{
  "markdown": "[![PyPI version](https://badge.fury.io/py/sieve-mcp.svg)](https://pypi.org/project/sieve-mcp/)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![MCP Compatible](https://img.shields.io/badge/MCP-Compatible-green.svg)](https://modelcontextprotocol.io)\n\n# Sieve MCP Server — AI-Powered Venture Capital Due Diligence\n\n**The first MCP server purpose-built for venture capital.** Drop a company name into Claude, Cursor, or Windsurf and get a quantified investment memo in 5 minutes — not a ChatGPT summary, a real analyst-grade IMPACT-X assessment with every claim verified against evidence.\n\n> **\"Screen a startup called Acme Corp\"** → Sieve researches the company, scores it across 7 dimensions, verifies every claim, and tells you: **Take the meeting** or **Pass**.\n\n## Why Sieve?\n\nMost VCs screen 50+ deals a month. Most of those are obvious passes — but you still spend 2-3 hours per deal on basic diligence before you know that. Sieve does that work in 5 minutes.\n\n### What You Get\n\n| Capability | Details |\n|---|---|\n| **Investment Memo** | Full analyst-grade memo with executive summary, key strengths, critical concerns, and actionable recommendation — not a ChatGPT summary |\n| **Deal Scoring (0-140)** | Quantified Sieve Score across 7 IMPACT-X dimensions — structured, repeatable, comparable across your portfolio |\n| **Red Flag Detection** | Automatically surfaces deal-breakers: founder risk, market timing issues, unsustainable unit economics, missing traction, competitive threats |\n| **Evidence Verification** | Every finding tagged as Documented, Discovered, Inferred, or Missing — cross-references pitch deck claims against real-world evidence |\n| **Competitive Landscape** | Maps competitors, identifies moat strength, evaluates defensibility and switching costs |\n| **Financial Model Assessment** | Evaluates unit economics, pricing power, revenue model viability, and path to profitability |\n| **Market Sizing** | TAM/SAM/SOM analysis with timing assessment — is the market ready? |\n| **Team Evaluation** | Founder-market fit, team completeness, domain expertise, execution track record |\n| **Traction Analysis** | Growth metrics, customer validation, revenue signals, engagement patterns |\n| **Real-time Deal Chat** | Ask follow-up questions, challenge findings, explore what-if scenarios, dig into any dimension |\n| **Sector-Aware Analysis** | Adapts benchmarks for fintech, healthtech, deeptech, climate, SaaS, consumer, and more |\n| **Stage-Calibrated** | Different expectations for pre-seed vs seed vs Series A — doesn't penalize early-stage for missing late-stage metrics |\n\n### What Makes Sieve Different\n\n- **Not a wrapper around ChatGPT.** Sieve runs a structured multi-agent analysis pipeline with real-time web research, evidence verification, and domain-specific benchmarks.\n- **We tell you what we don't know.** Every finding is evidence-typed (Documented / Discovered / Inferred / Missing) so you see exactly what's verified and where the gaps are.\n- **Repeatable framework.** The same IMPACT-X methodology every time, so you can compare deals apples-to-apples across your portfolio.\n- **Built by VCs.** Not a generic AI tool adapted for investing — purpose-built for the way investors actually evaluate deals.\n\n### IMPACT-X Framework\n\n| Dimension | What Sieve evaluates |\n|---|---|\n| **I** — Innovators | Founding team quality, experience, domain expertise |\n| **M** — Market | Opportunity size, timing, tailwinds |\n| **P** — Product | Solution strength, differentiation, technical depth |\n| **A** — Advantage | Competitive moat, defensibility, switching costs |\n| **C** — Commerce | Business model, unit economics, pricing power |\n| **T** — Traction | Growth metrics, validation signals, customer evidence |\n| **X** — X-Factor | Unique qualities, timing advantages, intangibles |\n\nEach dimension scores 0-20. Total Sieve Score ranges from 0-140.\n\n## Quick Start\n\n### Install\n\n```bash\npip install sieve-mcp\n```\n\nOr run directly without installing:\n\n```bash\nuvx sieve-mcp\n```\n\n### Get Your API Key\n\n1. Sign up free at [app.sieve.arceusxventures.com](https://app.sieve.arceusxventures.com)\n2. Go to **Settings** → copy your API key\n3. Free tier: 2 screens/month. Pro: unlimited.\n\n### Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"sieve\": {\n      \"command\": \"uvx\",\n      \"args\": [\"sieve-mcp\"],\n      \"env\": {\n        \"SIEVE_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n### Claude Code\n\n```bash\nclaude mcp add sieve -- uvx sieve-mcp\nexport SIEVE_API_KEY=\"your-api-key\"\n```\n\n### Cursor / Windsurf\n\nAdd to your MCP settings:\n\n```json\n{\n  \"mcpServers\": {\n    \"sieve\": {\n      \"command\": \"uvx\",\n      \"args\": [\"sieve-mcp\"],\n      \"env\": {\n        \"SIEVE_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n## Available Tools\n\n| Tool | What it does | Read-only |\n|---|---|---|\n| `sieve_screen` | Start a Quick Screen — pass a company name, optional website URL, pitch deck text, or description | No |\n| `sieve_status` | Poll analysis progress — see which dimensions are complete and current scores | Yes |\n| `sieve_summary` | Get the full investment memo — Sieve Score, recommendation, strengths, concerns, evidence | Yes |\n| `sieve_usage` | Check how many screens you've used this billing period | Yes |\n\n## Example Workflow\n\nJust talk to your AI assistant naturally:\n\n**1. Screen a startup**\n> \"Run a Sieve screen on Acme Corp at acme.com\"\n\n**2. Check progress** (analysis takes 2-5 minutes)\n> \"What's the status of that Sieve analysis?\"\n\n**3. Get the full investment memo**\n> \"Show me the Sieve results for Acme Corp\"\n\n**4. Explore the deal**\n> \"What are the red flags? Anything that should kill this deal?\"\n>\n> \"How strong is their competitive moat? Who are the main competitors?\"\n>\n> \"Walk me through their unit economics — is this business model viable?\"\n>\n> \"How does the founding team stack up? Any gaps?\"\n>\n> \"What's the market timing like? Is this too early or too late?\"\n>\n> \"Compare this deal to the last three I screened\"\n\n**5. Check your usage**\n> \"How many Sieve screens do I have left this month?\"\n\n### Pro tip: Upload a pitch deck for deeper analysis\n\nPaste pitch deck text or founder meeting notes for maximum accuracy:\n\n> \"Screen Acme Corp — here's their pitch deck text: [paste]. Also check acme.com\"\n\nSieve cross-references every pitch deck claim against real-world evidence. When a founder says \"fastest-growing in the category,\" Sieve checks if that's actually true.\n\n### More things you can ask\n\n| Use case | Example prompt |\n|---|---|\n| **Quick pass/take meeting** | \"Screen this company and give me the bottom line\" |\n| **Investment memo for IC** | \"Generate a full investment memo I can present to my partners\" |\n| **Red flag check** | \"What are the deal-breakers for this startup?\" |\n| **Competitive analysis** | \"Who competes with this company and how defensible are they?\" |\n| **Financial viability** | \"Does their business model make sense? What are the unit economics?\" |\n| **Team assessment** | \"Evaluate the founding team — any gaps or concerns?\" |\n| **Market validation** | \"Is the market real? What's the TAM and timing?\" |\n| **Batch screening** | \"Screen these 5 startups and rank them by Sieve Score\" |\n| **Follow-up prep** | \"Based on this analysis, what questions should I ask the founders?\" |\n| **Portfolio comparison** | \"How does this deal compare to others I've screened?\" |\n\n## Who Uses Sieve\n\n- **Solo GPs** screening 50+ deals/month — stop spending hours on obvious passes\n- **Angel investors** evaluating startups outside their domain — Sieve brings sector expertise\n- **Emerging fund managers** building a repeatable diligence process — consistent framework, every time\n- **Accelerators** standardizing evaluation — compare apples to apples across your cohort\n\n## Environment Variables\n\n| Variable | Required | Default | Description |\n|---|---|---|---|\n| `SIEVE_API_KEY` | Yes | — | Your Sieve API key ([get one free](https://app.sieve.arceusxventures.com/settings)) |\n| `SIEVE_API_URL` | No | `https://api.sieve.arceusxventures.com` | API base URL |\n\n## Running with Docker\n\n```bash\ndocker build -t sieve-mcp .\ndocker run -p 8080:8080 -e SIEVE_API_KEY=your-key sieve-mcp\n```\n\n## Development\n\n```bash\n# Install locally\npip install -e .\n\n# Run in stdio mode (for MCP clients)\nsieve-mcp\n\n# Run in HTTP mode (for remote/container deployment)\nsieve-mcp http\n```\n\n## Also Available As\n\nSieve isn't just an MCP server. Use it however fits your workflow:\n\n- **Web App** — [app.sieve.arceusxventures.com](https://app.sieve.arceusxventures.com) — Full experience with real-time deal chat and document upload\n- **REST API** — [api.sieve.arceusxventures.com/api/docs](https://api.sieve.arceusxventures.com/api/docs) — Integrate into custom deal flow pipelines\n- **Android App** — Screen startups on the go\n\n## Links\n\n- **Website**: [sieve.arceusxventures.com](https://sieve.arceusxventures.com)\n- **Web App**: [app.sieve.arceusxventures.com](https://app.sieve.arceusxventures.com)\n- **API Docs**: [api.sieve.arceusxventures.com/api/docs](https://api.sieve.arceusxventures.com/api/docs)\n- **PyPI**: [pypi.org/project/sieve-mcp](https://pypi.org/project/sieve-mcp/)\n- **Contact**: [hello@arceusxventures.com](mailto:hello@arceusxventures.com)\n\n## License\n\nMIT\n\n---\n\nBuilt by [ArceusX Ventures](https://sieve.arceusxventures.com) — from VCs, for VCs.\n\n<!-- mcp-name: io.github.lmwharton/sieve-mcp -->\n",
  "bytes": 9574,
  "sha": "189d9a54d0add0f8257f89f71fe83d915e08fe25d7710bb1dab160d7251e6b9c",
  "repo_slug": "lmwharton/sieve-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_lmwharton_sieve_mcp_46a56586/readme"
}