Skip to main content
Glama

dat.ai MCP Server

Browser automation, transcription, and LLM chat as MCP tools for any agent.

license tools python


Tools

Tool

Endpoint

Description

dat_browse

POST /api/v1/browsing/{async,sync}

Natural language browser automation. Sync (waits up to 10 min) or async (returns task_id immediately). Optional screenshots

dat_browse_status

GET /api/v1/browsing/status

Poll an async browsing task. Returns status + result if ready

dat_browse_screenshot

GET /api/v1/browsing/screenshots/{task_id}/{file}

Download a screenshot as base64 image data

dat_transcribe

POST /api/whisper/transcribe/{async,sync}

Whisper speech-to-text. Accepts audio URL or base64. Sync or async

dat_transcribe_status

GET /api/whisper/transcribe/status

Poll an async transcription task

dat_completions

POST /v1/chat/completions

OpenAI-compatible chat completions. Streaming, function calling, built-in dat.ai tools (net/fs/webview)

dat_chat

POST /api/chat

Ollama-compatible chat. NDJSON streaming, system prompts, built-in tools

Related MCP server: Sentinel Core Agent

Setup

Get an API key

Sign up at dat.ai and get your API key from the dashboard. See the official API docs for reference.

Hermes Agent (one-line install)

hermes plugins install willtholke/dat.ai-mcp --enable

Restart Hermes after installing. Set your API key in ~/.hermes/.env:

DAT_AI_API_KEY=your-api-key-here

The plugin registers all 7 tools as native Hermes tools. No MCP config needed.

Other MCP clients

Install the package:

pip install dat-ai-mcp

Or use directly with uvx (no install needed):

uvx dat-ai-mcp

Set the DAT_AI_API_KEY environment variable and add the server to your MCP client config

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "dat-ai": {
      "command": "uvx",
      "args": ["dat-ai-mcp"],
      "env": {
        "DAT_AI_API_KEY": "your-api-key-here"
      }
    }
  }
}

Cursor / other MCP clients

Same pattern: command uvx, args ["dat-ai-mcp"], env DAT_AI_API_KEY

Environment variable

DAT_AI_API_KEY=your-api-key-here

Usage examples

Browser automation

dat_browse({
  task: "Open https://example.com and summarize the page",
  screenshots_mode: "final_only"
})

Audio transcription

dat_transcribe({
  audio_url: "https://example.com/audio.mp3"
})

Chat completions with built-in tools

dat_completions({
  model: "qwen3:1.7b",
  messages: [{ role: "user", content: "Open https://example.com and summarize the page" }],
  datai_tools: { net: true, webview: true }
})

Troubleshooting

Tools not appearing in Hermes

If the dat.ai tools don't show up after installing the plugin:

  1. Don't also add an MCP server entry. The Hermes plugin registers all 7 tools as native Hermes tools. Adding a dat-ai entry to mcp_servers in config.yaml creates a redundant subprocess that can conflict with the native plugin. The plugin is the correct path — no MCP config needed.

  2. Verify the plugin is enabled:

    hermes plugins list

    dat-ai should show as enabled.

  3. Verify the toolset is enabled for your platform:

    hermes tools list

    dat-ai should appear under "Plugin toolsets" as enabled. If not, run hermes tools and enable it.

  4. Restart Hermes after config changes. Plugin tool definitions are cached per-session.

Development

git clone https://github.com/willtholke/dat.ai-mcp.git
cd dat.ai-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e .

License

MIT

Note

Special thanks to dat.ai co-founder & COO Eugenia Dushina for setting me up with the platform


Available Tools

7 tools
dat_browseA

Run a browser automation task on dat.ai. Give a natural language instruction and dat.ai will drive a real browser to complete it. Returns the result and any screenshot URLs. Uses sync mode by default (waits for completion, up to 10 min). Set async=true to get a task_id immediately and poll with dat_browse_status.

Inputs: task (required), async, fanout, timeout, +4 more.

dat_browse_screenshotA

Download a screenshot from a completed dat.ai browsing task. Returns the image as base64 data.

Inputs: task_id (required), filename (required).

dat_browse_statusA

Check the status of an async dat.ai browsing task. Returns status (queued/assigned/running/completed/failed) and result if ready.

Inputs: task_id (required).

dat_chatA

Ollama-compatible chat endpoint via dat.ai. Supports NDJSON streaming and non-streaming. Can enable built-in tools (net, fs, webview). Note: tools cannot be used with streaming.

Inputs: model (required), messages (required), stream, system, +2 more.

dat_completionsA

OpenAI-compatible chat completions via dat.ai. Supports streaming and non-streaming. Can enable built-in tools (net, fs, webview) via the datai.tools parameter. Note: tools cannot be used with streaming.

Inputs: model (required), messages (required), seed, stop, +7 more.

dat_transcribeA

Transcribe audio to text using dat.ai's Whisper API. Provide audio as a URL (the server will fetch it) or as base64-encoded data. Returns transcribed text. Uses sync mode (waits for completion, up to 10 min).

Inputs: async, audio_url, audio_base64, content_type.

dat_transcribe_statusA

Check the status of an async dat.ai transcription task.

Inputs: task_id (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 7 tools

    Disambiguation4/5

    Most tools have distinct purposes, but dat_chat and dat_completions are very similar (both chat endpoints with same features), which could cause misselection. The descriptions help differentiate, but overlap exists.

    Naming Consistency5/5

    All tools share the 'dat_' prefix and follow a verb or verb_noun pattern. Async status tools use 'status' suffix. The naming is consistent and predictable.

    Tool Count5/5

    7 tools is well-scoped for an AI service covering browsing, chat, and transcription. Each tool serves a clear purpose without redundancy.

    Completeness5/5

    The tool set covers all core features: browsing (sync/async, status, screenshot), chat (two API styles), and transcription (sync/async, status). No obvious gaps for the stated domain.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Exposes the local agent-browser CLI as MCP tools for browser automation and provides one-command integration with Codex. Enables navigation, interaction, page reading, tab management, and session control through natural language commands.
      7 npm
      1
      MIT
    • A
      license
      B
      quality
      C
      maintenance
      Provides AI agents with a real browser environment for web automation, memory, and secure credential management through 15 MCP tools.
      15
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to automate both web browsers and native desktop applications through a unified interface, supporting tasks like browsing, clicking, typing, and file clipboard operations via exposed MCP tools.
      1
      Apache 2.0