knowledge_think

Query-time synthesis over the knowledge base. Retrieves the top-K grounding excerpts for a question, then asks the local model to synthesize a CITED answer grounded only in them, plus an explicit report of what the knowledge base does NOT contain (gaps). Use when you want a synthesized, sourced a...

Server Ralph Hero ralph-hero-mcp-server
Category Read
Risk class Low
Parameters 00 required

What knowledge_think does on Ralph Hero

AI agents call knowledge_think to retrieve information from Ralph Hero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why knowledge_think needs a policy

The tool performs information retrieval and synthesis over an existing knowledge base. It reads data (queries and retrieves excerpts), synthesizes answers grounded in those excerpts, and reports gaps. The description explicitly indicates it only retrieves and synthesizes information without creating, modifying, deleting, or executing external operations. This is a read-only operation with minimal security impact.

From the tool's definition Tool description states it 'retrieves the top-K grounding excerpts' and 'returns retrieved sources' — these are query operations with no data modification, deletion, or external side effects.

Questions about knowledge_think

What does the knowledge_think tool do? +

Query-time synthesis over the knowledge base. Retrieves the top-K grounding excerpts for a question, then asks the local model to synthesize a CITED answer grounded only in them, plus an explicit report of what the knowledge base does NOT contain (gaps). Use when you want a synthesized, sourced answer instead of a raw result list. Fail-open: returns retrieved sources even when the local model is offline. It is categorised as a Read tool in the Ralph Hero MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on knowledge_think? +

Register the Ralph Hero MCP server in PolicyLayer and add a rule for knowledge_think: 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 Ralph Hero. Nothing to install.

What risk level is knowledge_think? +

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

Can I rate-limit knowledge_think? +

Yes. Add a rate_limit block to the knowledge_think 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 knowledge_think completely? +

Set action: deny in the PolicyLayer policy for knowledge_think. 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 knowledge_think? +

knowledge_think is provided by the Ralph Hero MCP server (ralph-hero-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.