This record as markdown: /tools/io-github-devopam-mcpg/mmr-search.md
What mmr_search does on Mcpg
AI agents invoke mmr_search to trigger actions in Mcpg. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why mmr_search is rated High
MMR (Maximal Marginal Relevance) search is typically a read/query operation used in vector similarity search to retrieve diverse results. However, because the description is empty, there is uncertainty about whether it executes arbitrary queries or has side effects.
From the tool's definition Tool name 'mmr_search' suggests a search/read operation (Maximal Marginal Relevance search), but the description is empty and uninformative. Sibling tools include vector search, reranking, and query analysis tools on a PostgreSQL MCP server.
Attacks that exploit this kind of access
The rule that runs mmr_search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcpg, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mmr_search, this is the rule to start with:
mmr_search stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcpg, apply this rule, and every mmr_search call is checked against it from then on.
Questions about mmr_search
mmr_search is a execute tool on the Mcpg MCP server. It is categorised as a Execute tool in the Mcpg MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcpg MCP server in PolicyLayer and add a rule for mmr_search: 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 Mcpg. Nothing to install.
mmr_search is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the mmr_search 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 mmr_search. 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.
mmr_search is provided by the Mcpg MCP server (pypi:mcpg). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcpg, and thousands of servers like it.
This server
Across the catalogue