Search for symbols or content within package documentation
AI agents call search_package_docs to retrieve information from MCP Package Docs Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information from documentation without modifying, executing, or destroying any data. It is a straightforward search utility for discovering documented symbols and content across multiple package managers (Go, Python, NPM, Rust, Swift).
From the tool's definition Tool name is 'search_package_docs' and description states it 'Search for symbols or content within package documentation' — clearly a read-only retrieval operation with no mutation or side effects.
Documented attack patterns abuse exactly the kind of access search_package_docs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Package Docs Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_package_docs:
{
"version": "1",
"default": "deny",
"tools": {
"search_package_docs": {}
}
}search_package_docs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for symbols or content within package documentation. It is categorised as a Read tool in the MCP Package Docs Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Package Docs Server MCP server in PolicyLayer and add a rule for search_package_docs: 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 Package Docs Server. Nothing to install.
search_package_docs 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 search_package_docs 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 search_package_docs. 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.
search_package_docs is provided by the MCP Package Docs Server MCP server (sammcj/mcp-package-docs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 MCP Package Docs Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 MCP Package Docs Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.