rich_fetch

Fetch rich results using the callback_key from web_search

Server Search MCP nanameru/websearch-mcp
Category Read
Risk class Low
Parameters 00 required

What rich_fetch does on Search MCP

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

Why rich_fetch needs a policy

This tool retrieves pre-computed search result data using a callback key from a prior web search. It has no side effects, does not modify data, does not execute code or commands, and does not delete or move resources. It is purely a read operation that queries and returns search results.

From the tool's definition Tool description: 'Fetch rich results using the callback_key from web_search' — the word 'fetch' indicates data retrieval.

Questions about rich_fetch

What does the rich_fetch tool do? +

Fetch rich results using the callback_key from web_search. It is categorised as a Read tool in the Search MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on rich_fetch? +

Register the Search MCP server in PolicyLayer and add a rule for rich_fetch: 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 Search MCP. Nothing to install.

What risk level is rich_fetch? +

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

Can I rate-limit rich_fetch? +

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

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

rich_fetch is provided by the Search MCP server (nanameru/websearch-mcp). 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.