AI agents call read_function_body to retrieve information from ContextGC without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays code content without modifying, executing, or deleting anything. It is a straightforward Read operation that queries file contents to expose function implementations for inspection purposes.
From the tool's definition Tool name 'read_function_body' and description explicitly states it 'Expands the full implementation of a specific function/method from a file' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Expands the full implementation of a specific function/method from a file. Use AFTER read_code_skeleton when you need to see a particular function. It is categorised as a Read tool in the ContextGC MCP Server, which means it retrieves data without modifying state.
Register the ContextGC MCP server in PolicyLayer and add a rule for read_function_body: 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 ContextGC. Nothing to install.
read_function_body 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 read_function_body 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 read_function_body. 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.
read_function_body is provided by the ContextGC MCP server (superzavier/contextgc-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 →