Enables analysis of Aave V3 liquidation opportunities on Ethereum mainnet, including real-time health factor monitoring, position tracking, risk assessment, and liquidation profit estimation for DeFi lending positions.
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., "@Aave Liquidation MCP Server check if 0x742d35Cc6634C0532925a3b844Bc454e4438f44e is at risk of liquidation"
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.
A Model Context Protocol (MCP) server for analyzing Aave V3 liquidation opportunities on Ethereum mainnet. This tool enables AI assistants like Claude to interact with Aave protocol data, monitor user positions, and identify liquidation opportunities.
Real-time health factor calculation for any Ethereum address
Multi-threshold risk detection:
HEALTHY: Health Factor > 1.05
AT_RISK: 1.0 < HF < 1.05
LIQUIDATABLE: HF < 1.0
Automatic risk level classification (HIGH, MEDIUM, LOW)
Account summary with collateral, debt, and borrow capacity
Detailed position breakdown by asset
Profit estimation for liquidation opportunities
Collateral and debt composition analysis
Liquidation bonus calculation (asset-specific)
Risk scoring based on multiple factors
Complete portfolio view for any address
Asset-by-asset breakdown of deposits and borrows
Collateral status for each asset
Real-time balance updates from on-chain data
Check up to 20 addresses simultaneously
Parallel processing for faster results
Summary statistics (liquidatable count, at-risk count, etc.)
Bulk risk assessment for portfolio monitoring
Real-time asset prices from Aave oracle
USD-denominated values for all positions
Reserve (asset) listing with full configuration
LTV, liquidation thresholds, and bonuses by asset
Current block number for data verification
Related MCP server: Datai MCP Server
Unlike existing liquidation bots that execute liquidations, this MCP server focuses on:
Analysis over Execution: Provides data and insights rather than executing transactions
AI-First Design: Optimized for integration with AI assistants via MCP protocol
Educational Value: Helps users understand DeFi liquidation mechanics
Research Tool: Useful for strategy development and risk analysis
Node.js 18 or higher
An Ethereum RPC endpoint (Alchemy, Infura, QuickNode, or your own node)
Clone or download this repository
Install dependencies:
npm installConfigure environment variables:
cp .env.example .env
# Edit .env and add your Ethereum RPC URLBuild the project:
npm run buildCreate a .env file in the project root:
# Required: Ethereum RPC endpoint
ETHEREUM_RPC_URL=https://eth-mainnet.g.alchemy.com/v2/YOUR_API_KEY
# Optional: Health factor warning threshold (default: 1.05)
HEALTH_FACTOR_THRESHOLD=1.05You can get a free Ethereum RPC endpoint from:
Alchemy: https://www.alchemy.com/ (Recommended, 300M compute units/month free)
Infura: https://www.infura.io/ (100k requests/day free)
QuickNode: https://www.quicknode.com/ (Free tier available)
Add this server to your Claude Desktop configuration file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"aave-liquidation": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/aave-liquidation-mcp/build/index.js"],
"env": {
"ETHEREUM_RPC_URL": "https://eth-mainnet.g.alchemy.com/v2/YOUR_API_KEY"
}
}
}
}Replace /ABSOLUTE/PATH/TO/ with the actual path to your installation.
Test the server functionality without MCP configuration:
# Get current ETH price
npm run demo:price
# View all Aave reserves (categorized)
npm run demo:reserves
# Run comprehensive connection test
npm run test:real-dataget_user_healthGet health factor and account data for a specific address.
Input:
{
"address": "0x742d35Cc6634C0532925a3b844Bc454e4438f44e"
}Output:
{
"address": "0x742d35Cc6634C0532925a3b844Bc454e4438f44e",
"healthFactor": "1.234",
"totalCollateralUSD": "150000.00",
"totalDebtUSD": "100000.00",
"availableBorrowsUSD": "20000.00",
"liquidationThreshold": "0.85",
"ltv": "0.80",
"isLiquidatable": false,
"isAtRisk": false,
"status": "HEALTHY"
}analyze_liquidationAnalyze a position for liquidation opportunity with detailed breakdown.
