Compressed file read for CONTEXT ONLY — strips comments, docstrings, types, and whitespace. Typical savings: 10-50% depending on comment density (up to 80% on heavily documented code, as low as 8% on minimal-comment code). Shows virtual line markers where content was stripped. NEVER use for files...
AI agents call fullscope_context 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 compresses file content for viewing purposes only. It explicitly states it is for context reading, not editing. No data is written, modified, or deleted — the stripping only affects the output representation, not the actual files. Severity is low because misuse at worst provides an incomplete view of a file.
From the tool's definition Compressed file read for CONTEXT ONLY — strips comments, docstrings, types, and whitespace... NEVER use for files you plan to edit
Attacks that exploit this kind of access
Compressed file read for CONTEXT ONLY — strips comments, docstrings, types, and whitespace. Typical savings: 10-50% depending on comment density (up to 80% on heavily documented code, as low as 8% on minimal-comment code). Shows virtual line markers where content was stripped. NEVER use for files you plan to edit — comments and formatting are permanently removed from output. Use the built-in Read tool when you need to Edit a file. 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_context: 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_context 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_context 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_context. 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_context 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 →