api_docs_formatter
AI agents call api_docs_formatter to retrieve information from Mcp Dev Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the server description, this tool formats API documentation from docstrings, which is a read/transform operation with no side effects. However, the tool description is empty, which lowers confidence. Formatting/generating docs is unlikely to be destructive or financial. Classified as Read (output generation from existing input) at low severity since misuse would have minimal blast radius.
From the tool's definition Tool name: api_docs_formatter; server description mentions 'API documentation formatting from docstrings'
Attacks that exploit this kind of access
api_docs_formatter. It is categorised as a Read tool in the Mcp Dev Tools MCP Server, which means it retrieves data without modifying state.
Register the Mcp Dev Tools MCP server in PolicyLayer and add a rule for api_docs_formatter: 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 Mcp Dev Tools. Nothing to install.
api_docs_formatter 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 api_docs_formatter 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 api_docs_formatter. 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.
api_docs_formatter is provided by the Mcp Dev Tools MCP server (skeval/mcp-dev-tools). 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 →