Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Obra CFO Assess my pitch deck for seed funding readiness"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
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.
Related MCP server: checkyourself
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.
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.
# 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 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.
deck_blueprint returns the fundable-deck framework and the prompts to build it.
prepare_assessment reads your materials and returns the assessment rubric for your
Claude to work through.
score_funding_readiness turns 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.
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.
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.
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
Apache-2.0.
Return the framework for a fundable pitch deck at your stage: the slide structure with an evidence bar for each, the research to run first (as paste-in prompts for your Claude), and the artifacts to produce before the deck exists (business plan, pricing, go-to-market). Use this when you have no deck yet or a weak one. It reads your Obra CTO report if present. Then build the deck and ask the CFO to rank it.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Project root to look for an Obra CTO report (.obra/cto-report.json). Defaults to the working directory. | |
| stage | No | Funding stage: pre-seed, seed, or series-a. Defaults to pre-seed. | |
| sector | No | Optional: your sector or one-line company description. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description is transparent about reading the Obra CTO report if present and the subsequent actions. No annotations were provided, so the description carries the full burden. It does not mention any side effects, but for a blueprint-generation tool, this is likely read-only. The behavior is clearly described.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences long and front-loads the purpose. Each sentence adds value: first sentence defines output, second gives usage context, third explains workflow. It is concise and well-structured, though slightly wordy in the first sentence.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description thoroughly explains the return values (slide structure, evidence bar, research prompts, artifacts). It also covers prerequisites (reading Obra) and follow-up actions (build deck, ask CFO). This is complete for a tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all three parameters (path, stage, sector). The description adds some context (path is for Obra report, stage defaults to pre-seed, sector is optional) but largely reinforces the schema. The value added is modest, earning a baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns 'the framework for a fundable pitch deck at your stage' and details the specific outputs: slide structure, evidence bar, research prompts, and artifacts. This distinguishes it from siblings prepare_assessment and score_funding_readiness, which focus on different tasks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this when you have no deck yet or a weak one.' It also provides a workflow: reads Obra CTO report, then build deck and ask CFO to rank it. This gives clear guidance on when and how to use the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the founder's funding materials (deck, plan, financials, one-pager) from a local path and return their contents with a rigorous assessment rubric. YOU, the host model, then assess them (separate facts from assumptions, extract the thesis, rate each dimension with evidence and confidence, find the weakest assumption, run the six-persona committee) and call score_funding_readiness with the structured result. Reads the Obra CTO report if present so technical claims rest on verified evidence. Materials stay local.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | A folder holding your materials, or a single file. Defaults to the working directory. | |
| files | No | Optional explicit list of file paths to read instead of scanning. | |
| stage | No | Funding stage: pre-seed, seed, or series-a. Defaults to pre-seed. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the tool's behavior: reads materials from local path, returns contents with rubric, and that materials stay local. It also describes the workflow in which the host model performs further assessment, ensuring transparency about the tool's role.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is moderately concise but includes some redundancy (e.g., repeating 'YOU, the host model'). It is structured with a clear first sentence stating the primary action, then explaining the workflow. It could be slightly more terse, but it remains readable and informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and the moderate complexity (3 parameters, all optional), the description is fairly complete. It explains what input to provide, what the tool returns, and how it integrates with the sibling tool score_funding_readiness. However, it does not describe the return format in detail, which is a minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds context beyond the schema: it clarifies that 'path' defaults to working directory, 'files' is an optional explicit list, and 'stage' includes examples. However, it does not significantly enhance understanding of parameter usage beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reads founder's funding materials from a local path and returns contents with a rigorous assessment rubric, distinguishing itself from sibling tools by specifying the subsequent workflow (host model assesses and calls score_funding_readiness). The verb 'prepare' is appropriate and the resource is well-defined.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly explains when to use the tool (to prepare a funding assessment) and mentions the subsequent step (calling score_funding_readiness). It also notes reading the Obra CTO report if present. However, it does not explicitly state when not to use it or provide alternative scenarios, but the context is clear enough for an AI agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Turn your structured assessment (from prepare_assessment) into a stage-calibrated funding-readiness dashboard: investment score, confidence, risk register, the facts/assumptions/opinions ledger, your weakest assumption, what must be true, the unknowns, and the investment committee. Reads the Obra CTO report for technical risk.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Project root to look for the Obra CTO report. Defaults to the working directory. | |
| stage | Yes | ||
| ledger | No | ||
| thesis | Yes | ||
| unknowns | Yes | ||
| committee | Yes | ||
| synthesis | No | ||
| dimensions | Yes | ||
| companyName | No | ||
| improvements | No | ||
| whatMustBeTrue | Yes | ||
| weakestAssumption | Yes | ||
| timeToNextValidation | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It states the tool reads the Obra CTO report for technical risk and produces dashboard components. However, it does not mention side effects, performance, or what happens if inputs are missing, leaving some transparency gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that packs key information, but it is somewhat dense and could benefit from structured formatting. It remains concise without superfluous content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 13 parameters, many required nested objects, and no output schema, the description is incomplete. It lists dashboard components but does not explain how inputs map to outputs or provide usage examples, leaving significant gaps for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 8%, and the description adds no parameter explanations beyond hinting at the 'path' parameter via 'Reads the Obra CTO report'. With 13 parameters, many nested, the description fails to clarify their roles, severely limiting tool usability.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb+resource structure: 'Turn your structured assessment into a stage-calibrated funding-readiness dashboard', listing dashboard components. It clearly distinguishes from siblings by focusing on scoring after assessment, while siblings 'deck_blueprint' and 'prepare_assessment' are about other phases.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this tool should be used after 'prepare_assessment' by referencing that output, but it does not explicitly state when to use it versus alternatives or provide exclusion criteria. The context is clear but lacks explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1deck_blueprintprepare_assessmentscore_funding_readinessScored across 3 tools
Each tool has a distinct and clear purpose: deck_blueprint for creating a slide structure, prepare_assessment for reading materials and generating an assessment rubric, and score_funding_readiness for producing a readiness dashboard. There is no overlap or ambiguity among them.
The naming uses snake_case but mixes patterns: deck_blueprint is noun_noun, while prepare_assessment and score_funding_readiness are verb_noun. This inconsistency makes the set slightly less predictable, though still readable.
Three tools is a small but appropriate number for a focused funding readiness server. They cover a sequential workflow (blueprint → prepare → score). It is slightly minimal but not under-scoped for the stated purpose.
The tools cover the assessment and scoring stages but lack a tool for actual deck building or iteration (the blueprint tool instructs the agent to build the deck externally). There are notable gaps in the lifecycle, such as updating materials or handling follow-up actions.
MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.
Marketplace MCP server for live venture-capital raises and agent-mediated dealflow.
Evidence-readiness MCP server: validate, audit, and score briefs, memos, and evidence packs.
MCP server for generating rough-draft project plans from natural-language prompts.
