Skip to main content
Glama
lmwharton/sieve-mcp

lmwharton/sieve-mcp

by lmwharton

PyPI version Python 3.10+ License: MIT MCP Compatible

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-mcp

Or run directly without installing:

uvx sieve-mcp

Get Your API Key

  1. Sign up free at app.sieve.arceusxventures.com

  2. Go to Settings → copy your API key

  3. 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

sieve_screen

Start a Quick Screen — pass a company name, optional website URL, pitch deck text, or description

No

sieve_status

Poll analysis progress — see which dimensions are complete and current scores

Yes

sieve_summary

Get the full investment memo — Sieve Score, recommendation, strengths, concerns, evidence

Yes

sieve_usage

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

SIEVE_API_KEY

Yes

—

Your Sieve API key (get one free)

SIEVE_API_URL

No

https://api.sieve.arceusxventures.com

API base URL

Running with Docker

docker build -t sieve-mcp .
docker run -p 8080:8080 -e SIEVE_API_KEY=your-key sieve-mcp

Development

# Install locally
pip install -e .

# Run in stdio mode (for MCP clients)
sieve-mcp

# Run in HTTP mode (for remote/container deployment)
sieve-mcp http

Also Available As

Sieve isn't just an MCP server. Use it however fits your workflow:

License

MIT


Built by ArceusX Ventures — from VCs, for VCs.

Available Tools

8 tools
sieve_dataroomA
Read-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_dealsA
Read-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_resultsA
Read-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_statusA
Read-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_usageA
Read-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

    A4.3/5.0

    Scored across 8 tools

    Disambiguation5/5

    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.

    Naming Consistency4/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides VC-grade startup intelligence, allowing founders to validate ideas and VCs to screen deals using tools like scoring, investor matching, and financial analysis.
      212 npm
      MIT