Input:
{
"address": "0x742d35Cc6634C0532925a3b844Bc454e4438f44e"
}Output:
{
"userAddress": "0x742d35Cc6634C0532925a3b844Bc454e4438f44e",
"healthFactor": "0.98",
"totalCollateralUSD": "150000.00",
"totalDebtUSD": "140000.00",
"riskLevel": "HIGH",
"potentialProfit": "7000.00",
"collateralAssets": [...],
"debtAssets": [...]
}get_user_positionsGet detailed collateral and debt positions for an address.
Input:
{
"address": "0x742d35Cc6634C0532925a3b844Bc454e4438f44e"
}get_aave_reservesGet list of all available Aave V3 reserves with their configurations.
Input: None required
Output: List of all reserves with LTV, liquidation threshold, liquidation bonus, etc.
get_asset_priceGet current USD price for a specific asset from Aave oracle.
Input:
{
"assetAddress": "0xC02aaA39b223FE8D0A0e5C4F27eAD9083C756Cc2"
}get_protocol_statusGet Aave V3 protocol status and current block number.
Input: None required
batch_check_addressesCheck multiple addresses at once for liquidation opportunities (max 20 addresses per request).
Input:
{
"addresses": [
"0x742d35Cc6634C0532925a3b844Bc454e4438f44e",
"0xAnotherAddress...",
"0xYetAnotherAddress..."
]
}Output:
{
"totalChecked": 3,
"liquidatable": 1,
"atRisk": 1,
"healthy": 1,
"results": [...]
}validate_addressValidate if a string is a properly formatted Ethereum address.
Input:
{
"address": "0x742d35Cc6634C0532925a3b844Bc454e4438f44e"
}Output:
{
"address": "0x742d35Cc6634C0532925a3b844Bc454e4438f44e",
"isValid": true,
"message": "Valid Ethereum address format"
}Once configured with Claude Desktop, you can ask questions like:
Single Address Queries:
"Check the health factor for address 0x742d35Cc6634C0532925a3b844Bc454e4438f44e"
"Are there any liquidation opportunities for this address?"
"What are the collateral positions for this user?"
"Analyze this address for liquidation risk: 0x..."
Batch Operations:
"Check these 5 addresses for liquidation risk: [paste addresses]"
"Monitor multiple wallets and tell me which ones are at risk"
"Compare liquidation risk across these addresses"
Protocol Queries:
"Show me all available assets in Aave V3"
"What's the current price of WETH in Aave?"
"What are the liquidation parameters for USDC?"
"What's the current block number?"
Validation:
"Is this a valid Ethereum address: 0x123..."
"Validate these addresses before I check them"
After installing and configuring the server, restart Claude Desktop and verify it's working:
Ask Claude:
Can you check the Aave protocol status?Claude will use the get_protocol_status tool and should return something like:
{
"protocol": "Aave V3",
"network": "Ethereum Mainnet",
"blockNumber": 18500000,
"poolAddress": "0x87870Bca3F3fD6335C3F4ce8392D69350B4fA4E2",
"status": "operational"
}> 1.0: Position is healthy
< 1.05: Position is at risk (warning)
< 1.0: Position can be liquidated
HIGH: Health factor < 1.0 (immediately liquidatable)
MEDIUM: Health factor between 1.0 and 1.02
LOW: Health factor between 1.02 and 1.05
When a position is liquidated, the liquidator receives a bonus (typically 5-10% depending on the asset). The potentialProfit field estimates this bonus.
aave-liquidation-mcp/
āāā src/
ā āāā index.ts # MCP server implementation
ā āāā aave-client.ts # Aave protocol interaction logic
ā āāā constants.ts # Contract addresses and ABIs
ā āāā types.ts # TypeScript type definitions
āāā build/ # Compiled JavaScript output
āāā package.json
āāā tsconfig.json
āāā .env # Configurationnpm run buildnpm run devThis will watch for file changes and recompile automatically.
