Full-text search across all cached meeting notes. Searches titles and content.
AI agents call search_cached_notes to retrieve information from Fellow MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries meeting data (notes, titles, content) from a local SQLite cache without creating, modifying, deleting, or executing any operations. It is a pure search/retrieval function with no side effects, matching the Read category definition.
From the tool's definition Tool performs 'full-text search across all cached meeting notes' with no modification capability. Searches 'titles and content' only.
Attacks that exploit this kind of access
Full-text search across all cached meeting notes. Searches titles and content. It is categorised as a Read tool in the Fellow MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Fellow MCP Server MCP server in PolicyLayer and add a rule for search_cached_notes: 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 Fellow MCP Server. Nothing to install.
search_cached_notes 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_cached_notes 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_cached_notes. 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_cached_notes is provided by the Fellow MCP Server MCP server (liba2k/unofficial-fellow-mcp). 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 →