searchCrates
AI agents call searchCrates to retrieve information from Mcp Docsrs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries Rust crate documentation metadata. Although the tool description is empty, the context from the server description and naming conventions strongly indicate this performs a search query against crate information without side effects. Search operations are classified as Read. The blast radius is low since accessing public documentation poses minimal risk.
From the tool's definition Tool name 'searchCrates' combined with server description stating it 'enables AI models to deeply access Rust crate documentation, including searching crates'; the verb 'search' and sibling tools like 'getCrateInfo', 'getItemDefinition', 'getItemExamples',…
Attacks that exploit this kind of access
searchCrates. It is categorised as a Read tool in the Mcp Docsrs MCP Server, which means it retrieves data without modifying state.
Register the Mcp Docsrs MCP server in PolicyLayer and add a rule for searchCrates: 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 Docsrs. Nothing to install.
searchCrates 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 searchCrates 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 searchCrates. 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.
searchCrates is provided by the Mcp Docsrs MCP server (shuakami/mcp-docsrs). 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 →