Read multiple files in one call, each minified. Saves tool-call overhead. Supports: (1) intent parameter — tell the tool WHY you\
AI agents call fullscope_batch_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.
The tool retrieves and reads multiple file contents, applying minification (stripping comments/docstrings/whitespace) to compress them. This is a data retrieval operation with no capacity to modify, delete, or execute code. The 'intent parameter' appears to be metadata guidance for the read operation, not a code execution mechanism. No write, destructive, or execution capabilities are described.
From the tool's definition Tool name includes 'context' and 'read', description states 'Read multiple files in one call' and 'Supports... intent parameter'. The verb 'read' and operation of retrieving file contents with minification are core retrieval functions with no side effects.
Attacks that exploit this kind of access
Read multiple files in one call, each minified. Saves tool-call overhead. Supports: (1) intent parameter — tell the tool WHY you\. 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_batch_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_batch_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_batch_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_batch_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_batch_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 →