Call any public Relay API endpoint with full parameters and get the raw, unfiltered response. Use get_api_schema first to discover endpoints and their parameter schemas, then use this tool to call them. This gives you access to all API features that the dedicated tools simplify away — for example...
AI agents invoke execute_api_call to trigger actions in Relay MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool permits an AI agent to execute arbitrary API calls to a blockchain bridge/swap protocol with user-controlled parameters. While individual read-only queries might seem benign, the ability to call 'any' endpoint with 'full parameters' creates risk of: (1) executing unauthorized token swaps/bridges with user funds, (2) manipulating swap parameters to extract value, (3) exploiting protocol vulnerabilities via…
From the tool's definition Tool description states it can 'Call any public Relay API endpoint with full parameters and get the raw, unfiltered response' and mentions accessing 'all API features' without restriction.
Attacks that exploit this kind of access
Call any public Relay API endpoint with full parameters and get the raw, unfiltered response. Use get_api_schema first to discover endpoints and their parameter schemas, then use this tool to call them. This gives you access to all API features that the dedicated tools simplify away — for example: - Full /quote/v2 params: slippageTolerance, appFees, includedSwapSources, useExternalLiquidity, topupGas, maxRouteLength, etc. - Full response data: detailed fee breakdowns, route objects, slippage details, protocol data, swap impact - Endpoints without dedicated tools: /price (lightweight pricing), /currencies/v2, /execute/* (with pre-signed data) - Advanced /requests/v2 query params: sortBy, sortDirection, includeOrderData, referrer, includeChildTxs For common operations (simple quotes, token search, chain status), prefer the dedicated tools — they validate inputs, resolve chain names/token symbols, and format responses. Use this tool when you need parameters or response fields those tools don. It is categorised as a Execute tool in the Relay MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Relay MCP Server MCP server in PolicyLayer and add a rule for execute_api_call: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Relay MCP Server. Nothing to install.
execute_api_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_api_call rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for execute_api_call. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
execute_api_call is provided by the Relay MCP Server MCP server (relayprotocol/relay-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →