Deep Research MCP

Deep Research MCP

This document is specifically about the deep-research-mcp project/repository, not Deep Research systems in general.

Repository: https://github.com/pminervini/deep-research-mcp

Use When

• You are working in or against the deep-research-mcp repository/project.
• You need to run deep-research-cli in direct agent mode.
• You need to call DeepResearchAgent and ResearchConfig from Python.
• You need to expose the deep-research-mcp project as an MCP server with deep-research-mcp.
• You need to connect to the MCP server from another client over HTTP.
• You need to understand which backend is used for OpenAI, Gemini, DR-Tulu, or Open Deep Research.
• You need to troubleshoot provider mix-ups caused by values already stored in ~/.deep_research.

Do Not Use When

• You only need the Textual TUI in cli/deep-research-tui.py.
• You need a generic guide to Deep Research agents, generic research workflows, or MCP outside the deep-research-mcp codebase.
• You are looking for model-selection advice outside the providers this repository already implements.

Mental Model

There are three layers:

1. deep-research-cli is the installed user-facing CLI.
2. src/deep_research_mcp/agent.py orchestrates research, callbacks, and status checks.
3. src/deep_research_mcp/backends/*.py performs provider-specific work.

The CLI can run in two modes:

• Agent mode: instantiate DeepResearchAgent directly.
• MCP client mode: connect to a running HTTP MCP server with --server-url.

The MCP server entrypoint is the console script:

uv run deep-research-mcp

It exposes two tools:

• deep_research
• research_status

Setup

The commands below assume you are running from the repository root.

Recommended install

uv sync --upgrade --extra dev

Compatible editable install

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
pip install -e .

Optional Open Deep Research extras

uv sync --upgrade --extra dev --extra open-deep-research

Environment variables by provider

OpenAI:

export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"

Gemini:

export GEMINI_API_KEY="YOUR_GEMINI_API_KEY"

DR-Tulu:

• there is no single required key defined by deep-research-mcp itself
• you must have a running DR-Tulu service that exposes POST {base_url}/chat

Provider Matrix

Config Precedence And The Most Important Pitfall

ResearchConfig.load() merges:

1. Built-in defaults
2. ~/.deep_research
3. Environment variables
4. CLI flags, which are injected as environment variables

This matters because the TOML file is flattened into keys like RESEARCH_API_KEY and RESEARCH_BASE_URL. If your saved config is pinned to Gemini and you run:

uv run deep-research-cli --provider openai research "..."

you may still send the request to Gemini or send the Gemini key to OpenAI unless you also override:

• --api-key
• --base-url
• sometimes --model

Safe pattern when switching providers from the command line:

uv run deep-research-cli \
  --provider openai \
  --api-style responses \
  --model gpt-5.6-sol \
  --api-key "$OPENAI_API_KEY" \
  --base-url https://api.openai.com/v1 \
  research "..."

Recommended Minimal Config Files

OpenAI Responses

[research]
provider = "openai"
api_style = "responses"
model = "gpt-5.6-sol"
api_key = "YOUR_OPENAI_API_KEY"
base_url = "https://api.openai.com/v1"
timeout = 1800
poll_interval = 30

Gemini Deep Research

[research]
provider = "gemini"
model = "deep-research-pro-preview-12-2025"
api_key = "YOUR_GEMINI_API_KEY"
base_url = "https://generativelanguage.googleapis.com"
timeout = 1800
poll_interval = 30

DR-Tulu

[research]
provider = "dr-tulu"
model = "dr-tulu"
base_url = "http://localhost:8080"
api_key = ""
timeout = 1800
poll_interval = 30

dr-tulu is different from the others: the deep-research-mcp repository does not ship the DR-Tulu service itself. The backend only expects something else to be listening at POST {base_url}/chat.

CLI: Direct Agent Mode

Direct agent mode is the default when you do not pass --server-url.

