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., "@Katana MCP Server Bridge 100 USDC from Ethereum to Katana"
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 interacting with the Katana network, providing seamless cross-chain bridging, DeFi operations, and Yearn vault management through AI assistants.
Cross-Chain Bridging
Bridge assets from Ethereum, Polygon, Arbitrum, and Base to Katana
Automatic deposit address generation
Support for major tokens (USDC, USDT, ETH, DAI, etc.)
SushiSwap Integration
Get real-time swap quotes
Execute token swaps with customizable slippage
Support for all major tokens on Katana
Yearn Vault Management
Deposit into yield-generating vaults
Withdraw from vault positions
View vault performance and user positions
Portfolio Management
Check token balances across all assets
Track Yearn vault positions
Monitor transaction history
Related MCP server: Universal Crypto MCP
Network | Chain ID | Minimum Deposit |
Ethereum | 1 | $50 |
Polygon | 137 | $2.5 |
Arbitrum | 42161 | $2.5 |
Base | 8453 | $2.5 |
Katana | 747474 | Destination |
ETH - Ethereum
USDC - USD Coin
USDT - Tether USD
WBTC - Wrapped Bitcoin
AUSD - Aave USD
USDS - USDS Stablecoin
yvUSDC - USDC Vault
yvETH - ETH Vault
yvUSDT - USDT Vault
yvWBTC - WBTC Vault
yvAUSD - AUSD Vault
Node.js 18.0.0 or higher
npm or pnpm package manager
A wallet private key with funds on supported networks
Add this server to your MCP-compatible AI assistant (like Claude Desktop):
{
"mcpServers": {
"katana-mcp": {
"command": "npx",
"args": ["katana-mcp"],
"env": {
"WALLET_PRIVATE_KEY": "your_private_key_here"
}
}
}
}Tool: bridgeAssets
Bridge tokens from supported chains to Katana network.
Parameters:
asset (string): Token symbol (e.g., 'USDC', 'ETH')
chain (string): Source chain ('ethereum', 'polygon', 'arbitrum', 'base')
amount (string): Amount to bridge (e.g., '100')
Example Usage:
Bridge 100 USDC from Ethereum to KatanaTool: getTokenBalances
Check your token balances on Katana network.
Parameters:
walletAddress (optional): Wallet address to check
Example Usage:
Show my token balances on KatanaTool: getYearnVaultInfo
Get detailed information about available Yearn vaults.
Example Usage:
Show me all available Yearn vaults on KatanaTool: depositToYearnVault
Deposit tokens into yield-generating vaults.
Parameters:
token (string): Token to deposit ('USDC', 'ETH', etc.)
amount (string): Amount to deposit
vaultTarget (string): Target vault ('USDC', 'ETH', 'WBTC', 'USDT', 'AUSD')
Example Usage:
Deposit 1000 USDC into the USDC vaultTool: withdrawFromYearnVault
Withdraw tokens from vault positions.
Parameters:
vaultAddress (string): Vault contract address
amount (string): Amount to withdraw
withdrawType (string): 'assets' or 'shares'
Tool: getUserYearnPositions
View your current vault positions and yields.
Example Usage:
Show my Yearn vault positionsTool: getSushiQuote
Get a quote for token swaps on SushiSwap.
Parameters:
tokenIn (string): Input token
tokenOut (string): Output token
amount (string): Amount to swap
maxSlippage (number): Maximum slippage percentage
Example Usage:
Get a quote to swap 1 ETH for USDC with 0.5% slippageTool: executeSushiSwap
Execute a token swap on SushiSwap.
Parameters:
tokenIn (string): Input token
tokenOut (string): Output token
amount (string): Amount to swap
maxSlippage (number): Maximum slippage percentage
Example Usage:
Swap 0.1 ETH for USDC with 2% slippage toleranceThe server includes comprehensive error handling for common issues:
Insufficient Balance: Clear messages about available vs required amounts
Network Issues: Automatic retry logic and helpful troubleshooting
Slippage Protection: Configurable slippage tolerance with sensible defaults
Gas Estimation: Automatic gas limit calculation with safety margins
Private Key Management: Secure environment variable handling
Transaction Simulation: Pre-execution validation to prevent failed transactions
Allowance Optimization: Efficient token approval management
Slippage Protection: Configurable MEV protection
Clone the repository
git clone https://github.com/yourusername/katana-mcp-server.git
cd katana-mcp-serverInstall dependencies
pnpm installEnvironment Configuration
Create a .env file in the root directory:
WALLET_PRIVATE_KEY=your_private_key_here⚠️ Security Warning: Never commit your private key to version control. Keep your .env file secure and private.
