Reads a source code file and returns ONLY its structural skeleton (imports, type definitions, class declarations, function signatures with parameter types and return types). Internal logic is replaced with
AI agents call read_code_skeleton 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 queries source code structure through AST parsing without side effects. It extracts metadata (imports, type definitions, signatures) but does not modify, execute, or delete anything. The output is informational only, making it a straightforward Read operation with low risk.
From the tool's definition Tool name contains 'read' and description states it 'Reads a source code file and returns ONLY its structural skeleton' with no mention of modifications, deletions, or code execution. The operation is purely retrieval-based.
Attacks that exploit this kind of access
Reads a source code file and returns ONLY its structural skeleton (imports, type definitions, class declarations, function signatures with parameter types and return types). Internal logic is replaced with. 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_code_skeleton: 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_code_skeleton 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_code_skeleton 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_code_skeleton. 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_code_skeleton 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 →