AI agents call search_code to retrieve information from MCP Code Indexer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches a code repository and retrieves matching code segments. This is a read-only operation that queries existing data without creating, modifying, deleting, or executing anything. There is no blast radius from misuse—an AI agent can only retrieve information already in the repository. Classified as Read with low severity.
From the tool's definition Tool name 'search_code' and description indicating it 'returns relevant code snippets' (搜索代码，返回相关代码片段). The description explicitly states the tool returns data without modification. This is a retrieval/query operation with no side effects.
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 MCP Code Indexer, 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.
搜索代码，返回相关代码片段. It is categorised as a Read tool in the MCP Code Indexer MCP Server, which means it retrieves data without modifying state.
Register the MCP Code Indexer 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 MCP Code Indexer. 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 MCP Code Indexer MCP server (zxfgds/mcp-code-indexer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 MCP Code Indexer tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 MCP Code Indexer tools catalogued and risk-classified — across an index of 42,500+ MCP servers.