Basic Shape

uv run deep-research-cli research "Your research query"

Useful Flags

uv run deep-research-cli \
  --provider openai \
  --api-style responses \
  --model gpt-5.6-sol \
  --api-key "$OPENAI_API_KEY" \
  --base-url https://api.openai.com/v1 \
  --timeout 900 \
  --poll-interval 10 \
  research "Your research query" \
  --system-prompt "Custom instructions" \
  --output-file report.md

Key flags:

• --provider
• --model
• --api-key
• --base-url
• --api-style
• --timeout
• --poll-interval
• --system-prompt or --system-prompt-file
• --no-analysis
• --output-file
• --json in agent mode only

Live OpenAI CLI Example

Command:

OPENAI_API_KEY="$OPENAI_API_KEY" \
uv run deep-research-cli \
  --provider openai \
  --api-style responses \
  --model gpt-5.6-sol \
  --api-key "$OPENAI_API_KEY" \
  --base-url https://api.openai.com/v1 \
  --timeout 900 \
  --poll-interval 10 \
  research "What are flow matching models in generative AI, and how do they differ from diffusion models?" \
  --system-prompt "Answer in exactly 3 bullets and one final takeaway sentence. Keep the whole answer under 180 words. Prefer recent, high-signal sources." \
  --output-file openai-report.md

Observed output excerpt:

============================================================
RESEARCH REPORT
============================================================
Task ID: <openai_task_id>
Total steps: 72
Search queries: 35
Citations: 8
Execution time: 216.15s

- **Flow-matching models** train continuous normalizing flows by learning a time-dependent vector field that pushes a simple prior (e.g. Gaussian noise) into the data distribution along a chosen probability path ...
- **Diffusion models** instead progressively add noise to data (via an SDE) and learn a score-based denoiser to reverse that process ...
- **Sampling differences:** Flow-matching generates samples by solving a learned ODE in (often) one shot ...

**Takeaway:** Flow-matching models use smooth ODE flows (vector fields) to map noise->data, subsuming diffusion's process as a special case; they typically allow a more direct, faster sampling path.

What this tells you:

• OpenAI Responses mode is genuinely multi-step in deep-research-mcp.
• total_steps and search_queries are meaningful for this backend.
• Direct agent mode blocks until the task completes.

Live Gemini CLI Example

Command:

GEMINI_API_KEY="$GEMINI_API_KEY" \
uv run deep-research-cli \
  --provider gemini \
  --model deep-research-pro-preview-12-2025 \
  --timeout 900 \
  --poll-interval 10 \
  research "What are flow matching models in generative AI, and how do they differ from diffusion models?" \
  --system-prompt "Answer in exactly 3 bullets and one final takeaway sentence. Keep the whole answer under 180 words. Prefer recent, high-signal sources." \
  --output-file gemini-report.md

Observed output excerpt:

============================================================
RESEARCH REPORT
============================================================
Task ID: <gemini_task_id>
Total steps: 1
Execution time: 99.00s

# Flow Matching vs. Diffusion Models

* **Core Concept:** Flow matching is a generative modeling framework that learns a deterministic, continuous velocity field ...
* **Key Differences:** While diffusion models rely on a fixed, stochastic process ...
* **Efficiency:** Because these generation trajectories are straighter and deterministic ...

Ultimately, while the two paradigms share deep mathematical connections, flow matching streamlines the generative process ...

Important Gemini-specific behavior:

• The normalized citation list may be empty even when the report text includes a Sources: section.
• Grounding URLs may appear as Google redirect URLs rather than the final origin URL.
• include_analysis does not map to a Gemini code-execution tool toggle in this backend.

