Skip to main content
Glama
agmonetti

plan-export-mcp

by agmonetti
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

plan-export-mcp

The visual export engine for coding agents. Turn Markdown plans and Mermaid diagrams into beautiful, shareable documents.

The Problem

When coding agents (Cursor, Claude Code, Pi, Windsurf, Aider) draft implementation plans or audit codebases, they generate rich Markdown with code diffs, Mermaid architecture diagrams, GitHub callouts, and task lists.

  • Inside your IDE: It looks crisp and structured.

  • When sharing: Sending raw .md on WhatsApp, Slack, or Email turns into an unreadable mess. Generic PDF converters output 1990s-style plain black-and-white academic papers, break Mermaid diagrams, and strip dark themes.

plan-export-mcp bridges this gap. It gives your AI agent a native MCP tool to export plans with pixel-perfect visual fidelity.

Related MCP server: Document Generator MCP

Key Features

  • High-Res PNG (Long Screenshot): Rendered at 2x Retina DPR. Ideal for WhatsApp and Slack because it renders inline in chat feeds without forcing teammates to download a PDF reader.

  • VS Code Code Highlighting: Powered by Shiki with language badges and diff support (+ / - lines).

  • GitHub Callouts & Alerts: Native support for > [!NOTE], > [!WARNING], > [!TIP], > [!IMPORTANT], and > [!CAUTION].

  • Mermaid Architecture Diagrams: Client-side vector rendering directly embedded as SVG.

  • Clean A4 PDF: Print-optimized with background colors and screen contrast preserved.

  • Self-Contained HTML: Embedded styles and local scripts with zero external dependencies.

  • Dual Mode: Use it as an MCP server for AI agents or as a standalone CLI tool.

Installation and Usage

Prerequisites

  • Node.js 18+

  • npm, pnpm, or yarn

(Note: HTML exports run in pure Node.js with zero browser dependencies. For PDF/PNG rendering, Puppeteer manages a lightweight headless browser automatically or uses system Chromium if present).

1. Run with NPX (Recommended)

Runs on-demand without any global installation.

Claude Code (One-liner CLI)

claude mcp add plan-export npx -y plan-export-mcp

Claude Desktop & Cursor (JSON Configuration)

Add to your claude_desktop_config.json or .cursor/mcp.json:

{
  "mcpServers": {
    "plan-export": {
      "command": "npx",
      "args": ["-y", "plan-export-mcp"]
    }
  }
}

Tip (Linux/Docker): If Puppeteer cannot locate Chrome automatically, specify its path explicitly:

"env": {
  "PUPPETEER_EXECUTABLE_PATH": "/usr/bin/google-chrome-stable"
}

2. Install Globally from NPM

Ideal for instant startup without network latency on every invocation:

npm install -g plan-export-mcp
{
  "mcpServers": {
    "plan-export": {
      "command": "plan-export-mcp"
    }
  }
}

3. Install from Source (Development)

Clone the repository and build locally:

git clone https://github.com/agmonetti/plan-export-mcp.git
cd plan-export-mcp
npm install
npm run build
{
  "mcpServers": {
    "plan-export": {
      "command": "node",
      "args": ["/path/to/plan-export-mcp/dist/index.js"]
    }
  }
}

Standalone CLI Usage

You can also run it directly in your terminal:

# Export to PNG and PDF in dark mode
npx plan-export-mcp docs/plan.md --theme dark

# Export to all formats in light mode
npx plan-export-mcp docs/plan.md --theme light --formats png,pdf,html --output-dir exports/

MCP Tool Reference: export_plan

Your AI agent can invoke this tool directly:

{
  "input": "docs/plans/feature-auth.md", // or raw markdown string
  "theme": "dark",                       // "dark" | "light" (default: "dark")
  "formats": ["png", "pdf"],             // ["png", "pdf", "html"]
  "outputDir": "./exports",              // default: "./exports"
  "outputName": "auth-plan"              // default: derived from file
}

Architecture

  • Runtime: Node.js (>= 18) + TypeScript

  • MCP SDK: @modelcontextprotocol/sdk (stdio transport)

  • Highlighter: Shiki (VS Code TextMate engine)

  • Diagrams: Mermaid.js

  • Headless Engine: Puppeteer with intelligent fallback to system Chrome/Chromium.

License

MIT © 2025

Available Tools

2 tools
export_planA

Export an AI agent implementation plan or audit (Markdown) to styled PDF, high-res PNG, or self-contained HTML matching IDE aesthetics.

