Instant repo overview — languages, complexity, file count, tech stack, code quality findings, and credential scanning. Use as your first call to understand any remote public codebase. Supports language filtering and path scoping (for large monorepos, analyze a subdirectory instead of the full rep...
Risk signalsAccepts file system path (path)
Part of the Searchcode server.
Free to start. No card required.
AI agents call code_analyze to retrieve information from Searchcode without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though code_analyze only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"code_analyze": {}
}
}See the full Searchcode policy for all 6 tools.
These attack patterns abuse exactly the kind of access code_analyze gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Instant repo overview — languages, complexity, file count, tech stack, code quality findings, and credential scanning. Use as your first call to understand any remote public codebase. Supports language filtering and path scoping (for large monorepos, analyze a subdirectory instead of the full repo). When analysing multiple repositories, call in parallel rather than sequentially. Dependency/build directories excluded by default.. It is categorised as a Read tool in the Searchcode MCP Server, which means it retrieves data without modifying state.
Register the Searchcode MCP server in PolicyLayer and add a rule for code_analyze: 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 Searchcode. Nothing to install.
code_analyze 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 code_analyze 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 code_analyze. 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.
code_analyze is provided by the Searchcode MCP server (https://api.searchcode.com/v1/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Searchcode tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.