Live DR-Tulu CLI Example

Command:

uv run deep-research-cli \
  --provider dr-tulu \
  --model dr-tulu \
  --base-url http://localhost:8080 \
  --timeout 1800 \
  research "What is flow matching in generative AI?" \
  --system-prompt "Answer in exactly 2 bullets and one takeaway sentence. Keep the whole answer under 120 words." \
  --no-analysis \
  --output-file dr-tulu-report.md

Observed output excerpt:

============================================================
RESEARCH REPORT
============================================================
Task ID: <dr_tulu_task_id>
Total steps: 3
Citations: 25
Execution time: 177.66s

- Flow matching trains a continuous normalizing flow by regressing a conditional drift (vector field) that deterministically maps noise to data in one straight-line ODE ...
- In practice, sampling solves the learned ODE forward ... and recent variants remove ODE solvers at generation time ...

Takeaway: Flow matching defines generative models as learned deterministic transport maps from noise to data via a conditional vector field ...

What this tells you:

• The current dr-tulu backend works against a live POST /chat service.
• total_steps comes from metadata.total_tool_calls.
• Citation extraction works by normalizing metadata.searched_links.
• DR-Tulu latency can still be substantial even for short prompts.

Live status CLI Example

Command:

OPENAI_API_KEY="$OPENAI_API_KEY" \
uv run deep-research-cli \
  --provider openai \
  --api-key "$OPENAI_API_KEY" \
  --base-url https://api.openai.com/v1 \
  status YOUR_OPENAI_TASK_ID

Observed output:

Task ID: YOUR_OPENAI_TASK_ID
Status: completed
Created: <provider_created_timestamp>
Completed: <provider_completed_timestamp>

Note that timestamp formatting is provider-specific:

• OpenAI Responses returned Unix timestamps here.
• Gemini research_status returned formatted datetimes in this environment.

Python API: ResearchConfig + DeepResearchAgent

The direct Python API is the cleanest way to embed the framework in another program.

Generic Pattern

import asyncio
from deep_research_mcp import DeepResearchAgent, ResearchConfig

async def main() -> None:
    config = ResearchConfig(
        provider="openai",
        api_style="responses",
        model="gpt-5.6-sol",
        api_key="YOUR_OPENAI_API_KEY",
        base_url="https://api.openai.com/v1",
        timeout=900,
        poll_interval=10,
    )

    agent = DeepResearchAgent(config)
    result = await agent.research(
        query="What are the current tradeoffs between flow matching and diffusion?",
        system_prompt="Answer in 3 bullets.",
        include_code_interpreter=False,
    )

    print(result.status)
    print(result.task_id)
    print(result.final_report)

asyncio.run(main())

Live Gemini Python Example

Code:

import asyncio
import json
from deep_research_mcp import DeepResearchAgent, ResearchConfig

async def main() -> None:
    config = ResearchConfig(
        provider="gemini",
        model="deep-research-pro-preview-12-2025",
        base_url="https://generativelanguage.googleapis.com",
        timeout=900,
        poll_interval=10,
    )

    agent = DeepResearchAgent(config)
    result = await agent.research(
        query="Why can flow matching models sample faster than diffusion models?",
        system_prompt="Answer in exactly 2 bullets and one takeaway sentence. Keep the whole answer under 140 words. Prefer papers or technical sources.",
        include_code_interpreter=False,
    )

    payload = {
        "status": result.status,
        "task_id": result.task_id,
        "execution_time": result.execution_time,
        "total_steps": result.total_steps,
        "report": result.final_report,
        "citations": [
            {"index": c.index, "title": c.title, "url": c.url}
            for c in result.citations[:5]
        ],
    }
    print(json.dumps(payload, ensure_ascii=False, indent=2))

asyncio.run(main())

Observed output excerpt:

{
  "status": "completed",
  "task_id": "<gemini_task_id>",
  "execution_time": 99.92130708694458,
  "total_steps": 1,
  "report": "# Acceleration in Generative Models\nResearch suggests that flow matching fundamentally accelerates generative sampling by replacing the complex stochasticity of diffusion with a highly efficient, straight-line mathematical path ...",
  "citations": []
}

What to expect from the Python result model:

• result.status is normalized across backends.
• result.task_id is always the backend task or synthetic task ID.
• result.final_report is the main payload.
• result.citations is normalized when the backend can extract them. Do not assume every provider fills it equally.

