promptflow-mcp
A Model Context Protocol server for prompt template management, enabling storage, versioning, search, and rendering of prompt templates via MCP tools.
README
<p align="center"> <img src="assets/logo.svg" width="120" alt="promptflow-mcp logo" /> </p>
<h1 align="center">promptflow-mcp</h1>
<p align="center"> <b>A Model Context Protocol server for prompt template management.</b><br /> Store, version, search and render prompts ā for AI agents and CLI users alike. </p>
<p align="center"> <a href="https://www.npmjs.com/package/@modelcontextprotocol/sdk"><img alt="MCP SDK" src="https://img.shields.io/badge/MCP-SDK-blue" /></a> <a href="https://www.typescriptlang.org/"><img alt="TypeScript" src="https://img.shields.io/badge/TypeScript-5.4-3178c6" /></a> <a href="./LICENSE"><img alt="License" src="https://img.shields.io/badge/License-MIT-green" /></a> <img alt="Node >= 18" src="https://img.shields.io/badge/Node-%3E%3D18-339933" /> <img alt="Version" src="https://img.shields.io/badge/version-0.2.1-orange" /> </p>
⨠Features
- š Template registry ā save prompts with variables (
{{input}}) - š Versioning ā every edit creates a new version; nothing is lost
- š Search ā full-text search across name, body and tags
- š§© Rendering ā interpolate
{{variables}}at call time - š¾ Local-first ā plain JSON on disk; back up or sync with git
- š MCP native ā works with any MCP client (Claude, Cursor, etc.)
<p align="center"> <img src="assets/demo.gif" alt="demo" width="640" /> </p>
š Quick start
# clone, install, build
git clone https://github.com/DuxuteLi70/promptflow-mcp.git
cd promptflow-mcp
npm install
npm run build
# run the tests
npm test
# start the MCP server
node dist/index.js
š MCP tools
| Tool | Description |
|---|---|
prompt.save |
Save or update a prompt template |
prompt.list |
List all templates (title, version, tags) |
prompt.get |
Get a template, rendered with variables |
prompt.search |
Full-text search |
prompt.delete |
Remove a template |
prompt.versions |
Show version history of a template |
š” Example
import { TemplateRegistry } from "./src/storage/store.js";
const reg = new TemplateRegistry();
// save a template
const id = reg.save("code-review", "Review this diff:\n{{diff}}", ["review"]);
// render it with variables
const rendered = reg.render(id, { diff: "..." });
// every save keeps history
reg.update(id, "Review this carefully:\n{{diff}}");
reg.versions(id); // [{version: 1, ...}, {version: 2, ...}]
š¦ Project layout
promptflow-mcp/
āāā src/
ā āāā index.ts # entry point
ā āāā server.ts # MCP server wiring
ā āāā tools/ # MCP tool definitions
ā āāā storage/ # JSON-file template store
āāā tests/ # unit tests (node:test)
āāā docs/ # design & usage docs
āāā examples/ # MCP client config examples
āāā assets/ # logo + demo media
š¤ Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
š License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.