# route_query

A execute tool on the 1c Mcp Rag Search MCP server.

Agent View of the PolicyLayer registry record for `route_query`. HTML page: https://policylayer.com/tools/1c-mcp-rag-search/route-query

## Facts

- Tool: `route_query`
- Server: 1c Mcp Rag Search (`Smaturus/1c-mcp-rag-search`) — https://policylayer.com/tools/1c-mcp-rag-search.md
- Homepage: https://github.com/Smaturus/1c-mcp-rag-search
- Risk category: Execute (High risk)
- Registry record: grade A, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why route_query is rated High

The tool description is empty, which lowers confidence significantly. However, based on the server's purpose and sibling tools, 'route_query' likely dispatches queries to other MCP tools and planners — effectively triggering external operations on behalf of the caller. This is an Execute-level concern because routing can invoke arbitrary downstream tools with unpredictable side effects.

From the tool's own definition: "Tool name 'route_query' on a server described as routing 'natural language queries to appropriate MCP tools and planners' with 'multi-intent detection, task planning, and strict role-based filtering to prevent misexecution or unauthorized access.'"

## Use case

AI agents invoke route_query to trigger actions in 1c Mcp Rag Search. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 1c Mcp Rag Search:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "route_query": {
      "limits": [
        {
          "counter": "route_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on 1c Mcp Rag Search (8)

- `evaluate_retrieval` — Other — https://policylayer.com/tools/1c-mcp-rag-search/evaluate-retrieval.md
- `codesearch` — Read — https://policylayer.com/tools/1c-mcp-rag-search/codesearch.md
- `index_stats` — Read — https://policylayer.com/tools/1c-mcp-rag-search/index-stats.md
- `metadatasearch` — Read — https://policylayer.com/tools/1c-mcp-rag-search/metadatasearch.md
- `search` — Read — https://policylayer.com/tools/1c-mcp-rag-search/search.md
- `search_1c_metadata` — Read — https://policylayer.com/tools/1c-mcp-rag-search/search-1c-metadata.md
- `search_hybrid` — Read — https://policylayer.com/tools/1c-mcp-rag-search/search-hybrid.md
- `search_knowledge_base` — Read — https://policylayer.com/tools/1c-mcp-rag-search/search-knowledge-base.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=1c-mcp-rag-search · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/1c-mcp-rag-search
