Full-text search of documents by title.
AI agents call refmd-search-documents to retrieve information from RefMD MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs full-text search queries against Markdown documents, which is a read-only operation that retrieves data without modification, deletion, or execution of code. It poses minimal risk as it only returns search results from existing documents. No side effects or state changes occur from using this tool.
From the tool's definition Tool description explicitly states 'Full-text search of documents by title' and 'search' is a quintessential read operation.
Attacks that exploit this kind of access
Full-text search of documents by title. It is categorised as a Read tool in the RefMD MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RefMD MCP Server MCP server in PolicyLayer and add a rule for refmd-search-documents: 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 RefMD MCP Server. Nothing to install.
refmd-search-documents 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 refmd-search-documents 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 refmd-search-documents. 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.
refmd-search-documents is provided by the RefMD MCP Server MCP server (refmdio/mcp-server). 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 →