AI agents call get_source_code to retrieve information from Rust Docs MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves source code from a public documentation repository (docs.rs). Retrieving publicly available source code has no side effects, cannot modify or delete data, and poses minimal risk. It is fundamentally a Read operation. Severity is low because the source is public and read-only access to documentation carries minimal blast radius.
From the tool's definition Tool name 'get_source_code' and server context indicate retrieval of publicly available Rust source code from docs.rs. Server description states it 'provides AI tools with access to Rust documentation' with capabilities to 'search' and 'get' information.
Documented attack patterns abuse exactly the kind of access get_source_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rust Docs MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_source_code:
{
"version": "1",
"default": "deny",
"tools": {
"get_source_code": {}
}
}get_source_code 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.
get_source_code. It is categorised as a Read tool in the Rust Docs MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Rust Docs MCP Server MCP server in PolicyLayer and add a rule for get_source_code: 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 Rust Docs MCP Server. Nothing to install.
get_source_code 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 get_source_code 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 get_source_code. 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.
get_source_code is provided by the Rust Docs MCP Server MCP server (laptou/rust-docs-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rust Docs MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Rust Docs MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.