📊 [LIBRARIAN PROTOCOL] Assess retrieval quality after a query. THE LIBRARIAN PROTOCOL: After running project_query, use this tool to assess whether the results meet quality thresholds. The Librarian will recommend debugging or repair actions if quality is marginal or poor. WHAT THIS DOES: 1. Cal...
AI agents call indexfoundry_librarian_assess 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 is a read-only assessment and analytics tool. It inspects query results, computes statistics (min/max/avg scores), and provides recommendations for debugging or repair. It does not execute queries itself, does not modify data, does not trigger external operations based on variable inputs, and does not delete or transfer resources.
From the tool's definition The tool 'assesses retrieval quality after a query' by 'calculating min/max/avg scores' and 'comparing against quality thresholds.' It performs analysis and generates recommendations but does not create, modify, delete, execute commands, or move money.
Attacks that exploit this kind of access
📊 [LIBRARIAN PROTOCOL] Assess retrieval quality after a query. THE LIBRARIAN PROTOCOL: After running project_query, use this tool to assess whether the results meet quality thresholds. The Librarian will recommend debugging or repair actions if quality is marginal or poor. WHAT THIS DOES: 1. Calculates min/max/avg scores from results 2. Compares against quality thresholds 3. Assigns quality level (excellent/good/marginal/poor) 4. Generates recommendations based on quality 5. Suggests debug_query or re-chunking if needed QUALITY LEVELS: - Excellent: avg >= 0.80, min >= 0.60 - Good: meets configured thresholds - Marginal: close to threshold (within 80%) - Poor: below thresholds USE WHEN: - After project_query to validate results - Before returning answers to users - To decide if re-indexing is needed RETURNS: Quality assessment with scores, thresholds, and recommendations. 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_assess: 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_assess 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_assess 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_assess. 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_assess 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 →