Build the project
pnpm run build
# or
npm run buildStart the server
pnpm run start
# or
npm run startkatana-mcp-server/
├── index.ts # Main server implementation
├── dist/ # Compiled JavaScript
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md We welcome contributions! Please see our contributing guidelines:
Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request
"WALLET_PRIVATE_KEY not found"
Ensure your .env file contains your private key
Verify the environment variable is correctly set
"Insufficient balance" errors
Check your token balance on the source chain
Ensure you have enough for gas fees
Verify minimum deposit requirements are met
Transaction failures
Try increasing slippage tolerance
Check network congestion
Ensure sufficient gas token balance
Bridge issues
Verify the token is supported on the source chain
Check minimum deposit amounts
Ensure wallet has sufficient balance
Issues: Open an issue on GitHub with detailed error messages
Discussions: Use GitHub Discussions for questions and feature requests
Documentation: Check this README and inline code comments
Bridge tokens from supported chains to Katana network. Automatically generates deposit address and sends tokens from your wallet. Also inform user their tokens will be automatically bridged to ETH on Katana.
| Name | Required | Description | Default |
|---|---|---|---|
| asset | Yes | Token symbol to bridge (e.g., 'USDC', 'ETH', 'DAI') | |
| chain | Yes | Source chain name (ethereum, polygon, base, arbitrum) | |
| amount | Yes | Amount to bridge in token units (e.g., '100' for 100 USDC) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full burden. It discloses that it auto-generates a deposit address and sends tokens, and that tokens become ETH on Katana. However, it omits details like permission requirements, reversibility, and error handling.
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 pack essential actions and a note about bridging to ETH. Concise but could be more structured; front-loads the main action.
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?
Missing output format or return behavior. Since there is no output schema, the description should explain what the tool returns (e.g., transaction hash), but it only says to 'inform user'. Also unclear if synchronous.
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 covers all three parameters (asset, chain, amount) with clear descriptions. The description adds no additional meaning beyond naming supported chains implicitly, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool bridges tokens to Katana, generates a deposit address, and sends tokens from the wallet. It explicitly distinguishes itself from sibling tools like swaps and vault deposits.
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. It does not mention prerequisites, chain specifics, or when not to bridge.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Deposit tokens into a Yearn vault on Katana network. Only works with tokens already on Katana (USDC, ETH, WBTC, USDT, AUSD).
| Name | Required | Description | Default |
|---|---|---|---|
| token | Yes | Token to deposit that's already on Katana (e.g., 'USDC', 'ETH', 'WBTC') | |
| amount | Yes | Amount to deposit in human-readable format (e.g., '100' for 100 USDC) | |
| vaultTarget | Yes | Target vault to deposit into (e.g., 'USDC' vault to get yvUSDC) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states basic functionality and token constraints, omitting important details like approval requirements, failure modes, gas implications, or return behavior for a deposit 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 consists of two sentences, each serving a clear purpose: stating the action and constraining usage. It is front-loaded with the core verb and resource, with no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a DeFi deposit operation, the description lacks critical context such as output (e.g., transaction hash), prerequisites (e.g., token approval), and potential error conditions. It is adequate for basic understanding but insufficient for safe and informed usage.
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 baseline is 3. The tool description adds no new parameter information beyond restating what the schema already provides (e.g., supported tokens). It does not enhance understanding of the parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Deposit tokens into a Yearn vault'), specifies the network ('Katana network'), and lists the supported tokens, distinguishing it from sibling tools like bridgeAssets or withdrawFromYearnVault.
