AI agents call search_markdown to retrieve information from Md without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches markdown content without modifying, deleting, or executing operations. The server explicitly states it retrieves data without embeddings or uploading. Confidence is 0.75 rather than higher because the description is empty, but the name and server context provide strong indicators this is a retrieval operation.
From the tool's definition Tool name 'search_markdown' strongly indicates searching/querying documentation. Server context confirms it exposes 'local markdown documentation, notes, and knowledge bases' for retrieval.
Attacks that exploit this kind of access
search_markdown. It is categorised as a Read tool in the Md MCP Server, which means it retrieves data without modifying state.
Register the Md MCP server in PolicyLayer and add a rule for search_markdown: 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 Md. Nothing to install.
search_markdown 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 search_markdown 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 search_markdown. 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.
search_markdown is provided by the Md MCP server (ly2xxx/md-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 →