AI agents call root_fetch to retrieve information from Docs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the MCP server's core purpose is indexing and exposing documentation through search and fetch operations, 'root_fetch' most likely retrieves indexed documents or their content. This is a Read operation—it retrieves data without modification or side effects. The lack of a description lowers confidence from high to medium-high, but the context and naming pattern strongly suggest read-only retrieval.
From the tool's definition Tool name 'root_fetch' combined with server's stated function to 'expose' documentation via 'search and fetch tools' indicates data retrieval capability. The 'fetch' verb is typical for Read operations (retrieve, query, get).
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
root_fetch. It is categorised as a Read tool in the Docs MCP Server, which means it retrieves data without modifying state.
Register the Docs MCP server in PolicyLayer and add a rule for root_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 Docs. Nothing to install.
root_fetch 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 root_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.
Set action: deny in the PolicyLayer policy for root_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.
root_fetch is provided by the Docs MCP server (pankaj28843/docs-mcp-server). 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 →