Ultra-compressed file read showing ONLY function/class/method signatures with IMPORTS and EXPORTS summary — all implementation bodies are replaced with expand handles. Strong on function-heavy code (80-99% savings), weaker on flat data/config files. Use when you need to understand a module API su...
AI agents call fullscope_skeleton to retrieve information from Mcp Agent Opt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and summarizes file contents in a compressed form. It performs no writes, executions, or destructive operations. The explicit warning 'NEVER use for files you plan to edit' and the recommendation to use other tools for editing confirms it is strictly a read/query operation. Misuse potential is minimal as it only displays structural metadata of code files.
From the tool's definition Ultra-compressed file read showing ONLY function/class/method signatures with IMPORTS and EXPORTS summary — all implementation bodies are replaced with expand handles
Attacks that exploit this kind of access
Ultra-compressed file read showing ONLY function/class/method signatures with IMPORTS and EXPORTS summary — all implementation bodies are replaced with expand handles. Strong on function-heavy code (80-99% savings), weaker on flat data/config files. Use when you need to understand a module API surface without reading implementation details. NEVER use for files you plan to edit. For implementation details, use fullscope_context. For editing, use the built-in Read tool. It is categorised as a Read tool in the Mcp Agent Opt MCP Server, which means it retrieves data without modifying state.
Register the Mcp Agent Opt MCP server in PolicyLayer and add a rule for fullscope_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 Mcp Agent Opt. Nothing to install.
fullscope_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 fullscope_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 fullscope_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.
fullscope_skeleton is provided by the Mcp Agent Opt MCP server (justguy/fullscope-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 →