📚 [LIBRARIAN PROTOCOL] Audit project state for health and readiness. THE LIBRARIAN PROTOCOL: The Librarian is an Active Data Curator that validates index state before queries and self-corrects when retrieval quality is poor. Use this tool to implement the
AI agents call indexfoundry_librarian_audit to retrieve information from IndexFoundry MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs state validation and health checks on an existing project/index. It retrieves and analyzes information about the vector database's current state but does not create, modify, delete, or execute external operations. The audit function is purely observational and diagnostic, making it a Read category tool with low severity since it cannot cause harm through misuse.
From the tool's definition Tool name contains 'audit' and description states it 'validates index state' and 'audits project state for health and readiness' — these are read-only inspection operations with no modification or deletion of data.
Attacks that exploit this kind of access
📚 [LIBRARIAN PROTOCOL] Audit project state for health and readiness. THE LIBRARIAN PROTOCOL: The Librarian is an Active Data Curator that validates index state before queries and self-corrects when retrieval quality is poor. Use this tool to implement the. It is categorised as a Read tool in the IndexFoundry MCP MCP Server, which means it retrieves data without modifying state.
Register the IndexFoundry MCP server in PolicyLayer and add a rule for indexfoundry_librarian_audit: 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 IndexFoundry MCP. Nothing to install.
indexfoundry_librarian_audit 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 indexfoundry_librarian_audit 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 indexfoundry_librarian_audit. 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.
indexfoundry_librarian_audit is provided by the IndexFoundry MCP server (mnehmos/mnehmos.index-foundry.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 →