# trace_callers

BFS 逐层找出调用指定函数的函数：depth=1 为直接调用者，

Agent View of the PolicyLayer registry record for `trace_callers`. HTML page: https://policylayer.com/tools/0xyubo-ripple-mcp/trace-callers

## Facts

- Tool: `trace_callers`
- Server: Ripple-MCP (`0xyubo/ripple-mcp`) — https://policylayer.com/tools/0xyubo-ripple-mcp.md
- Homepage: https://github.com/0xYubo/Ripple-Mcp
- Risk category: Read (Low risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "trace_callers",
    "arguments": {}
  }
}
```

## Why trace_callers is rated Low

The tool is purely analytical: it traverses the call graph to identify callers of a function at various depths (depth=1 for direct callers). This is equivalent to a 'find' or 'search' operation on code structure, with no side effects. It retrieves call relationship data without altering code, executing arbitrary commands, or destroying data.

From the tool's own definition: "Tool performs 'BFS 逐层找出调用指定函数的函数' (breadth-first search to find functions that call a specified function). This is a query/analysis operation that traces call relationships without modifying, executing, or deleting any code."

## Use case

AI agents call trace_callers to retrieve information from Ripple-MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Ripple-MCP:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "trace_callers": {}
  }
}
```

## Other tools on Ripple-MCP (5)

- `analyze_python_ast` — Read — https://policylayer.com/tools/0xyubo-ripple-mcp/analyze-python-ast.md
- `find_definition` — Read — https://policylayer.com/tools/0xyubo-ripple-mcp/find-definition.md
- `generate_impact_report` — Read — https://policylayer.com/tools/0xyubo-ripple-mcp/generate-impact-report.md
- `get_code_context` — Read — https://policylayer.com/tools/0xyubo-ripple-mcp/get-code-context.md
- `scan_patterns` — Read — https://policylayer.com/tools/0xyubo-ripple-mcp/scan-patterns.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0xyubo-ripple-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0xyubo-ripple-mcp