or default behaviors.
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 purpose: 'Get the latest DeFi lending rates (collateralized borrowing markets).' It specifies the verb ('Get'), resource ('latest DeFi lending rates'), and scope ('collateralized borrowing markets'), making the action and domain explicit. However, it doesn't distinguish this tool from sibling tools like 'search_best_rates' or 'compare_platforms', which likely serve related but different purposes in rate analysis.
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. It mentions filtering capabilities but doesn't explain how this differs from siblings such as 'search_best_rates' or 'compare_platforms', leaving the agent to infer usage context. There's no mention of prerequisites, exclusions, or specific scenarios where this tool is preferred over others.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find the best borrow or supply rates for a specific asset.
| Name | Required | Description | Default |
|---|---|---|---|
| asset | Yes | The asset to search for (e.g., USDC, USDT, WETH) | |
| type | Yes | Whether to search for best borrow rates (lowest) or supply rates (highest) | |
| chain | No | Optional: filter by blockchain | |
| limit | No | Number of results to return (default: 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'finds' rates, implying a read-only operation, but doesn't cover critical aspects like rate limits, authentication needs, data freshness, or what 'best' means (e.g., sorted order, criteria). For a tool with no annotation coverage, this leaves significant gaps in understanding its behavior.
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 front-loads the core purpose without any wasted words. It's appropriately sized for a tool with clear parameters and no complex output schema, making it easy for an agent to parse quickly.
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 moderate complexity (4 parameters, no output schema, no annotations), the description is minimally adequate. It covers the purpose but lacks usage guidelines, behavioral details, and output information. Without annotations or an output schema, the agent is left with gaps in understanding how to interpret results or handle edge cases, making it incomplete for optimal use.
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%, so the schema fully documents all parameters. The description adds no additional meaning beyond what's in the schema—it mentions 'specific asset' and 'borrow or supply rates', which are already covered by the 'asset' and 'type' parameter descriptions. With high schema coverage, the baseline is 3, as the description doesn't compensate but doesn't detract either.
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 purpose: 'Find the best borrow or supply rates for a specific asset.' It specifies the verb ('find'), resource ('rates'), and scope ('specific asset'), distinguishing it from siblings like 'get_latest_rates' or 'compare_platforms' by focusing on best rates. However, it doesn't explicitly differentiate from 'get_earn_markets' or 'calculate_looping_strategy', which might involve rate-related operations, so it's not a perfect 5.
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. It doesn't mention sibling tools like 'compare_platforms' or 'get_latest_rates', nor does it specify prerequisites or exclusions. The agent must infer usage from the purpose alone, which is insufficient for optimal tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0calculate_looping_strategycompare_platformsget_dbi_indexget_earn_marketsget_latest_ratessearch_best_ratesEach tool has a clearly distinct purpose with no overlap: calculate_looping_strategy focuses on leverage metrics, compare_platforms compares rates across platforms, get_dbi_index retrieves a specific index, get_earn_markets lists deposit products, get_latest_rates provides lending rates, and search_best_rates finds optimal rates. The descriptions clearly differentiate their functions, eliminating any ambiguity.
The tool names follow a consistent verb_noun pattern (e.g., calculate_looping_strategy, compare_platforms, get_dbi_index) with all using snake_case. However, there is a minor deviation with 'search_best_rates' using 'search' instead of 'get' or 'compare', which slightly breaks the pattern but remains readable and coherent.
With 6 tools, the count is well-scoped for a DeFi rates server, covering key areas like strategy calculation, rate comparison, index retrieval, market listings, and rate searches. Each tool earns its place without redundancy, making it efficient for agents to navigate and use.
The tool set provides comprehensive coverage for DeFi rates, including borrowing, lending, deposits, and strategy analysis. Minor gaps exist, such as no explicit tools for historical rate trends or protocol-specific detailed analytics, but agents can work around these using the available tools for core workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Crypto yield data for AI agents: lending, savings, staking, borrowing & stablecoin rates. 18 tools.
Aave - 6 tools for lending rates, supply, and borrow data
Loan & mortgage calculator, compound interest, ROI, crypto prices, FX conversion for AI agents.
Evidence-based market data for AI agents deploying capital in DeFi. Empirical, not advertised.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/qingfeng/defi-rates-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
