Scan the project and discover all AI_README.md files. Returns an index of all README files with their paths, scopes, and coverage patterns.
AI agents call discover_ai_readmes to retrieve information from Ai Readme without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
projectRoot | string | Yes | The root directory of the project. Use the current working directory (e.g., from environment or pwd). If unsure, pass the project root path. |
excludePatterns | array | — | Glob patterns to exclude (e.g., ['node_modules/**', '.git/**']) |
Parameters from the server's own tool schema.
This tool performs a read-only scan operation that indexes existing AI_README.md files. It retrieves and returns data about file locations, scopes, and patterns without altering any state. This is a classic Read operation with minimal risk — the worst outcome of misuse would be information disclosure about the project structure.
From the tool's definition Tool description states it 'Scan[s] the project and discover[s]' and 'Returns an index' — purely informational retrieval with no side effects. No modifications, deletions, or external operations are performed.
Documented attack patterns abuse exactly the kind of access discover_ai_readmes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ai Readme, and nothing reaches the server without passing your rules. This is the rule we recommend for discover_ai_readmes:
{
"version": "1",
"default": "deny",
"tools": {
"discover_ai_readmes": {}
}
}discover_ai_readmes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Scan the project and discover all AI_README.md files. Returns an index of all README files with their paths, scopes, and coverage patterns. It is categorised as a Read tool in the Ai Readme MCP Server, which means it retrieves data without modifying state.
discover_ai_readmes accepts 2 parameters: projectRoot, excludePatterns. Required: projectRoot. The full parameter table on this page comes from the server's own tool schema.
Register the Ai Readme MCP server in PolicyLayer and add a rule for discover_ai_readmes: 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 Ai Readme. Nothing to install.
discover_ai_readmes 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 discover_ai_readmes 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 discover_ai_readmes. 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.
discover_ai_readmes is provided by the Ai Readme MCP server (ai-readme-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ai Readme, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Ai Readme tools catalogued and risk-classified — across an index of 43,000+ MCP servers.