MCP Deep Research Server
Autonomous multi-source deep research with DuckDuckGo search (zero API keys), parallel scrapers, markdown cleaning, synthesis with citations, fact-checking, and persistent memory.
Que pouvez-vous faire avec MCP Deep Research Server ?
- ✅ Logo + pro README + badges
- ✅ GitHub Actions CI (Node 18/20/22) + Release workflow
- ✅ Issue templates, PR template, CONTRIBUTING, SECURITY
- ✅
.editorconfig, smoke test script - ✅ Optimized
package.jsonfor npm publishing - ✅ CHANGELOG tracked
Installation
Les étapes d'installation sont dans la documentation ci-dessous. Documentation
Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
Deep Research MCP Server
Non-generic MCP for real research. Search → Scrape → Synthesize → Fact-check → Remember.
Why not generic?
| Generic MCP (boring) | This MCP (pro) |
|---|---|
echo, fetch | Orchestrated deep research |
| Returns raw HTML | Cheerio + Turndown → clean markdown + headings, links, meta |
| No memory | Persistent memory in ~/.mcp-deep-research/ |
| One page at a time | Parallel 3-worker scraper, 10min cache |
| No reasoning | Fact-check with stance scoring, contradiction detection |
Architecture
graph LR
A[User: deep_research topic] --> B[search_web DDG HTML]
B --> C[Parallel Scrape x3-8]
C --> D[cheerio clean + turndown md]
D --> E[extract_insights heuristic]
E --> F[Synthesize Report + Citations]
F --> G[memory_save + history]
F --> H[Return to Claude]
I[compare_sources] --> C
J[fact_check_claim] --> B
K[memory_search] --> G
Tools (8)
| Tool | What it does | Params | ||
|---|---|---|---|---|
search_web | DuckDuckGo HTML search, no API key, UDDG decode | query, count 1-10, timeFilter | ||
scrape_page | Fetch + main-content heuristic + markdown | `url, format=markdown | text | full, extractMainOnly` |
extract_insights | Entities, stats regex, key-point scoring, reading time | content, goal? | ||
deep_research | Power tool — search → parallel scrape → synthesize report | `topic, depth=quick | standard | deep, maxSources, saveMemory` |
compare_sources | 2-5 URLs → consensus vs unique vs contradictions | urls[], focus? | ||
fact_check_claim | Searches support + debunked OR false, heuristic verdict | claim, searchDepth | ||
memory_save | Save finding to JSON, survives restarts | key, value, tags[], source? | ||
memory_search | Fuzzy search in persistent memory | query, tags[], limit |
Resources:
research://memory— all saved findingsresearch://history— last 100 actionsresearch://stats— cache size, uptime
Prompts:
deep-dive-research— full research workflowfact-check— fact-checker squadcompare-narratives— bias & comparison table
Quickstart & Installation
⚡ 1-Click Auto Setup for Claude Desktop (Recommended)
Run this single command in your terminal:
npx mcp-deep-research-server --install
That's it! It automatically detects your OS, writes the config to your
claude_desktop_config.json, and configures the 8 research tools. Just restart Claude Desktop.
📦 Install via Smithery
To automatically install for Claude Desktop or Cursor via Smithery:
npx -y @smithery/cli install mcp-deep-research-server --client claude
🛠️ Manual / Other Clients Setup
Run via npx:
npx mcp-deep-research-server
Or build from source:
git clone https://github.com/SECRET4422/mcp-deep-research-server.git
cd mcp-deep-research-server
npm install
npm run build
🤖 Agent Skill (Claude Code / Antigravity / Cursor / Agent Frameworks)
This repository includes an open-standard Agent Skill that teaches AI coding assistants when and how to autonomously run deep research workflows.
- Import via skill directory:
skills/deep-research/ - Spec compliant with Claude Code, Cursor, and Google Antigravity agents.
Test (smoke)
npm run test:mcp
# or
npm run inspect # opens http://localhost:6274
Manually tested:
[search] Dehradun → 3 results ✓
[deep_research] What is MCP → 3 sources in 2.1s ✓
tools/list → 8 tools ✓
Add to Claude Desktop
Edit config:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"deep-research": {
"command": "node",
"args": ["/absolute/path/to/mcp-deep-research-server/build/index.js"]
}
}
}
Restart Claude Desktop.
Add to Cursor / Windsurf / VS Code
.cursor/mcp.json or mcp.json:
{
"mcpServers": {
"deep-research": {
"command": "node",
"args": ["./build/index.js"],
"cwd": "/path/to/mcp-deep-research-server"
}
}
}
Example Prompts
Deep Research:
Use deep_research to research "Best LLM fine-tuning in 2026, depth deep" then compare LoRA vs QLoRA
Fact Check:
Fact check claim: "Bun is faster than Node" using fact_check_claim
Compare:
Compare these 3 URLs about MCP architecture focusing on security: https://modelcontextprotocol.io/docs/getting-started/intro https://www.anthropic.com/news/model-context-protocol https://en.wikipedia.org/wiki/Model_Context_Protocol
See examples/claude-example.md for more.
Data Storage
All in ~/.mcp-deep-research/:
memory.json— persistent findingshistory.json— audit log (100 max)cache/— reserved
No DB, no external calls except search/scrape.
Pro Features in v1.1.0
- ✅ Logo + pro README + badges
- ✅ GitHub Actions CI (Node 18/20/22) + Release workflow
- ✅ Issue templates, PR template, CONTRIBUTING, SECURITY
- ✅
.editorconfig, smoke test script - ✅ Optimized
package.jsonfor npm publishing - ✅ CHANGELOG tracked
Roadmap
- [ ] Tavily / Brave API fallback if keys present
- [ ] PDF parsing via
pdf-parse - [ ] YouTube transcript tool
- [ ] Vector search on memory (embeddings)
- [x] SSRF protection — private/internal IP blocklist for
scrape_page - [x] Smithery & Glama registry integration
Dev
npm run dev # tsx watch
npm run build
npm run lint
Guidelines in CONTRIBUTING.md.
License
MIT © Prabhakar Pal — See LICENSE
Built with 🧠 for Dehradun → World. Not a generic MCP.
Questions fréquentes
Qu'est-ce que MCP Deep Research Server ?
Autonomous multi-source deep research with DuckDuckGo search (zero API keys), parallel scrapers, markdown cleaning, synthesis with citations, fact-checking, and persistent memory.
Comment installer MCP Deep Research Server ?
Suivez les étapes d'installation de sa documentation, affichée sur cette page et dans son dépôt.
MCP Deep Research Server est-il open source ?
Oui. Son code est sur GitHub sous licence MIT.
Qui maintient MCP Deep Research Server ?
Il est publié par SECRET4422. AI.tn le référence sans le maintenir ni le recommander.
Issu des listes communautaires awesome-mcp-servers et du dépôt GitHub du projet. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.