MCP Server

Start In Stdio Mode

uv run deep-research-mcp

Use this when another client will spawn the server as a subprocess.

Start In HTTP Mode

uv run deep-research-mcp --transport http --host 127.0.0.1 --port 8080

The Streamable HTTP endpoint is:

http://127.0.0.1:8080/mcp

Provider-Pinned HTTP Server Example

This pattern avoids accidental reuse of a different provider's saved credentials:

RESEARCH_PROVIDER=gemini \
RESEARCH_API_KEY="$GEMINI_API_KEY" \
RESEARCH_BASE_URL=https://generativelanguage.googleapis.com \
RESEARCH_MODEL=deep-research-pro-preview-12-2025 \
RESEARCH_POLL_INTERVAL=10 \
uv run deep-research-mcp --transport http --host 127.0.0.1 --port 8081

MCP Tools

deep_research

Use for normal research. Key inputs:

• query
• system_instructions
• include_analysis
• callback_url

The query must contain the complete research question and any user-provided context needed to answer it. Use system_instructions for research methodology, source, scope, and output requirements. Conversational hosts should ask any necessary follow-up questions before calling the tool.

research_status

Use to poll a known task ID.

CLI As MCP Client

When you pass --server-url, the CLI becomes an MCP client instead of creating DeepResearchAgent itself.

Live CLI-over-MCP Example

Command:

uv run deep-research-cli \
  research "Why can flow matching models use fewer inference steps than diffusion models?" \
  --server-url http://127.0.0.1:8081/mcp \
  --system-prompt "Answer in exactly 2 bullets and one takeaway sentence. Keep the whole answer under 140 words. Prefer technical sources." \
  --no-analysis \
  --output-file mcp-report.md

Observed client-side progress output:

[progress] 0.0 Research started...
[progress] 1.0 Research in progress (1 minute)
[progress] 100.0% Research completed successfully

Observed report excerpt:

# Research Report: Why can flow matching models use fewer inference steps than diffusion models?

# Inference Efficiency of Flow Matching

* **Optimal Transport Trajectories:** Unlike diffusion models that reverse stochastic, highly curved random walks, flow matching models learn a continuous, deterministic vector field ...
* **Reduced Discretization Error:** Because these straight flow trajectories possess near-minimal curvature ...

**Takeaway:** Flow matching models require significantly fewer inference steps because they replace tortuous stochastic diffusion processes with highly rectified, deterministic ODEs ...

## Research Metadata
- **Total research steps**: 1
- **Search queries executed**: 0
- **Citations found**: 0
- **Task ID**: <mcp_task_id>
- **Execution time**: 88.10 seconds

Python Speaking MCP Directly

Live research_status Example

Code:

import asyncio
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

TASK_ID = "YOUR_TASK_ID"

async def main() -> None:
    async with streamablehttp_client("http://127.0.0.1:8081/mcp") as (read_stream, write_stream, _):
        async with ClientSession(read_stream, write_stream) as session:
            await session.initialize()
            result = await session.call_tool("research_status", {"task_id": TASK_ID})
            print(result.structuredContent)

asyncio.run(main())

Observed output:

{'result': 'Task YOUR_TASK_ID status: completed\nCreated at: <created_at>\nCompleted at: <completed_at>'}

Backend-Specific Notes

OpenAI Responses Backend

• Implemented in src/deep_research_mcp/backends/openai_backend.py
• Uses client.responses.create(..., background=True)
• Polls with client.responses.retrieve(task_id)
• Uses web_search for Responses models
• Uses an unlimited returned-token budget for supported GPT-5 reasoning models
• Adds code_interpreter only when include_code_interpreter=True
• Omits code_interpreter for legacy Pro models that do not support it
• Uses xhigh reasoning effort for GPT-5.2+ research models and high for earlier GPT-5 models
• enable_reasoning_summaries=True adds summary="auto" to the reasoning settings

Use this when you want:

