lmwharton/sieve-mcp

Overview

Sieve-MCP takes a company name and returns a score across seven startup evaluation dimensions, helping investors decide which meetings are worth taking. It runs as a Python-based tool that automates the initial screening process.

Best for

Best for
Early‑stage investors and analysts needing fast, repeatable startup evaluations.

Use cases

• Quickly scoring a batch of startup names to prioritize leads
• Automating initial due diligence checks for early-stage investments
• Integrating startup assessment into a larger deal flow pipeline

Notes

Sieve-MCP takes a company name and returns a score across seven startup evaluation dimensions, helping investors decide which meetings are worth taking. It runs as a Python-based tool that automates the initial screening process.

4 stars on GitHub. Last updated 2026-03-18. Licensed MIT.

Use cases

• Quickly scoring a batch of startup names to prioritize leads
• Automating initial due diligence checks for early-stage investments
• Integrating startup assessment into a larger deal flow pipeline

Pros

• Provides a structured, multi‑dimension score from just a company name
• Saves time on manual research during early screening
• Simple input/output that fits into existing workflows

Cons

• Scoring depends on the freshness and breadth of underlying public data
• May miss qualitative or off‑record signals that a human would catch
• Limited to the seven predefined dimensions without customization

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.