OpenPitch

Name: OpenPitch
Author: Avierovich

@Avierovich

关于 OpenPitch

Open, real-time intelligence on AI startups — valuations, ARR, funding — every figure sourced, dated, and confidence-scored, with public-source contradiction flags. A free PitchBook alternative your AI agent can read: read-only, zero LLM calls, no API key. Run with: uvx openpitch

基本信息

分类

AI 与智能体

传输方式

stdio

发布者

Avierovich

提交者

Avierovich

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "openpitch": {
      "command": "uvx",
      "args": [
        "openpitch-mcp"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is OpenPitch?

OpenPitch is a free, open-source MCP server that provides a real-time intelligence layer for AI startups — acting as a public, confidence-scored, sourced alternative to PitchBook and CB Insights. It mines podcasts, news, SEC filings, and web sources to extract metrics like valuation, ARR, and funding, then reconciles contradictions into a consensus with provenance. It's built for AI agents (Claude Code, Codex) and for anyone who needs a fresh, traceable first look at AI companies.

How to use OpenPitch?

No API key or signup required. Use uvx openpitch-mcp for zero-install, or pip install openpitch then run openpitch-mcp. Configure your agent's MCP settings as shown in the README. For the pipeline (rebuild data), clone the repo and use openpitch seed. Data lives in the git repo as committed JSON, read by the local server.

Key features of OpenPitch

Mines podcasts, news, SEC filings, and the web for metrics
Every figure linked to its original source (podcast timestamp, filing, article)
Confidence-scored based on source reliability, corroboration, and freshness
Reconciles conflicting sources, surfacing consensus range and contradiction flags
Learns which sources to trust over time
Version-tracked via git history as audit log
Composable: emits typed events other agents can subscribe to
A2A-discoverable via generated agent card
60-second install, free to run and use

Use cases of OpenPitch

Ask your coding agent for AI startup metrics with sourced confidence
Build a newsletter agent that triggers on material events
Create a press/PR workflow that routes funding/valuation events above a confidence threshold
Drive investor outbound by monitoring universe entries and growth thresholds
Give your AI a grounded, sourced fact base to avoid hallucinating AI‑company numbers

FAQ from OpenPitch

Is OpenPitch really free? No API key or signup?

Yes — the data is committed to a public repository. The MCP server reads it locally. There is no key, no signup, and it runs entirely on free tiers. No cost to run or use.

What data does OpenPitch cover?

Global AI startups (140+ profiled across 12 sectors) and a dedicated MENA AI/tech segment. The top 50 are dynamically ranked by VC attention. Coverage grows daily via auto‑discovery.

How does OpenPitch handle conflicting sources?

When sources disagree, OpenPitch returns a consensus range plus a contradiction flag. It never silently guesses — you see the variance and can inspect each source.

What transport does the MCP server use?

The MCP server runs locally over stdio. Configuration is done via the agent's MCP config (e.g., Claude Code or Codex). There is no server‑side component.

What are the known limits of OpenPitch?

Figures are probabilistic, not verified. Coverage is narrow by design (global AI + MENA segment). It is not investment advice. Always verify before acting. Open quality items are tracked publicly.

AI 与智能体分类下的更多 MCP 服务器

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K