• background execution
• search-query accounting
• best support for research_status
• the deep-research-mcp repo's intended "deep research" path

OpenAI Chat Completions Backend

Still provider="openai", but set:

--api-style chat_completions

Differences:

• no background task
• no research_status tracking
• no code_interpreter
• good for compatible third-party endpoints

Gemini Backend

• Implemented in src/deep_research_mcp/backends/gemini_backend.py
• Uses google.genai.Client(...).interactions
• Creates background interactions with store=True
• Polls until the interaction is completed
• Ignores include_code_interpreter

Observed real-world consequences from live runs:

• often total_steps is small
• the report may embed a Sources: section directly
• the normalized citation list may still be empty
• URLs may be grounding redirects

DR-Tulu Backend

• Implemented in src/deep_research_mcp/backends/dr_tulu_backend.py
• Sends one request to:

POST {base_url}/chat

• Expects JSON response fields:
  • response
  • metadata.searched_links
  • metadata.total_tool_calls
• research_status() always returns unknown

Correct direct CLI shape:

uv run deep-research-cli \
  --provider dr-tulu \
  --model dr-tulu \
  --base-url http://localhost:8080 \
  research "Your query here"

Correct Python shape:

from deep_research_mcp import DeepResearchAgent, ResearchConfig

config = ResearchConfig(
    provider="dr-tulu",
    model="dr-tulu",
    base_url="http://localhost:8080",
)
agent = DeepResearchAgent(config)

Important limitation:

• The deep-research-mcp repository does not bootstrap DR-Tulu for you.
• You need a separately running DR-Tulu service that exposes /chat.
• Without that service, DR-Tulu examples fail immediately with a connection error.
• The current backend expects base_url without the /chat suffix, because it appends /chat internally.
• A live run was verified against a separately running DR-Tulu deployment whose base URL pointed at the service root; the current backend uses /chat.

Troubleshooting

Symptom: OpenAI call hits Gemini or sends the wrong key

Cause:

• your ~/.deep_research file already has research.api_key or research.base_url for another provider

Fix:

• override --api-key
• override --base-url
• optionally override --model
• or use a provider-specific config file with --config

Symptom: research_status is not useful

Cause:

• you are using chat_completions, dr-tulu, or open-deep-research

Fix:

• use openai + responses or gemini if you need task polling

Symptom: Gemini report has sources in text but citations is empty

Cause:

• the Gemini backend only populates normalized citations when it can map annotations/output objects cleanly

Fix:

• treat final_report as the canonical user-facing output
• treat result.citations as best-effort normalization

Short Recipes

Fastest safe OpenAI command

OPENAI_API_KEY="$OPENAI_API_KEY" \
uv run deep-research-cli \
  --provider openai \
  --api-style responses \
  --model gpt-5.6-sol \
  --api-key "$OPENAI_API_KEY" \
  --base-url https://api.openai.com/v1 \
  research "Your query"

Fastest safe Gemini command

GEMINI_API_KEY="$GEMINI_API_KEY" \
uv run deep-research-cli \
  --provider gemini \
  --model deep-research-pro-preview-12-2025 \
  --api-key "$GEMINI_API_KEY" \
  --base-url https://generativelanguage.googleapis.com \
  research "Your query"

Start an HTTP MCP server and use the CLI as the client

Terminal 1:

RESEARCH_PROVIDER=gemini \
RESEARCH_API_KEY="$GEMINI_API_KEY" \
RESEARCH_BASE_URL=https://generativelanguage.googleapis.com \
uv run deep-research-mcp --transport http --host 127.0.0.1 --port 8081

Terminal 2:

uv run deep-research-cli \
  research "Your query" \
  --server-url http://127.0.0.1:8081/mcp

Final Guidance

If you only remember three things, remember these:

1. Use full provider overrides when your saved TOML file is already specialized.
2. Use openai + responses or gemini when you need status polling.
3. Treat DR-Tulu as an external dependency: the deep-research-mcp repo's DR-Tulu backend is a client, not the service itself.