PitchDeck MCP Server
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., "@PitchDeck MCP Server Make a pitch deck for ZenHire: high churn, AI recruiting, $5B market, monthly subscription."
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.
PitchDeck MCP Server
An MCP (Model Context Protocol) server that generates AI-powered pitch decks for startups and businesses.
Features
generate_pitch_deck - Creates a complete investor pitch deck with:
Title slide
Problem statement
Solution overview
Market opportunity
Business model
Competitive landscape (optional)
Traction & milestones
Team overview
Financial projections
Funding request (optional)
Closing slide
Installation
npm install
npm run buildUsage
As an MCP Server
Add to your MCP client configuration (e.g., Claude Desktop):
{
"mcpServers": {
"pitchdeck": {
"command": "node",
"args": ["/path/to/pitchdeck-mcp/dist/index.js"]
}
}
}Tool: generate_pitch_deck
Generate a complete pitch deck for your startup.
Required Inputs:
Parameter | Type | Description |
| string | The name of the company or startup |
| string | The problem or pain point the company solves |
| string | The solution or product the company offers |
| string | Target market and size (e.g., "$10B healthcare market") |
| string | How the company makes money |
Optional Inputs:
Parameter | Type | Description |
| string | Industry vertical (auto-detected if not provided) |
| string | Key competitors and landscape |
| string | Amount being raised (e.g., "$2M seed round") |
| string | Allocation of funding |
Example:
{
"company_name": "TechFlow",
"problem": "Small businesses waste 20+ hours per week on manual data entry",
"solution": "AI-powered automation platform with 99.9% accuracy",
"market_size": "$200B SMB administrative software market",
"business_model": "SaaS subscription: $99/month starter, $299/month pro",
"competition": "Legacy players like SAP are slow and expensive",
"funding_amount": "$3M Seed Round"
}Output:
Returns a JSON object with:
companyName: Company nameslides: Array of slide objects withtitle,content, andtypegeneratedAt: ISO timestamp
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Run tests
npm test
# Build for production
npm run buildTesting
npm testTests cover:
Required field generation
Optional field handling (competition, funding)
Slide content validation
Edge cases (company names with spaces)
License
MIT
Available Tools
1 toolgenerate_pitch_deckB
Generate a professional AI-powered pitch deck for a startup or business. Returns a complete slide deck with title, problem, solution, market, business model, traction, team, financials, and closing slides.
Inputs: company_name (required), problem (required), solution (required), market_size (required), +5 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools, as there are no other tools to confuse it with. The tool's purpose is clearly defined and distinct by default.
The single tool name 'generate_pitch_deck' follows a clear verb_noun pattern, and with no other tools, consistency is inherently perfect. There are no deviations or mixed conventions to evaluate.
A single tool is too few for a server named 'PitchDeck MCP Server', which suggests a broader domain like pitch deck creation and management. This minimal toolset feels thin and limits functionality, as it only covers generation without supporting operations like editing, listing, or deleting pitch decks.
The tool surface is severely incomplete for the implied domain of pitch deck management. While generation is covered, there are significant gaps such as updating existing decks, retrieving or listing decks, deleting decks, or handling slide-level operations, which will likely cause agent failures in broader workflows.
Related MCP Connectors
MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.
MCP server for generating rough-draft project plans from natural-language prompts.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.