AI agents call swarm_search_code to retrieve information from Mcp Swarm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation using ripgrep, a standard code search utility. It retrieves matching text from code without side effects, modifications, or irreversible actions. The action is query-based and returns information only, fitting the Read category.
From the tool's definition Tool description states '在代码库中搜索文本内容（使用 ripgrep）' which translates to 'search text content in codebase (using ripgrep)'. The name 'swarm_search_code' and description indicate a search/query operation that retrieves data from a codebase without modifying it.
Attacks that exploit this kind of access
在代码库中搜索文本内容（使用 ripgrep）。. It is categorised as a Read tool in the Mcp Swarm MCP Server, which means it retrieves data without modifying state.
Register the Mcp Swarm MCP server in PolicyLayer and add a rule for swarm_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 Swarm. Nothing to install.
swarm_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 swarm_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 swarm_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.
swarm_search_code is provided by the Mcp Swarm MCP server (moselu/mcp-swarm). 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 →