Return indexing statistics for one or all named sources.
AI agents call summarize_source to retrieve information from MemoryMesh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports metadata about existing indexed sources—a read-only operation with no side effects. It does not create, modify, delete, or execute external operations. The local-first, privacy-preserving nature of MemoryMesh means this query stays on the user's machine. Risk is minimal even if misused by an agent, as it only exposes statistics about what has already been indexed locally.
From the tool's definition The tool 'returns indexing statistics' from local sources without modifying data. Described as a query/reporting function that provides information about indexed documents and sources.
Attacks that exploit this kind of access
Return indexing statistics for one or all named sources. It is categorised as a Read tool in the MemoryMesh MCP Server, which means it retrieves data without modifying state.
Register the MemoryMesh MCP server in PolicyLayer and add a rule for summarize_source: 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 MemoryMesh. Nothing to install.
summarize_source 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 summarize_source 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 summarize_source. 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.
summarize_source is provided by the MemoryMesh MCP server (kilhubprojects/memory-mesh). 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 →