quality.evaluate_factuality

Check factual accuracy of responses against knowledge bases

Server ContextForge MCP Gateway jrmatherly/mcp-context-forge
Category Read
Risk class Low
Parameters 00 required

What quality.evaluate_factuality does on ContextForge MCP Gateway

AI agents call quality.evaluate_factuality to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why quality.evaluate_factuality needs a policy

This tool retrieves or compares data (checking responses against stored knowledge bases) without creating, modifying, executing code, deleting, or moving money. It is fundamentally a read operation that queries knowledge bases for validation purposes. No side effects or state changes are implied.

From the tool's definition Tool name 'evaluate_factuality' combined with description 'Check factual accuracy of responses against knowledge bases' indicates a verification/query operation.

Questions about quality.evaluate_factuality

What does the quality.evaluate_factuality tool do? +

Check factual accuracy of responses against knowledge bases. It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on quality.evaluate_factuality? +

Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for quality.evaluate_factuality: 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 ContextForge MCP Gateway. Nothing to install.

What risk level is quality.evaluate_factuality? +

quality.evaluate_factuality is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit quality.evaluate_factuality? +

Yes. Add a rate_limit block to the quality.evaluate_factuality 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.

How do I block quality.evaluate_factuality completely? +

Set action: deny in the PolicyLayer policy for quality.evaluate_factuality. 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.

What MCP server provides quality.evaluate_factuality? +

quality.evaluate_factuality is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

quality.evaluate_factuality is one line of ContextForge MCP Gateway's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.