Obra CFO
Local-first MCP server that simulates an investment committee on your pitch materials to assess funding readiness, integrating with Obra CTO for technical evidence.
README
Obra CFO
A local-first MCP server that makes you funding-ready. You install it in your own Claude. It reads your pitch materials on your machine and runs the investment committee on you before a real one does. Nothing is uploaded.
This is the free preview of Obra's role lineup, and it stays free and local. It is the sibling of the Obra CTO: the CTO proves your build, the CFO turns that proof into a funding case. The full playbook, the deep committee, and the templates that fix each gap live in the Build with Obra community.
The Obra founders' toolkit
Two free, local, open-source MCPs built to work as a pair:
- Obra CTO: is it built? Scores your codebase and surfaces what a technical diligence would flag. GitHub · npm
- Obra CFO (this one): is it fundable? Runs the investment committee on your pitch and turns your verified build into a funding case. GitHub · npm
Run the CTO first. The CFO reads its report as grade-A technical evidence. The method, the deep versions, and Obra in beta live in Build with Obra.
Why local-first
A tool that reads your deck, plan, and financials should not ship them somewhere. This server makes no network calls. Your materials stay where they are. You can read every line of this server before you run it, which is the point of keeping it open.
Two modes
Build. If you have no deck yet or a weak one, deck_blueprint hands your Claude the
framework for a fundable deck at your stage: the slide structure with an evidence bar for
each, the research to run first, and the artifacts to produce before the deck exists
(business plan, pricing, go-to-market). Each piece is a paste-in prompt you give your own
Claude. You build it on your machine; we give the framework, not the finished writing.
Rank. When the deck exists, prepare_assessment reads your materials and hands your
Claude a rigorous rubric. Your Claude separates facts from assumptions, extracts your
thesis, rates each dimension with evidence and confidence, finds your weakest load-bearing
assumption, and runs a six-persona investment committee. Then score_funding_readiness
turns that into a stage-calibrated dashboard.
What a dashboard looks like
# Obra CFO: funding readiness
## 74 / 100 · Promising, diligence required
| Signal | Reading |
|---|---|
| Investment score | 74 / 100 |
| Confidence in assessment | 61% |
| Venture return potential | High |
| Execution risk | Medium |
| Market risk | Medium |
| Team risk | Low |
| Technical risk | Low (from Obra CTO: 88/100, grade A) |
| Recommendation | Proceed to targeted diligence |
Under it: your facts/assumptions/opinions ledger, your weakest assumption, what must be true, the unknowns register, and the committee views. Calibrated to your stage, not a one-size score.
The Obra CTO handoff
The CFO reads the Obra CTO's report from .obra/cto-report.json if it is there. A
verified, tested build is grade-A technical evidence that a deck alone can never claim,
and it feeds the Technical Reviewer and your Moat slide. If the report is missing, the
CFO tells you to run the CTO first, because without it your technical claims rest on
assertion (grade D) and an investor's diligence will cap them exactly the same way.
Tools
deck_blueprintreturns the fundable-deck framework and the prompts to build it.prepare_assessmentreads your materials and returns the assessment rubric for your Claude to work through.score_funding_readinessturns your Claude's structured assessment into the dashboard.
A normal run is: build the deck (blueprint) or point at your existing one, prepare the assessment, then score.
Install
Add it to your Claude MCP config (Claude Desktop or Claude Code):
{
"mcpServers": {
"obra-cfo": {
"command": "npx",
"args": ["-y", "obra-cfo"]
}
}
}
Then ask your Claude: "Give me the Obra CFO pitch deck blueprint for seed stage," or "Assess my funding materials in ./fundraise with Obra CFO."
Prefer to run from source? Clone the repo, run npm install && npm run build, and point
the config at node /absolute/path/to/obra-cfo/dist/index.js.
What this is not
Not a deck generator, not a guarantee of a term sheet, not a replacement for your own Claude reading your materials. It is the investment committee, run on you first, from your real materials and your verified build, so you walk in prepared.
What's next
The Obra CFO is the free preview. To go further:
- The full cook: the deep authoring behind each slide, current market intelligence, the full six-persona committee, and the templates that fix each gap.
- The rest of the team: the Obra CTO for build readiness, and each new role as it ships.
- Obra itself, in beta: the AI employee that runs your back office. Members go first.
See the whole toolset and where it is going at https://get-obra.com/build
The full method and the community live in Build with Obra: https://www.skool.com/build-with-obra-5361/about
License
Apache-2.0.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.