# multi_file_chat

Chat with multiple files using Groq

Agent View of the PolicyLayer registry record for `multi_file_chat`. HTML page: https://policylayer.com/tools/97k-mcp-audio-server/multi-file-chat

## Facts

- Tool: `multi_file_chat`
- Server: MCP Audio Server (`97k/mcp-audio-server`) — https://policylayer.com/tools/97k-mcp-audio-server.md
- Homepage: https://github.com/97k/mcp-audio-server
- 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": "multi_file_chat",
    "arguments": {}
  }
}
```

## Why multi_file_chat is rated High

This tool sends multiple files to an external AI service (Groq) and executes inference/chat operations. It spans Read (reading files) and Execute (triggering external API calls with potentially sensitive file contents). The most severe applicable category is Execute, as it initiates external operations dependent on supplied arguments.

From the tool's own definition: "'Chat with multiple files using Groq' — triggers external API calls to Groq service with user-supplied files and queries, executing an external LLM inference operation whose effects depend on arguments"

## Use case

AI agents invoke multi_file_chat to trigger actions in MCP Audio 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 MCP Audio Server:

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

## Other tools on MCP Audio Server (3)

- `split_audio` — Read — https://policylayer.com/tools/97k-mcp-audio-server/split-audio.md
- `summarize_transcript` — Read — https://policylayer.com/tools/97k-mcp-audio-server/summarize-transcript.md
- `transcribe_audio` — Read — https://policylayer.com/tools/97k-mcp-audio-server/transcribe-audio.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=97k-mcp-audio-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/97k-mcp-audio-server