Pool: 0x87870Bca3F3fD6335C3F4ce8392D69350B4fA4E2
Pool Data Provider: 0x7B4EB56E7CD4b454BA8ff71E4518426369a138a3
Oracle: 0x54586bE62E3c3580375aE3723C145253060Ca0C2
@modelcontextprotocol/sdk: MCP protocol implementation
ethers: Ethereum library for contract interaction
dotenv: Environment variable management
Mainnet Only: Currently supports Ethereum mainnet only
Read-Only: Does not execute liquidations, only analyzes opportunities
Rate Limits: Subject to your RPC provider's rate limits
Gas Estimation: Profit calculations are estimates and don't account for gas costs
Multi-chain support (Arbitrum, Optimism, Polygon, Base)
Historical liquidation data and analytics
Advanced profit calculations including gas costs
Webhook notifications for at-risk positions
Integration with The Graph for historical queries
Support for Aave V2 alongside V3
MIT
Contributions are welcome! Please feel free to submit a Pull Request.
This tool is for educational and research purposes only. Liquidating positions on DeFi protocols involves financial risk. Always do your own research and understand the risks before participating in DeFi activities.
Analyze a user position for liquidation opportunity. Returns detailed information including collateral assets, debt assets, risk level, and potential profit.
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | Ethereum address to analyze (must be a valid address) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It states the tool returns 'detailed information' but doesn't disclose behavioral traits like whether this is a read-only operation, requires authentication, has rate limits, or what happens with invalid addresses. The description is functional but lacks critical operational context for a financial analysis tool.
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 zero waste: first states purpose, second describes return values. Appropriately sized and front-loaded with the core function. Could be slightly more structured but earns its place efficiently.
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 single-parameter tool with no annotations and no output schema, the description provides adequate purpose and return value overview. However, it lacks completeness regarding error conditions, authentication needs, and detailed behavioral context that would be important for a liquidation analysis tool in financial systems.
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% (address parameter fully documented in schema), so baseline is 3. The description adds no additional parameter semantics beyond what's in the schema - it doesn't explain address format requirements, network context, or validation behavior.
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: 'Analyze a user position for liquidation opportunity' with specific verb ('analyze') and resource ('user position'). It distinguishes from siblings like 'get_user_positions' (which likely lists positions) by focusing on liquidation analysis, but doesn't explicitly contrast with 'get_user_health' which might provide similar risk assessment.
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 when assessing liquidation risk ('for liquidation opportunity'), but provides no explicit guidance on when to use this versus alternatives like 'get_user_health' or 'get_user_positions'. No prerequisites, exclusions, or comparative context are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Batch check multiple Ethereum addresses for liquidation opportunities. Returns a summary of all addresses with their health status.
| Name | Required | Description | Default |
|---|---|---|---|
| addresses | Yes | Array of Ethereum addresses to check (max 20 addresses) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only states what the tool does and returns, without disclosing behavioral traits like rate limits, authentication requirements, data freshness, or what 'health status' entails. It mentions a 'summary' but doesn't describe format or detail level.
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 with zero waste: the first states the action and purpose, the second specifies the return. It's front-loaded with the core functionality and appropriately sized for a single-parameter tool.
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 batch operation tool with no annotations and no output schema, the description adequately covers purpose and basic behavior but lacks details on output format, error handling, or performance characteristics. Given the complexity (batch processing) and missing structured data, it's minimally complete but has clear 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 description coverage is 100%, with the parameter 'addresses' fully documented in the schema (array of strings, max 20). The description adds no additional parameter semantics beyond implying the addresses are Ethereum-specific, which is already clear from the schema description. 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 specific action ('batch check'), target resource ('multiple Ethereum addresses'), and purpose ('for liquidation opportunities'), with the return value specified. It distinguishes from siblings like 'analyze_liquidation' (which likely analyzes individual cases) and 'validate_address' (which validates format rather than checking health).
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 when needing to check multiple addresses for liquidation opportunities, but provides no explicit guidance on when to use this vs. alternatives like 'get_user_health' (for single addresses) or 'analyze_liquidation' (for detailed analysis). No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get list of all available reserves (assets) in Aave V3 protocol with their configuration.
| 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 a list with configuration, but does not disclose critical traits like whether it's read-only, requires authentication, has rate limits, or details the return format. 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, efficient sentence that front-loads the key action and resource. It uses minimal words to convey the essential information without any waste, making it 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 (simple read operation with 0 parameters) and lack of annotations/output schema, the description is adequate but has clear gaps. It explains what the tool does but misses behavioral context and usage guidelines. This meets the minimum viable standard but could be more complete.
