# ai_chat

Chat with your local Llama model. Zero cost, fully private. Supports multi-turn conversation, system prompts, and .brain file loading. Example: ai_chat({ message:

Agent View of the PolicyLayer registry record for `ai_chat`. HTML page: https://policylayer.com/tools/io-github-0nork-0nmcp/ai-chat

## Facts

- Tool: `ai_chat`
- Server: 0nmcp (`0nmcp`) — https://policylayer.com/tools/io-github-0nork-0nmcp.md
- Install: `npx -y 0nmcp`
- Homepage: https://github.com/0nork/0nMCP
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- 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": "ai_chat",
    "arguments": {}
  }
}
```

## Why ai_chat is rated High

This tool executes a local LLM inference process, triggering external computation. It supports loading '.brain files' and system prompts, which means it can influence model behavior dynamically. The effects depend on the arguments passed (message, system prompt, loaded files), classifying it as Execute.

From the tool's own definition: "'Chat with your local Llama model' and 'Supports multi-turn conversation, system prompts, and .brain file loading'"

## Use case

AI agents invoke ai_chat to trigger actions in 0nmcp. 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 0nmcp:

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

## Other tools on 0nmcp (217)

- `crm_marketplace_delete_charge` — Destructive — https://policylayer.com/tools/io-github-0nork-0nmcp/crm-marketplace-delete-charge.md
- `crm_marketplace_uninstall` — Destructive — https://policylayer.com/tools/io-github-0nork-0nmcp/crm-marketplace-uninstall.md
- `crm_media_bulk_delete` — Destructive — https://policylayer.com/tools/io-github-0nork-0nmcp/crm-media-bulk-delete.md
- `crm_media_delete` — Destructive — https://policylayer.com/tools/io-github-0nork-0nmcp/crm-media-delete.md
- `patent_watchlist` — Destructive — https://policylayer.com/tools/io-github-0nork-0nmcp/patent-watchlist.md
- `shadcn_theme` — Destructive — https://policylayer.com/tools/io-github-0nork-0nmcp/shadcn-theme.md
- `vault_container_revoke` — Destructive — https://policylayer.com/tools/io-github-0nork-0nmcp/vault-container-revoke.md
- `ai_embed` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/ai-embed.md
- `ai_generate` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/ai-generate.md
- `api_call` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/api-call.md
- `app_build` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/app-build.md
- `app_open` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/app-open.md
- `brain_compile` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/brain-compile.md
- `brain_import` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/brain-import.md
- `brain_train` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/brain-train.md
- `council_debate` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/council-debate.md
- `council_solve` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/council-solve.md
- `crm_build_ai_workflow` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/crm-build-ai-workflow.md
- `crm_deploy_snapshot` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/crm-deploy-snapshot.md
- `crm_run_ai_workflow` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/crm-run-ai-workflow.md
- `execute` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/execute.md
- `flow_run_now` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/flow-run-now.md
- `landing_pages_deploy` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/landing-pages-deploy.md
- `plugin_build` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/plugin-build.md
- `plugin_execute` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/plugin-execute.md
- `rc_sequence_to_user_workflow` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/rc-sequence-to-user-workflow.md
- `run_workflow` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/run-workflow.md
- `site_run` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/site-run.md
- `training_feed` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/training-feed.md
- `vault_container_escrow_unwrap` — Execute — https://policylayer.com/tools/io-github-0nork-0nmcp/vault-container-escrow-unwrap.md
- …and 187 more: https://policylayer.com/tools/io-github-0nork-0nmcp.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=io-github-0nork-0nmcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-0nork-0nmcp