Favicon of deep-research-mcp

deep-research-mcp Skill

AI Agent SkillCode & Developer ToolsPythonOpen source

deep-research-mcp is a Python AI agent skill for Cursor, Codex with uvx/pip, remote URL. MCP server for OpenAI's Deep Research APIs, Gemini Deep Research Agent, Allen AI's DR-Tulu, and Hugging Face's Open Deep Research

How to use deep-research-mcp Skill

Install or run

uv run python cli/deep-research-cli.py \
  --provider gemini \
  --model deep-research-preview-04-2026 \
  --base-url https://generativelanguage.googleapis.com \
  research "What is the capital of France?"

Client configuration

{
  "mcpServers": {
    "deep-research": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/deep-research-mcp", "deep-research-mcp"],
      "env": {
        "RESEARCH_PROVIDER": "gemini",
        "GEMINI_API_KEY": "$GEMINI_API_KEY"
      }
    }
  }
}

Compatible clients

CursorCodex

What is deep-research-mcp Skill?

deep-research-mcp is a Python AI agent skill for Cursor, Codex with uvx/pip, remote URL. MCP server for OpenAI's Deep Research APIs, Gemini Deep Research Agent, Allen AI's DR-Tulu, and Hugging Face's Open Deep Research This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Trust signal
85/100
Maintenance signal
80/100
Adoption signal
48/100

Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.

Key capabilities

  • Reusable instructions support
  • Includes SKILL.md support
  • Shell commands support
  • Document generation support
  • OpenAI provider support
  • Anthropic provider support
  • Google provider support

Technical details

Install or run deep-research-mcp using uvx/pip. Check pminervini/deep-research-mcp for the latest setup command.

uvx/pipremote URLCursorCodexstdioHTTPSSE
  • Built for Python
  • Install or run with uvx/pip
  • Install or run with remote URL
  • Works with Cursor
  • Works with Codex
  • Uses stdio transport
  • Uses HTTP transport
  • Uses SSE transport

Requirements and access

PythonMIT licenseAPI key requiredNetwork accessAPI key requiredNetwork access

Security and permissions

Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.

Destructive actionsWrite actionsNetwork accessCredentials requiredCan write or update dataMay support destructive actionsAPI key required authenticationHosted or remote

When to use deep-research-mcp Skill

  • Use it for reusing agent instructions, scripts, and references.
  • Use it for agent skills workflows.
  • Use it for coding workflows.
  • Use it for data workflows.
  • Use it for cursor users.

Built with

Pythonuvx/pipremote URLCursorCodexstdioHTTPSSE

Explore related resources

Frequently asked questions

What is deep-research-mcp?

deep-research-mcp is a Python AI agent skill for Cursor, Codex with uvx/pip, remote URL. MCP server for OpenAI's Deep Research APIs, Gemini Deep Research Agent, Allen AI's DR-Tulu, and Hugging Face's Open Deep Research

Who is deep-research-mcp best for?

deep-research-mcp is best for reusing agent instructions, scripts, and references, agent skills workflows, coding workflows, data workflows, cursor users.

How do I install deep-research-mcp?

Install or run deep-research-mcp using uvx/pip. Check deep-research-mcp for the latest setup command.

Is deep-research-mcp actively maintained?

deep-research-mcp may need a closer maintenance check before production use.

Share:

Stars
87
Forks
10
Last commit
2 months ago
Repository age
1 year
License
MIT

Auto-fetched from GitHub.

Similar to deep-research-mcp