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 0 parameters with 100% coverage, so no parameter information is needed. The description does not add parameter details, which is acceptable here. Baseline is 4 for 0 parameters, as it avoids redundancy and focuses on the tool's purpose.
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 verb 'Get' and the resource 'list of all available reserves (assets) in Aave V3 protocol with their configuration.' It specifies the scope (all available reserves) and the protocol version (V3). However, it does not explicitly differentiate from siblings like 'get_asset_price' or 'get_user_positions,' which would require a 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 does not mention when-not scenarios or refer to sibling tools for related tasks, such as using 'get_asset_price' for pricing data or 'get_user_positions' for user-specific reserves. This lack of context leaves usage unclear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get current price for a specific asset from Aave oracle.
| Name | Required | Description | Default |
|---|---|---|---|
| assetAddress | Yes | Token contract address |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but offers minimal behavioral insight. It states it 'gets' data (implying read-only), but doesn't disclose rate limits, error conditions, authentication needs, or what 'current' means (e.g., real-time vs. cached). It adds little beyond the basic 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 with zero waste. It's front-loaded with the core purpose and appropriately sized for a simple tool. Every word 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 low complexity (1 parameter, no output schema, no annotations), the description is minimally adequate. It covers the basic 'what' but lacks context on usage, behavior, or output format. For a read-only tool, it meets the bare minimum but leaves 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 description coverage is 100%, with the parameter 'assetAddress' documented as 'Token contract address'. The description adds no additional meaning beyond this, such as format examples or validation rules. Baseline 3 is appropriate as the schema handles 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 a specific verb ('Get') and resource ('current price for a specific asset'), and identifies the data source ('from Aave oracle'). It doesn't explicitly distinguish from siblings like 'get_aave_reserves', but the focus on price vs. reserves is implied. No tautology or misleading elements.
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 prerequisites, exclusions, or compare to sibling tools (e.g., 'get_aave_reserves' for broader data). Usage is implied by the purpose but lacks explicit context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get general Aave V3 protocol status including current block number.
| 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 full burden. It states it's a read operation ('Get'), implying safety, but doesn't disclose behavioral traits such as rate limits, authentication needs, error conditions, or what 'general protocol status' entails beyond block number.
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 front-loads the core purpose and includes specific details, making it easy 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 has no parameters, no output schema, and no annotations, the description is adequate but minimal. It covers the basic purpose but lacks details on return format, error handling, or broader context needed for full agent understanding.
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 with 100% schema coverage, so no parameter documentation is needed. The description adds value by specifying what information is retrieved ('general Aave V3 protocol status including current block number'), which is appropriate for a parameterless tool.
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 verb 'Get' and the resource 'general Aave V3 protocol status', including specific content 'current block number'. It doesn't explicitly differentiate from siblings like 'get_aave_reserves' or 'get_user_health', but the purpose is unambiguous.
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. It doesn't mention prerequisites, timing, or comparisons to sibling tools like 'get_aave_reserves' for reserve data or 'get_user_health' for user-specific status.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get health factor and account data for a specific Ethereum address on Aave V3. Returns collateral, debt, and liquidation status.
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | Ethereum address to check (must be a valid address) |
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. While it states the tool returns specific data (collateral, debt, liquidation status), it doesn't describe error handling, rate limits, authentication needs, or whether it's a read-only operation. For a tool with zero 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, well-structured sentence that efficiently conveys the tool's purpose and output. It is front-loaded with the core action and resource, with no wasted words or 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?
Given the tool's moderate complexity (single parameter, no output schema, no annotations), the description is minimally adequate. It covers the purpose and return values but lacks details on behavioral traits, error handling, and usage context. Without annotations or an output schema, it doesn't fully compensate for these 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?
The schema description coverage is 100%, with the parameter 'address' fully documented in the input schema. The description adds no additional parameter semantics beyond what the schema provides, such as format examples or edge cases. With high schema coverage, the baseline score 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 the specific action ('Get health factor and account data'), the resource ('for a specific Ethereum address on Aave V3'), and the scope ('Returns collateral, debt, and liquidation status'). It distinguishes itself from siblings like 'get_user_positions' by focusing on health metrics rather than general positions.
