MCP server for Tool Pantry — 216 free browser tools for PDF, images, video and text that process files locally
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add toolpantry-mcp -- npx -y toolpantry-mcp{
"mcpServers": {
"toolpantry-mcp": {
"command": "npx",
"args": ["-y", "toolpantry-mcp"]
}
}
}MCP Servers overview
# Tool Pantry MCP Server
An [MCP](https://modelcontextprotocol.io) server for **[Tool Pantry](https://toolpantry.app)** — 216 free browser tools for PDF, images, video, audio and text that process files **entirely in the user's browser**. Nothing is uploaded, there is no account, no watermark and no file-size limit.
The server has two jobs:
1. **`search_tools`** — find the exact tool page for a request ("compress image to 100kb", "merge pdf", "heic to jpg") so an agent can hand over a working link instead of generic advice.
2. **Small stateless helpers** — text stats, hashing, UUIDs, passwords, JSON formatting, Base64, colour conversion and QR codes, all served by the same public API.
Zero dependencies, ~200 lines, runs on any Node 18+.
## Listed in the official MCP registry
```
io.github.wu736139669/toolpantry-mcp
```
```bash
curl "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.wu736139669/toolpantry-mcp"
```
## Use it over HTTP
The same server runs on Cloudflare Workers at **`https://mcp.toolpantry.app/mcp`** (streamable HTTP, stateless):
```bash
curl -X POST https://mcp.toolpantry.app/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
```
`https://mcp.toolpantry.app/` returns a small health/capability JSON.
## Install
```bash
# Claude Desktop / Claude Code (stdio)
npx -y toolpantry-mcp
```
```json
{
"mcpServers": {
"toolpantry": {
"command": "npx",
"args": ["-y", "toolpantry-mcp"]
}
}
}
```
Run from a checkout:
```bash
git clone https://github.com/wu736139669/toolpantry-mcp.git
node toolpantry-mcp/mcp-server.mjs
```
## Tools
| Tool | What it does |
| --- | --- |
| `search_tools` | Search the 216-tool catalog; returns the tool name, URL and description |
| `text_stats` | Characters, words, sentences, paragraphs, lines, reading time |
| `hash_text` | SHA-1 / SHA-256 / SHA-384 / SHA-512 digests (hex + base64) |
| `generate_uuid` | Random UUID v4 values |
| `generate_password` | Random passwords from the platform crypto RNG |
| `json_format` | Validate, pretty-print or minify JSON |
| `base64` | Encode or decode UTF-8 text |
| `color_convert` | Hex colour to RGB and HSL |
| `qr_code` | QR code as SVG for any text or URL |
## Install
Every tool is a thin wrapper over the public, key-free API at `https://toolpantry.app/api` — the same endpoints are documented in the [API reference](https://toolpantry.app/api). Point the server somewhere else with `TOOLPANTRY_API=https://toolpantry.app/api`.
## Why a tool directory needs an MCP server
Most "AI tool" directories are chat boxes. A file task is not a chat task: the agent should not ask the user to upload a passport scan to a stranger's server. Tool Pantry's whole premise is that the work happens in the user's own tab, so the agent's job is only to pick the right URL and hand it over.
## Related
- [toolpantry.app](https://toolpantry.app) — the site (also available as [llms.txt](https://toolpantry.app/llms.txt) and a [tools.json](https://toolpantry.app/tools.json) catalog)
- [markdown-for-agents-worker](https://github.com/wu736139669/markdown-for-agents-worker) — serve Markdown to agents from any static site
- [toolpantry-skill](https://github.com/wu736139669/toolpantry-skill) — the same routing knowledge as an installable Agent Skill
- [press kit](https://toolpantry.app/press) — boilerplate copy, logos and screenshots
## License
MIT
What people ask about toolpantry-mcp
What is wu736139669/toolpantry-mcp?
+
wu736139669/toolpantry-mcp is mcp servers for the Claude AI ecosystem. MCP server for Tool Pantry — 216 free browser tools for PDF, images, video and text that process files locally It has 0 GitHub stars and its last recorded update is dated 2026-10-19.
How do I install toolpantry-mcp?
+
You can install toolpantry-mcp by cloning the repository (https://github.com/wu736139669/toolpantry-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is wu736139669/toolpantry-mcp safe to use?
+
Our security agent has analyzed wu736139669/toolpantry-mcp and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains wu736139669/toolpantry-mcp?
+
wu736139669/toolpantry-mcp is maintained by wu736139669. The last recorded GitHub activity is dated 2026-10-19, with 0 open issues.
Are there alternatives to toolpantry-mcp?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy toolpantry-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/wu736139669-toolpantry-mcp)<a href="https://claudewave.com/repo/wu736139669-toolpantry-mcp"><img src="https://claudewave.com/api/badge/wu736139669-toolpantry-mcp" alt="Featured on ClaudeWave: wu736139669/toolpantry-mcp" width="320" height="64" /></a>More MCP Servers
Reverse engineer anything with agents, from app behavior down to native binaries.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ A Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev