lmwharton/sieve-mcp
Sieve MCP Server — AI-Powered Venture Capital Due Diligence
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.
"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.
Why Sieve?
Most 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.
What You Get
Capability | Details |
Investment Memo | Full analyst-grade memo with executive summary, key strengths, critical concerns, and actionable recommendation — not a ChatGPT summary |
Deal Scoring (0-140) | Quantified Sieve Score across 7 IMPACT-X dimensions — structured, repeatable, comparable across your portfolio |
Red Flag Detection | Automatically surfaces deal-breakers: founder risk, market timing issues, unsustainable unit economics, missing traction, competitive threats |
Evidence Verification | Every finding tagged as Documented, Discovered, Inferred, or Missing — cross-references pitch deck claims against real-world evidence |
Competitive Landscape | Maps competitors, identifies moat strength, evaluates defensibility and switching costs |
Financial Model Assessment | Evaluates unit economics, pricing power, revenue model viability, and path to profitability |
Market Sizing | TAM/SAM/SOM analysis with timing assessment — is the market ready? |
Team Evaluation | Founder-market fit, team completeness, domain expertise, execution track record |
Traction Analysis | Growth metrics, customer validation, revenue signals, engagement patterns |
Real-time Deal Chat | Ask follow-up questions, challenge findings, explore what-if scenarios, dig into any dimension |
Sector-Aware Analysis | Adapts benchmarks for fintech, healthtech, deeptech, climate, SaaS, consumer, and more |
Stage-Calibrated | Different expectations for pre-seed vs seed vs Series A — doesn't penalize early-stage for missing late-stage metrics |
What Makes Sieve Different
Not a wrapper around ChatGPT. Sieve runs a structured multi-agent analysis pipeline with real-time web research, evidence verification, and domain-specific benchmarks.
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.
Repeatable framework. The same IMPACT-X methodology every time, so you can compare deals apples-to-apples across your portfolio.
Built by VCs. Not a generic AI tool adapted for investing — purpose-built for the way investors actually evaluate deals.
IMPACT-X Framework
Dimension | What Sieve evaluates |
I — Innovators | Founding team quality, experience, domain expertise |
M — Market | Opportunity size, timing, tailwinds |
P — Product | Solution strength, differentiation, technical depth |
A — Advantage | Competitive moat, defensibility, switching costs |
C — Commerce | Business model, unit economics, pricing power |
T — Traction | Growth metrics, validation signals, customer evidence |
X — X-Factor | Unique qualities, timing advantages, intangibles |
Each dimension scores 0-20. Total Sieve Score ranges from 0-140.
Related MCP server: NUVC MCP Server
Quick Start
Install
pip install sieve-mcpOr run directly without installing:
uvx sieve-mcpGet Your API Key
Sign up free at app.sieve.arceusxventures.com
Go to Settings → copy your API key
Free tier: 2 screens/month. Pro: unlimited.
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"sieve": {
"command": "uvx",
"args": ["sieve-mcp"],
"env": {
"SIEVE_API_KEY": "your-api-key"
}
}
}
}Claude Code
claude mcp add sieve -- uvx sieve-mcp
export SIEVE_API_KEY="your-api-key"Cursor / Windsurf
Add to your MCP settings:
{
"mcpServers": {
"sieve": {
"command": "uvx",
"args": ["sieve-mcp"],
"env": {
"SIEVE_API_KEY": "your-api-key"
}
}
}
}Available Tools
Tool | What it does | Read-only |
| Start a Quick Screen — pass a company name, optional website URL, pitch deck text, or description | No |
| Poll analysis progress — see which dimensions are complete and current scores | Yes |
| Get the full investment memo — Sieve Score, recommendation, strengths, concerns, evidence | Yes |
| Check how many screens you've used this billing period | Yes |
Example Workflow
Just talk to your AI assistant naturally:
1. Screen a startup
"Run a Sieve screen on Acme Corp at acme.com"
2. Check progress (analysis takes 2-5 minutes)
"What's the status of that Sieve analysis?"
3. Get the full investment memo
"Show me the Sieve results for Acme Corp"
4. Explore the deal
"What are the red flags? Anything that should kill this deal?"
"How strong is their competitive moat? Who are the main competitors?"
"Walk me through their unit economics — is this business model viable?"
"How does the founding team stack up? Any gaps?"
"What's the market timing like? Is this too early or too late?"
"Compare this deal to the last three I screened"
5. Check your usage
"How many Sieve screens do I have left this month?"
Pro tip: Upload a pitch deck for deeper analysis
Paste pitch deck text or founder meeting notes for maximum accuracy:
"Screen Acme Corp — here's their pitch deck text: [paste]. Also check acme.com"
Sieve 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.
More things you can ask
Use case | Example prompt |
Quick pass/take meeting | "Screen this company and give me the bottom line" |
Investment memo for IC | "Generate a full investment memo I can present to my partners" |
Red flag check | "What are the deal-breakers for this startup?" |
Competitive analysis | "Who competes with this company and how defensible are they?" |
Financial viability | "Does their business model make sense? What are the unit economics?" |
Team assessment | "Evaluate the founding team — any gaps or concerns?" |
Market validation | "Is the market real? What's the TAM and timing?" |
Batch screening | "Screen these 5 startups and rank them by Sieve Score" |
Follow-up prep | "Based on this analysis, what questions should I ask the founders?" |
Portfolio comparison | "How does this deal compare to others I've screened?" |
Who Uses Sieve
Solo GPs screening 50+ deals/month — stop spending hours on obvious passes
Angel investors evaluating startups outside their domain — Sieve brings sector expertise
Emerging fund managers building a repeatable diligence process — consistent framework, every time
Accelerators standardizing evaluation — compare apples to apples across your cohort
Environment Variables
Variable | Required | Default | Description |
| Yes | — | Your Sieve API key (get one free) |
| No |
| API base URL |
Running with Docker
docker build -t sieve-mcp .
docker run -p 8080:8080 -e SIEVE_API_KEY=your-key sieve-mcpDevelopment
# Install locally
pip install -e .
