Search company documents and code using natural language queries. Stateless search across all indexed company content. Searches the entire branch directory: {reposBasePath}/{defaultProject}/{defaultBranch}
AI agents call search_code to retrieve information from Claude Context MCP 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 indexed codebase data without side effects. It is purely informational (semantic search), returns results without altering state, and cannot execute code, delete files, or move money. The stateless nature and search-only functionality confirm Read category.
From the tool's definition Tool performs "Search company documents and code using natural language queries" and "Stateless search across all indexed company content" — these are read-only operations with no modification, deletion, or execution capabilities.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Search company documents and code using natural language queries. Stateless search across all indexed company content. Searches the entire branch directory: {reposBasePath}/{defaultProject}/{defaultBranch}. It is categorised as a Read tool in the Claude Context MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Context MCP server in PolicyLayer and add a rule for search_code: 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 Claude Context MCP. Nothing to install.
search_code 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 search_code 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 search_code. 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.
search_code is provided by the Claude Context MCP server (sahinrasit/ibtech-mcp-claude-context). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search_code is one line of Claude Context's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →