conv_search_messages
Substring search over message bodies. Returns the matching messages newest first; use conv_get_conversation to load surrounding context.
This record as markdown: /tools/com-getmunin-munin/conv-search-messages.md
What conv_search_messages does on Munin
AI agents call conv_search_messages to retrieve information from Munin without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why conv_search_messages is rated Low
This tool retrieves/queries existing message data without creating, modifying, deleting, or executing any operations. The search functionality is a classic Read operation with minimal blast radius even if misused by an AI agent, as it only exposes existing messages that the agent likely already has access to in the broader conversation/CRM platform.
From the tool's definition Tool performs 'substring search over message bodies' and 'returns the matching messages' — a query operation with no side effects. Description explicitly states it retrieves data and references loading context with a separate read tool (conv_get_conversation).
Attacks that exploit this kind of access
The rule that runs conv_search_messages safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Munin, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For conv_search_messages, this is the rule to start with:
conv_search_messages is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Munin, apply this rule, and every conv_search_messages call is checked against it from then on.
Questions about conv_search_messages
Substring search over message bodies. Returns the matching messages newest first; use conv_get_conversation to load surrounding context. It is categorised as a Read tool in the Munin MCP Server, which means it retrieves data without modifying state.
Register the Munin MCP server in PolicyLayer and add a rule for conv_search_messages: 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 Munin. Nothing to install.
conv_search_messages 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 conv_search_messages 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 conv_search_messages. 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.
conv_search_messages is provided by the Munin MCP server (https://mcp.getmunin.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Munin, and thousands of servers like it.
This server
Across the catalogue