AI agents call get_file_context to retrieve information from Codetex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves pre-computed file summaries from a code knowledge base (SQLite vector search index). It queries existing data without modifying, executing code, or affecting external systems. No reversible or irreversible changes are made. This is a classic Read operation with minimal blast radius.
From the tool's definition Tool name is 'get_file_context' and description states 'Return the Tier 2 file summary for a specific file.' The verb 'Return' and the context of a code indexing/search server indicate this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Return the Tier 2 file summary for a specific file. It is categorised as a Read tool in the Codetex MCP Server, which means it retrieves data without modifying state.
Register the Codetex MCP server in PolicyLayer and add a rule for get_file_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 Codetex. Nothing to install.
get_file_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 get_file_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 get_file_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.
get_file_context is provided by the Codetex MCP server (mrosata/codetex-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 →