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 that tokens must already be on Katana but does not explicitly state when to use this tool over bridging or swapping alternatives. It lacks when-not-to-use guidance and alternative recommendations, leaving usage context somewhat vague.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a token swap on SushiSwap on Katana network
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Amount to swap in human-readable format (e.g., '0.1' for 0.1 tokens) | |
| tokenIn | Yes | Input token symbol or address (e.g., 'USDC', 'ETH', or token address) | |
| tokenOut | Yes | Output token symbol or address (e.g., 'ETH', 'USDT', or token address) | |
| maxSlippage | No | Maximum slippage tolerance as percentage (e.g., 2.0 for 2%) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does not disclose side effects (gas, approval), auth needs, or return format. Minimal behavioral info.
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. Could benefit from more context while remaining concise, but it is not overly verbose.
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?
Lacks explanation of return values, preconditions (e.g., token approval), or output. For a swap execution tool, this is insufficient 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% and schema descriptions are clear and illustrative. The description adds no value beyond schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action ('Execute a token swap') and specific resource ('SushiSwap on Katana network'), distinguishing it from quote and bridge 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 guidance on when to use this tool vs alternatives like getSushiQuote for quotes or bridgeAssets for bridging. The agent lacks context on workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a quote for swapping tokens on SushiSwap on Katana network
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Amount to swap in human-readable format (e.g., '1.5' for 1.5 tokens) | |
| tokenIn | Yes | Input token symbol or address (e.g., 'ETH', 'USDC', or token address) | |
| tokenOut | Yes | Output token symbol or address (e.g., 'USDT', 'WBTC', or token address) | |
| maxSlippage | No | Maximum slippage tolerance as percentage (e.g., 0.5 for 0.5%) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the burden. It states 'get a quote', suggesting a read-only operation, but provides no additional behavioral traits (e.g., network latency, authentication needs). No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, highly concise with no wasted words, and front-loads the core purpose.
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 simple quote tool with no output schema, the description adequately conveys intent but lacks details on what the quote returns (e.g., price, pool). It is minimally complete but not rich.
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 covers all 4 parameters with descriptions (100% coverage), so the description adds minimal value beyond restating the human-readable format for amount. Baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets a quote for swapping tokens on SushiSwap on Katana network, specifying the verb, resource, and context, and distinguishes it from siblings like executeSushiSwap.
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 the tool is for obtaining a quote before swapping, but does not explicitly state when to use it versus alternatives like executeSushiSwap or other tools, leaving usage context ambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get token balances for your wallet on Katana network (uses address from private key in environment)
| 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 reveals that the tool uses the private key from the environment, but does not disclose error scenarios, rate limits, or whether it modifies state. It implies a read operation but lacks explicit safety guarantees.
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 concise sentence that efficiently conveys the tool's purpose and key constraint (wallet from environment). No extraneous 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?
The description is sufficient for a simple read tool with no parameters, but it lacks details on output format, network prerequisites, and error handling. Given no output schema, the description 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 no parameters, so schema coverage is 100%. The description adds context that the address is derived from environment, but since there are no parameters, the baseline of 3 is appropriate; no further param information needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets token balances for the user's wallet on the Katana network, using the address from the private key in the environment. It distinguishes itself from sibling tools like bridgeAssets and depositToYearnVault which are write operations.
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 token balances on Katana, but does not explicitly state when to use this tool over alternatives like getUserYearnPositions or getSushiQuote. No exclusions or when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed information about your Yearn vault positions (uses address from private key in environment)
| Name | Required | Description | Default |
|---|---|---|---|
| address | No | Optional: Wallet address to check Yearn positions for (defaults to address from private key in env) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It states it 'gets information' and uses the private key from environment, but does not explicitly confirm it is read-only, has no side effects, or requires specific permissions. For a read operation, this omission is significant. A 2 is appropriate as it adds some context but fails to assure agents of safety.
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 sentence of 16 words, front-loading the purpose. Every word earns its place; there is no filler. It is optimally concise for the information conveyed.
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, the description could mention what kind of information is returned (e.g., position details, balances). It is complete enough for a simple tool with one parameter, but the lack of return value context leaves agents uncertain about what to expect. Thus, a 3—adequate but with room for improvement.
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?
Only one parameter exists, and the schema description (100% coverage) already explains it well: 'Optional: Wallet address to check Yearn positions for (defaults to address from private key in env)'. The description reinforces this by mentioning the environment address, adding no contradiction. Parameter semantics are fully addressed.
