webhound-mcp

Run budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness, and return inspectable cited evidence.

AI & ML

Install Command

npx -y webhound-mcp

Claude Desktop Config

{
  "mcpServers": {
    "webhound-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "webhound-mcp"
      ]
    }
  }
}

webhound-mcp is a community MCP server that connects AI assistants like Claude to run budgeted reports and datasets with hound, webhound's deepseek v4 pro + gpt-5.4 research harness, and return inspectable cited evidence. It runs locally on your machine, keeping your data private and giving you full control over the connection. AI engineers can use it to chain models and pipelines into more powerful workflows.

About webhound-mcp

Overview

Run budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness, and return inspectable cited evidence.

Topics

mcp, mcp-server, model-context-protocol, agent, agent-skills, research, web-research, research-agent, webhound, claude, cursor, codex

Who Should Use webhound-mcp?

1Search and retrieve information using natural language
2Control a browser and scrape the web through Claude
3Chain AI models and pipelines through a unified MCP interface
4Let Claude orchestrate other AI tools and models

How to Install webhound-mcp

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.