ParametersJSON Schema
NameRequiredDescriptionDefault
inputYesPath to the markdown file (relative or absolute) OR raw markdown text content
themeNoVisual theme: "light" (GitHub Light) or "dark" (GitHub Dark). Default: "light"
formatsNoList of export formats. Default: ["png", "pdf"]
outputDirNoDirectory where exported files will be saved. Default: "./exports"
outputNameNoBase filename for exports without extension. Default: derived from input file or "plan"

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the disclosure burden. It conveys the core behavior—converting Markdown to styled PDF/PNG/HTML—but does not mention that files will be written to an output directory, possible overwrite behavior, or that outputName/outputDir defaults apply.

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

Conciseness5/5

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

The description is a single, information-dense sentence with no filler. It front-loads the input type and then enumerates output formats and styling, so every clause earns its place.

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

Completeness3/5

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

The tool is simple and the schema covers all parameters, but with no annotations and no output schema the description still leaves gaps: no mention of file-system side effects, no guidance on default output naming, and no cue about when render_diagram would be the better choice.

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 input schema already explains all five parameters including defaults. The description adds only context about styling ('matching IDE aesthetics'), not new parameter-level meaning, keeping this at the baseline.

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

Purpose4/5

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

The description names a specific verb ('Export'), resource ('AI agent implementation plan or audit (Markdown)'), and target formats (PDF, PNG, HTML), so an agent knows what the tool produces. It does not explicitly contrast with render_diagram, but the Markdown-plan/audit focus is enough to avoid confusion for a typical call.

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

Usage Guidelines4/5

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

The description gives clear context for when to use the tool: whenever an implementation plan or audit in Markdown needs to be exported to a styled document format. It does not state exclusions or explicitly name the sibling as an alternative, which prevents a 5.

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

render_diagramA

Render an isolated Mermaid diagram (sequence, flowchart, class, architecture, ER) directly to a cropped PNG or SVG file with optional visual preview in chat.

ParametersJSON Schema
NameRequiredDescriptionDefault
themeNoVisual theme: "light" (GitHub Light) or "dark" (GitHub Dark). Default: "light"
formatNoOutput format: "png" (high-res auto-cropped image) or "svg" (vector XML). Default: "png"
diagramYesRaw Mermaid diagram definition code (e.g. "graph TD\nA-->B" or "sequenceDiagram...")
outputDirNoDirectory where exported diagram file will be saved. Default: "./exports"
outputNameNoBase filename for the diagram without extension. Default: "diagram-<timestamp>"
includeBase64NoWhether to include base64 image data in MCP response for direct visual rendering in chat. Default: true

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations provided, the description carries the behavioral disclosure burden. It reveals that the tool writes an isolated file, crops the output, and can include a base64 visual preview in chat. It could mention overwrite behavior or whether rendering requires external services, but 'isolated' plus direct-to-file and preview details give a useful safety picture.

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

Conciseness5/5

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

A single sentence front-loads the action and resource, then efficiently enumerates diagram types, output format, file target, and chat preview. There is no filler or redundant restatement of the tool name.

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

Completeness4/5

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

For a six-parameter tool without an output schema, the description covers the essential workflow: Mermaid input, cropped PNG/SVG file output, and optional visual preview. The schema handles defaults and enums; the description could be more explicit about exactly what the tool returns to the caller, but an agent has enough to invoke it correctly.

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 baseline is 3 and the description is not required to document every parameter. It adds the supported Mermaid diagram types, which the schema does not list, but otherwise mostly paraphrases the format and includeBase64 parameters rather than adding substantial new parameter-level meaning.

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 names a specific verb and resource: render a Mermaid diagram, enumerates supported diagram types, and specifies the output format (cropped PNG/SVG) plus optional chat preview. This clearly distinguishes it from the sibling export_plan, which concerns plans rather than rendering diagram definitions into image files.

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

Usage Guidelines4/5

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

The description gives clear context for when to use the tool: converting Mermaid definitions into standalone cropped image files or providing an in-chat visual preview. It does not explicitly state when not to use it or name the sibling as an alternative, but the supported diagram types and output modes make the intended scope clear.

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. Dates show when Glama detected each change.

  1. 2 tool updatesv0.1.0
    • First observedexport_plan
    • First observedrender_diagram
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation4/5

The two tools target different output types and inputs: one exports whole Markdown plans/audits, the other renders isolated Mermaid diagrams. There is mild potential for confusion when a plan includes diagrams, but the descriptions make the boundary clear.

Naming Consistency5/5

Both tools follow the same verb_noun pattern: export_plan and render_diagram. The naming is parallel, predictable, and accurately reflects each tool's function.

Tool Count3/5

With only two tools, the server feels thin but is still reasonably scoped for a narrow plan-export and diagram-rendering purpose. It is not bloated, yet it sits at the lower boundary of acceptable tool count.

Completeness4/5

The core workflows are covered: exporting plans to common document formats and rendering diagrams to image formats. Minor gaps exist, such as batch processing or combining plan text and diagrams into a single export, but agents can accomplish the primary tasks without dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/agmonetti/plan-export-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server