Get the full directory entry for one API by its exact APIs.guru name/key (e.g. "stripe.com" or "googleapis.com:calendar"). Returns every version of that API with its info (title, description, provider, categories), last-updated date, docs link, and OpenAPI/Swagger spec URLs (swaggerUrl JSON + swa...
AI agents call get_api to retrieve information from Mcp Apis Guru without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Exact APIs.guru directory key, e.g. "stripe.com" or "googleapis.com:calendar". |
Parameters from the server's own tool schema.
This tool purely retrieves and returns metadata about public APIs from a directory. It reads existing data without creating, modifying, deleting, or executing anything. The output is informational only (specs, documentation links, metadata). An AI agent misusing this tool can only over-query or spam the directory—a low-severity read operation with negligible blast radius.
From the tool's definition Tool description states it 'Get[s] the full directory entry' and 'Returns every version of that API with its info...and OpenAPI/Swagger spec URLs.' The verb is retrieval/query with no modification capability.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Get the full directory entry for one API by its exact APIs.guru name/key (e.g. "stripe.com" or "googleapis.com:calendar"). Returns every version of that API with its info (title, description, provider, categories), last-updated date, docs link, and OpenAPI/Swagger spec URLs (swaggerUrl JSON + swaggerYamlUrl YAML), plus which version is preferred. Use this once you know the exact name (from search_apis) to fetch the spec URLs for an API. It is categorised as a Read tool in the Mcp Apis Guru MCP Server, which means it retrieves data without modifying state.
get_api accepts 1 parameter: name. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Apis Guru MCP server in PolicyLayer and add a rule for get_api: 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 Mcp Apis Guru. Nothing to install.
get_api is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_api 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 get_api. 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.
get_api is provided by the Mcp Apis Guru MCP server (https://gateway.pipeworx.io/apis-guru/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 →