Search indexed code by pattern, keyword, or natural language (semantic=true) when repository readiness is ready. If the tool returns index_unavailable with safe_fallback=native_search, use native search and follow the readiness remediation, such as reindex. Ready misses return results=[] with rea...
AI agents call search_code to retrieve information from Code-Index-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_code retrieves and queries code data without side effects. It supports pattern matching, keyword search, and semantic search but only reads from the index. No create, modify, delete, execute, or financial operations are described. The fallback mechanism (native_search) and readiness checks confirm this is a read-only retrieval tool. Path restrictions are access controls, not dangerous capabilities.
From the tool's definition Tool performs search operations across indexed code: 'Search indexed code by pattern, keyword, or natural language'; returns 'results=[]' with metadata; no modification, deletion, or execution described.
Documented attack patterns abuse exactly the kind of access search_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code-Index-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_code:
{
"version": "1",
"default": "deny",
"tools": {
"search_code": {}
}
}search_code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search indexed code by pattern, keyword, or natural language (semantic=true) when repository readiness is ready. If the tool returns index_unavailable with safe_fallback=native_search, use native search and follow the readiness remediation, such as reindex. Ready misses return results=[] with readiness metadata. Accepts optional repository param (registered repo name or filesystem path); filesystem paths must be inside MCP_ALLOWED_ROOTS or the tool returns path_outside_allowed_roots. It is categorised as a Read tool in the Code-Index-MCP MCP Server, which means it retrieves data without modifying state.
Register the Code-Index- 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 Code-Index-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 Code-Index- MCP server (viperjuice/code-index-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Code-Index-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Code-Index-MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.