Sieve MCP Server

AI startup due diligence — screen companies across 7 dimensions, get a Sieve Score.

Local serverstdioGo

What is the Sieve MCP server?

AI startup due diligence — screen companies across 7 dimensions, get a Sieve Score. That is what the sieve mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

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.

The tools it exposes

The server publishes 4 tools. What each one is for:

  • sieve_screen — Start a Quick Screen — pass a company name, optional website URL, pitch deck text, or description
  • sieve_status — Poll analysis progress — see which dimensions are complete and current scores
  • sieve_summary — Get the full investment memo — Sieve Score, recommendation, strengths, concerns, evidence
  • sieve_usage — Check how many screens you've used this billing period

Getting it running

Installation goes through your MCP client rather than a global install: point it at sieve-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What it needs from you

Configuration is passed through the environment: SIEVE_API_KEY, SIEVE_API_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

Plenty of payments and commerce servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Sieve's toolset — sieve_screen, sieve_status, sieve_summary and 1 more — is a fair guide to whether it matches your workflow. It is maintained by lmwharton; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
sieve_screenStart a Quick Screen — pass a company name, optional website URL, pitch deck text, or description
sieve_statusPoll analysis progress — see which dimensions are complete and current scores
sieve_summaryGet the full investment memo — Sieve Score, recommendation, strengths, concerns, evidence
sieve_usageCheck how many screens you've used this billing period

How to install the Sieve MCP server

{
  "mcpServers": {
    "sieve": {
      "command": "uvx",
      "args": ["sieve-mcp"],
      "env": {
        "SIEVE_API_KEY": "your-api-key"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
SIEVE_API_KEYCredential the server authenticates with.Yes
SIEVE_API_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Sieve to sieve screen.
  • Use Sieve to sieve status.
  • Use Sieve to sieve summary.

Frequently asked questions

It connects Sieve to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (sieve_screen, sieve_status, sieve_summary, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Sieve directly.