# auto_routed_completion

A execute tool on the DeepMyst MCP Server MCP server.

Agent View of the PolicyLayer registry record for `auto_routed_completion`. HTML page: https://policylayer.com/tools/deepmyst-deepmyst-mcp/auto-routed-completion

## Facts

- Tool: `auto_routed_completion`
- Server: DeepMyst MCP Server (`deepmyst/deepmyst-mcp`) — https://policylayer.com/tools/deepmyst-deepmyst-mcp.md
- Homepage: https://github.com/DeepMyst/DeepMyst-MCP
- Risk category: Execute (High risk)
- Registry record: grade B, 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": "auto_routed_completion",
    "arguments": {}
  }
}
```

## Why auto_routed_completion is rated High

Based on the server context, this tool likely routes queries to external LLM models and triggers completions — an external operation. The empty description lowers confidence significantly. Sibling tools like 'smart_completion' and 'optimized_completion' suggest this tool executes LLM inference requests, placing it in Execute.

From the tool's own definition: "Tool name 'auto_routed_completion' and server context describe automatic LLM routing and completion generation; description is empty and uninformative."

## Use case

AI agents invoke auto_routed_completion to trigger actions in DeepMyst MCP Server. 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 DeepMyst MCP Server:

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

## Other tools on DeepMyst MCP Server (4)

- `smart_completion` — Execute — https://policylayer.com/tools/deepmyst-deepmyst-mcp/smart-completion.md
- `deepmyst_completion` — Read — https://policylayer.com/tools/deepmyst-deepmyst-mcp/deepmyst-completion.md
- `get_best_model_for_query` — Read — https://policylayer.com/tools/deepmyst-deepmyst-mcp/get-best-model-for-query.md
- `optimized_completion` — Read — https://policylayer.com/tools/deepmyst-deepmyst-mcp/optimized-completion.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=deepmyst-deepmyst-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deepmyst-deepmyst-mcp