在指定项目中搜索字段的实现位置
AI agents call find_field_in_code to retrieve information from Claude Stats MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation to locate where a field is implemented in code. It retrieves and queries data—no side effects, no execution, no data modification. This is a classic Read category action similar to 'search', 'find', 'list', or 'get'. The narrow scope (searching fields in code) and read-only nature warrant low severity.
From the tool's definition Tool name 'find_field_in_code' and description '在指定项目中搜索字段的实现位置' (search for field implementation location in specified project) indicates a search/query operation that retrieves information about code structure without modifying or executing anything.
Attacks that exploit this kind of access
在指定项目中搜索字段的实现位置. It is categorised as a Read tool in the Claude Stats MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Stats MCP server in PolicyLayer and add a rule for find_field_in_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 Stats MCP. Nothing to install.
find_field_in_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 find_field_in_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 find_field_in_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.
find_field_in_code is provided by the Claude Stats MCP server (upjiang/ai-mcp-study). 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 →