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 detailed information about your Yearn vault positions'. It specifies the resource (Yearn vault positions) and the verb (Get). It also distinguishes from siblings like depositToYearnVault, withdrawFromYearnVault, and getYearnVaultInfo by focusing on positions rather than actions or vault metadata.
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 noting the address default from environment. It doesn't explicitly state when to use vs alternatives, but the sibling tools are action-oriented (bridge, deposit, withdraw, swap) vs this read-only query, so the usage is implicitly clear. Lack of explicit when-not or alternatives prevents a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed information about Yearn vaults on Katana network
| Name | Required | Description | Default |
|---|---|---|---|
| vaultAddress | No | Specific vault address to query (optional - if not provided, returns info for all known vaults) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must fully disclose behavior. It says 'Get detailed information' without specifying what fields or structure are returned, whether it is a read-only operation, or any potential performance implications. Lacks essential behavioral context for an agent.
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?
One concise sentence that conveys the primary purpose. No extraneous words. However, it could be slightly improved by adding structure or clarifying what 'detailed information' includes, but it remains efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks output schema and does not describe the returned data shape. Given no annotations and a single optional parameter, the description should at least hint at the fields or use cases (e.g., APY, TVL). Incomplete for an agent to reliably 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% for the single optional parameter vaultAddress, which is already well-described in the input schema. The tool description does not add additional meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description states a specific verb ('Get'), resource ('detailed information about Yearn vaults'), and scope ('on Katana network'). It clearly distinguishes from sibling tools like depositToYearnVault, withdrawFromYearnVault, and getUserYearnPositions which focus on user actions or positions rather than vault info.
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 prerequisites, such as needing to know vault addresses, or when it is appropriate to call before deposit or withdrawal operations. The description implies no exclusions but provides no explicit context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Withdraw tokens from a Yearn vault on Katana chain
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Amount of underlying tokens to withdraw (in token units, e.g., '1.5') | |
| vaultAddress | Yes | Address of the Yearn vault to withdraw from | |
| withdrawType | No | Whether to withdraw by asset amount or share amount | assets |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must disclose behavior. The description only states it withdraws tokens, implying a destructive mutation, but does not mention any required approvals, gas costs, or potential side effects.
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 short sentence, which is efficient. However, it lacks structured detail for a complex operation, preventing a perfect score.
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 tool has 3 parameters and no output schema. The description is minimal and does not explain the return value, error states, or the effect of different withdraw types, making it incomplete for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (all parameters have descriptions). The tool description adds no additional meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('withdraw') and the resource ('tokens from a Yearn vault on Katana chain'). It distinguishes the tool from sibling tools like depositToYearnVault.
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 mention of prerequisites (e.g., need to have deposited tokens, need vault address), and no explanation of when to use each withdraw type.
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.
v1.3.0bridgeAssetsdepositToYearnVaultexecuteSushiSwapgetSushiQuotegetTokenBalancesgetUserYearnPositionsgetYearnVaultInfowithdrawFromYearnVaultEach tool targets a distinct operation: bridging assets, swapping on SushiSwap (with a separate quote tool), and Yearn vault actions (deposit, withdraw, info). No two tools have overlapping purposes.
All tool names follow a consistent camelCase verb_noun pattern (e.g., bridgeAssets, getTokenBalances, depositToYearnVault). Verbs like 'get', 'execute', 'deposit', 'withdraw' are used consistently.
With 8 tools covering bridging, swapping, and yield operations, the count is well-scoped for the server's purpose. Each tool serves a clear role without redundancy.
The tool set covers core workflows: bridging, swapping with quotes, and full Yearn vault management. Minor gaps exist (e.g., no approval tool or token listing), but agents can execute the primary actions without dead ends.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Non-custodial DeFi for AI agents: swaps, concentrated liquidity (V3/V4) zaps + ranges, 5 EVM chains
Token swaps and honeypot/rug checks for AI agents on 8 chains, paid per-call in USDC via x402.
DeFi safety layer for AI agents: wallet safety, token risk, tx decode/simulate. 20 tools.
Non-custodial DeFi tools for AI agents on Solana: swaps, perps, lending, staking, equities.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/PlayAINetwork/Katana_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server