# Run in stdio mode (for MCP clients)
sieve-mcp
# Run in HTTP mode (for remote/container deployment)
sieve-mcp httpAlso Available As
Sieve isn't just an MCP server. Use it however fits your workflow:
Web App — app.sieve.arceusxventures.com — Full experience with real-time deal chat and document upload
REST API — api.sieve.arceusxventures.com/api/docs — Integrate into custom deal flow pipelines
Android App — Screen startups on the go
Links
Website: sieve.arceusxventures.com
Web App: app.sieve.arceusxventures.com
API Docs: api.sieve.arceusxventures.com/api/docs
Contact: hello@arceusxventures.com
License
MIT
Built by ArceusX Ventures — from VCs, for VCs.
Available Tools
8 toolssieve_dataroomARead-only
List all documents in a deal's data room.
Shows what files and content have been uploaded for a deal, along with their processing status.
Inputs: deal_id (required). Returns: object
sieve_dataroom_addA
Add a document to a deal's data room. Creates the deal if needed.
This is the primary way to get documents into Sieve for screening. Upload a pitch deck, financials, or any document -- then call sieve_screen to analyze everything in the data room.
Provide company_name to create a new deal (or find existing), or deal_id to add to an existing deal.
Provide exactly one content source: file_path (local file), text (raw text/markdown), or url (fetch from URL).
Inputs: title (required), company_name, deal_id, website_url, +4 more. Returns: object
sieve_dealsARead-only
List deals in your Sieve pipeline.
Search by company name or list all deals. Returns deal metadata including Sieve scores for screened deals.
Inputs: search, limit. Returns: object
sieve_memoA
Get or generate an investment memo for a deal.
If generate=false (default), retrieves the existing memo. If generate=true, creates a new memo (~15-30 seconds). Requires a completed screen.
Inputs: deal_id (required), generate, memo_type. Returns: object
sieve_resultsARead-only
Get the full results of a completed Sieve analysis.
Returns the Sieve Score (0-140), meeting decision (Take Meeting/Pass/ Need More Info), executive summary, key strengths, and key concerns.
Inputs: deal_id (required), sections. Returns: object
sieve_screenA
Run a Sieve IMPACT-X Quick Screen on a startup.
Analyzes the company across 7 dimensions (Innovators, Market, Product, Advantage, Commerce, Traction, X-Factor) and returns an analysis ID. Takes 2-5 minutes to complete. Upserts -- if the company was previously screened, returns the existing deal (set confirm=true to re-screen).
Two ways to use:
v3 (recommended): First add documents with sieve_dataroom_add, then call sieve_screen(deal_id=...) to analyze everything in the data room.
v2 (legacy): Call sieve_screen(company_name=..., website_url=...) directly. At least one of website_url or pitch_deck_text is required in this mode.
Inputs: company_name, deal_id, website_url, pitch_deck_text, +2 more. Returns: object
sieve_statusARead-only
Check the progress of a Sieve analysis.
Returns which IMPACT-X dimensions are complete with their scores, overall progress percentage, and current phase.
Inputs: deal_id (required). Returns: object
sieve_usageARead-only
Check your Sieve API usage for the current billing period.
Shows screens used, monthly limit, tier, and organization name.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose: listing documents, adding documents, listing deals, running screens, checking status, retrieving results, getting memos, and checking usage. No two tools overlap in functionality.
All tools share the 'sieve_' prefix, but naming patterns are mixed: some are plain nouns (e.g., sieve_dataroom, sieve_deals) while others use verb_noun (e.g., sieve_dataroom_add). This minor inconsistency prevents a perfect score.
With 8 tools, the set covers the full document screening lifecycle without unnecessary duplication. Each tool serves a necessary role, and the count feels appropriate for the domain.
The tool set covers the primary workflow: add documents, screen, check status, get results, and generate memos. However, it lacks update or delete operations for documents or deals, which could be useful but are not critical for core use.
Maintenance
Related MCP Connectors
Pre-diligence AI for founders, investors, and firms — multi-agent pitch analysis and deal flow.
VC and startup intelligence: AI VC Finder, deal sourcing, deck analysis and market data.
Research, strategy, financial models and decks, priced and approved per job, in your AI assistant
AI-powered board deck generation and governance reporting for private equity firms.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceGenerate executive-ready presentations via API. 32 slide types, 24 chart types, 15 themes, finance vertical with DCF/comp tables/waterfalls. Renders PPTX from JSON IR or natural language prompts.7MIT

NUVC MCP Serverofficial
AlicenseNot gradedqualityCmaintenanceProvides VC-grade startup intelligence, allowing founders to validate ideas and VCs to screen deals using tools like scoring, investor matching, and financial analysis.212 npmMIT- AlicenseNot gradedqualityDmaintenanceA self-owned deal memory layer that turns meeting notes, emails, and calls into structured deal signals for solo founders and early teams.MIT
- FlicenseBqualityDmaintenanceConverts meetings, chats, and notes into reusable knowledge for a venture capital firm, enabling knowledge capture and retrieval via Claude or Codex.4-