AI agents call docs_read 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.
This tool retrieves documentation content from local installed packages. It performs a pure read operation with no capacity to modify, delete, or execute code. The blast radius of misuse is minimal—an agent can only access documentation that should be accessible to developers. No data is altered, no commands are executed, and no external systems are affected.
From the tool's definition Tool is named docs_read and described as 'Read the full markdown content of one doc file.' The operation retrieves documentation content without modification or side effects.
Attacks that exploit this kind of access
Read the full markdown content of one doc file. Pass the package name and the path from docs_list. 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 docs_read: 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.
docs_read 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 docs_read 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 docs_read. 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.
docs_read is provided by the Docs MCP server (particle-academy/docs-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 →