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 for checking health metrics on Aave V3, but provides no explicit guidance on when to use this tool versus alternatives like 'analyze_liquidation' or 'get_user_positions'. It doesn't mention prerequisites, exclusions, or comparative contexts with sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed breakdown of a user collateral and debt positions across all Aave V3 assets.
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | Ethereum address to query |
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 detailed breakdown'), implying a read-only operation, but doesn't specify if it requires authentication, has rate limits, returns real-time or cached data, or handles errors. For a tool with no annotations, 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 directly states the tool's purpose without unnecessary words. It is front-loaded with the core action and scope, making it easy to parse quickly. Every part of the sentence earns its place by specifying key details.
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 (querying financial positions across assets), lack of annotations, and no output schema, the description is minimally adequate. It covers the purpose but misses behavioral traits, usage context, and return value details. For a tool with no structured support, it should do more to compensate, but it meets the basic threshold.
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 100% description coverage, with the 'address' parameter clearly documented as an 'Ethereum address to query'. The description adds no additional parameter details beyond what the schema provides, such as format examples or validation rules. Baseline 3 is appropriate since 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 with a specific verb ('Get') and resource ('user collateral and debt positions'), specifying the scope ('across all Aave V3 assets'). It distinguishes from siblings like 'get_user_health' by focusing on detailed breakdowns rather than health metrics, but doesn't explicitly differentiate from all siblings like 'batch_check_addresses'.
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 prerequisites, exclusions, or compare with siblings like 'get_user_health' for health-focused queries or 'batch_check_addresses' for multiple addresses. Usage is implied by the purpose but lacks explicit context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Validate if a string is a valid Ethereum address format.
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | Address string to validate |
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 validates format but does not specify what constitutes a valid Ethereum address (e.g., checksum, length), whether it performs network checks, or what the output looks like (e.g., boolean, error details). This leaves significant gaps for a tool with no annotation coverage.
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 unnecessary words. It directly states the tool's function, making it easy to parse and understand 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 lack of annotations and output schema, the description is incomplete. It does not explain the validation criteria, return values, or error handling, which are critical for understanding how to use this tool effectively. The description alone is insufficient for a tool with no structured behavioral data.
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 input schema already documents the single parameter 'address' as a string to validate. The description adds no additional parameter semantics beyond what the schema provides, such as format examples or validation rules, meeting the baseline for high schema 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 clearly states the specific action ('validate') and resource ('Ethereum address format'), distinguishing it from siblings like batch_check_addresses (which handles multiple addresses) or get_user_positions (which retrieves user data). It precisely communicates the tool's function without ambiguity.
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 for validating Ethereum addresses, but provides no explicit guidance on when to use this tool versus alternatives like batch_check_addresses for multiple addresses or other siblings for unrelated tasks. It lacks context on prerequisites or exclusions.
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.
analyze_liquidationbatch_check_addressesget_aave_reservesget_asset_priceget_protocol_statusget_user_healthget_user_positionsvalidate_addressScored across 8 tools
Most tools have distinct purposes, such as analyzing liquidations, checking addresses, getting reserves, and fetching user health. However, 'get_user_health' and 'get_user_positions' could be slightly overlapping, as both provide user-specific data, but their descriptions clarify that one focuses on health status while the other gives a detailed breakdown of positions.
All tool names follow a consistent verb_noun pattern using snake_case, such as 'analyze_liquidation', 'batch_check_addresses', and 'get_user_health'. This uniformity makes the set predictable and easy to understand, with no deviations in naming conventions.
With 8 tools, the server is well-scoped for its purpose of monitoring and analyzing Aave V3 liquidation opportunities. Each tool serves a specific function, from data retrieval to validation, without feeling bloated or insufficient for the domain.
The tool set covers key aspects like analyzing liquidations, checking user health, fetching asset prices, and validating addresses, providing a solid foundation for liquidation workflows. A minor gap is the lack of tools for executing liquidations or interacting with smart contracts, which could limit full automation, but the existing tools support comprehensive analysis and monitoring.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Official Aave MCP for V3 and V4 markets, positions, governance, and transaction preparation.
Aave - 6 tools for lending rates, supply, and borrow data
Crypto yield data for AI agents: lending, savings, staking, borrowing & stablecoin rates. 18 tools.
Real-time Ethereum liquidation intelligence for AI agents and MEV bots.
