Search for content within an MDX file
AI agents call search_mdx to retrieve information from MDX MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves content from MDX files with no capability to modify, delete, or execute code. Search operations are inherently read-only with no side effects. Lowest severity due to limited blast radius if misused by an AI agent—worst case is information disclosure of already-stored content.
From the tool's definition Tool name 'search_mdx' and description 'Search for content within an MDX file' indicate data retrieval without modification. Server description emphasizes 'read, search, convert, and extract metadata' as core functions.
Attacks that exploit this kind of access
Search for content within an MDX file. It is categorised as a Read tool in the MDX MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MDX MCP Server MCP server in PolicyLayer and add a rule for search_mdx: 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 MDX MCP Server. Nothing to install.
search_mdx 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_mdx 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_mdx. 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_mdx is provided by the MDX MCP Server MCP server (llmtooling/mdx-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 →