Skip to content
Conduit

mcp server

agentic-browser

Himaanshuuuu04/agentic-browsercommunitylistedunreviewed
Use tool

Set up

Runs on your computer. Pick your agent and operating system.

Before you start

  • uv (`curl -LsSf https://astral.sh/uv/install.sh | sh`)
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "himaanshuuuu04-agentic-browser": {
      "command": "uvx",
      "args": [
        "agentic-browser"
      ]
    }
  }
}

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Oct 24, 2026

agentic-browser

FastAPI backend and MCP server exposing your LLM, GitHub prompt chain, and website tools.

Run the FastAPI backend

Requirements: Python 3.12+

  1. Install deps
uv sync
  1. Set env as needed
export GOOGLE_API_KEY=...
export OPENAI_API_KEY=...
export ANTHROPIC_API_KEY=...
export OLLAMA_BASE_URL=http://localhost:11434
  1. Start server
uvicorn app.main:app --reload --host 0.0.0.0 --port 5454

Endpoints:

  • GET /health
  • POST /v1/chat/generate
  • POST /v1/github/answer
  • POST /v1/website/markdown
  • POST /v1/website/html-to-md

Run the MCP server

The MCP server communicates over stdio. Many MCP clients can launch it directly.

Entrypoint: python -m mcp_server.server or the script agentic-mcp if installed as a package.

Tool names:

  • llm.generate
  • github.answer
  • website.fetch_markdown
  • website.html_to_md

Input schemas are defined in the server, aligning with the FastAPI payloads.

↑↓ navigate openesc close