⭐ PREFERRED SEARCH: Use this INSTEAD OF Grep for finding code by description. Natural language search with BM25 ranking. Saves 70-90% tokens vs reading files directly. Examples:
AI agents call get_relevant_context to retrieve information from MCP Context Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries code data without side effects. It enables navigation and information lookup through natural language processing, which is a read-only operation. The emphasis on token efficiency and reducing file reads further confirms it is a retrieval mechanism. No creation, modification, deletion, or execution of arbitrary commands is indicated.
From the tool's definition Tool performs 'Natural language search with BM25 ranking' to 'find code by description' and 'query specific code symbols and logic.' The description explicitly positions it as a search alternative to grep for retrieval purposes with no modification capability…
Documented attack patterns abuse exactly the kind of access get_relevant_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Context Manager, and nothing reaches the server without passing your rules. This is the rule we recommend for get_relevant_context:
{
"version": "1",
"default": "deny",
"tools": {
"get_relevant_context": {}
}
}get_relevant_context 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.
⭐ PREFERRED SEARCH: Use this INSTEAD OF Grep for finding code by description. Natural language search with BM25 ranking. Saves 70-90% tokens vs reading files directly. Examples:. It is categorised as a Read tool in the MCP Context Manager MCP Server, which means it retrieves data without modifying state.
Register the MCP Context Manager MCP server in PolicyLayer and add a rule for get_relevant_context: 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 Context Manager. Nothing to install.
get_relevant_context 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_relevant_context 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_relevant_context. 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_relevant_context is provided by the MCP Context Manager MCP server (transparentlyok/mcp-context-manager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Context Manager, 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.
21 MCP Context Manager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.