Skip to main content
Glama
automatikstudio

PitchDeck MCP Server

by automatikstudio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

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 build

Usage

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

company_name

string

The name of the company or startup

problem

string

The problem or pain point the company solves

solution

string

The solution or product the company offers

market_size

string

Target market and size (e.g., "$10B healthcare market")

business_model

string

How the company makes money

Optional Inputs:

Parameter

Type

Description

industry

string

Industry vertical (auto-detected if not provided)

competition

string

Key competitors and landscape

funding_amount

string

Amount being raised (e.g., "$2M seed round")

use_of_funds

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 name

  • slides: Array of slide objects with title, content, and type

  • generatedAt: ISO timestamp

Development

# Install dependencies
npm install

# Run in development mode
npm run dev

# Run tests
npm test

# Build for production
npm run build

Testing

npm test

Tests cover:

  • Required field generation

  • Optional field handling (competition, funding)

  • Slide content validation

  • Edge cases (company names with spaces)

License

MIT

Available Tools

1 tool
generate_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.

ParametersJSON Schema
NameRequiredDescriptionDefault
company_nameYesThe name of the company or startup
problemYesThe problem or pain point the company solves
solutionYesThe solution or product the company offers
market_sizeYesThe target market and its size (e.g., '$10B healthcare market')
business_modelYesHow the company makes money (e.g., 'SaaS subscription', 'marketplace fees')
industryNoThe industry vertical (optional, defaults to extracting from market_size)
competitionNoKey competitors and competitive landscape (optional)
funding_amountNoAmount of funding being raised (optional, e.g., '$2M seed round')
use_of_fundsNoHow the funding will be used (optional)

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions the tool 'returns a complete slide deck' but lacks critical behavioral details: whether this is a generative AI operation (implied by 'AI-powered'), potential rate limits, quality expectations, format of the return (e.g., PDF, presentation file), or any authentication requirements. The description is insufficient for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately concise with two sentences that efficiently convey the core functionality and output. It's front-loaded with the main action and avoids unnecessary details. Every sentence earns its place, though minor improvements in structure are possible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (generative output with 9 parameters), lack of annotations, and no output schema, the description is incomplete. It doesn't explain the return format, quality, limitations, or how parameters map to the output. For a tool with no structured behavioral data, this leaves significant gaps for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all 9 parameters. The description adds no parameter-specific information beyond implying the inputs feed into the slide deck generation. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('generate', 'returns') and resources ('professional AI-powered pitch deck', 'complete slide deck'). It distinguishes what it produces (a full deck with specific slide types) without restating the tool name. No sibling tools exist, so differentiation isn't needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or constraints. It simply states what the tool does without context about appropriate scenarios or limitations. No sibling tools exist, but general usage context is missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedgenerate_pitch_deck
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.2/5.0

Scored across 1 tool

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count2/5

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.

Completeness2/5

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.

Resources

Related MCP Connectors