mcp-prompt-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., "@mcp-prompt-server list available prompts"
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.
π MCP Prompt Server
A lightweight Model Context Protocol server for dynamic prompt management
β¨ Features
π Dynamic Prompt Loading β Automatically discover and register markdown files from the
prompts/directoryπ Resource Management β Serve documentation and reference materials via MCP resources
β‘ Zero Configuration β Add prompts and resources by simply creating markdown files with YAML frontmatter
π Security First β Built-in path traversal protection, file size limits, and input validation
π― MCP Compliant β Full implementation of MCP prompt and resource primitives via FastMCP framework
π Remote Installation β Run directly from GitHub without cloning
Related MCP server: Amazon Q Custom Prompt MCP Server
π§ Requirements
Python >=3.11
Package manager:
uv(installs automatically withuvx)
Quick Start
Using with Claude Cli
Add this configuration to your Claude Cli MCP settings:
{
"mcpServers": {
"prompt-server": {
"type": "stdio",
"command": "uvx",
"args": [
"--from",
"git+https://github.com/marcmodin/mcp-prompt-server@v0.1.0",
"mcp-prompt-server"
]
}
}
}Using with GitHub Copilot
Create .vscode/mcp.json in your project:
{
"mcpServers": {
"prompt-server": {
"type": "stdio",
"command": "uvx",
"args": [
"--from",
"git+https://github.com/marcmodin/mcp-prompt-server@v0.1.0r",
"mcp-prompt-server"
]
}
}
}Running Remotely
# Run directly from GitHub
uvx --from git+https://github.com/marcmodin/mcp-prompt-server@v0.1.0 mcp-prompt-server
# Debug with MCP Inspector
npx @modelcontextprotocol/inspector uvx --from git+https://github.com/marcmodin/mcp-prompt-server@v0.1.0 mcp-prompt-serverπ Documentation
Architecture β System design and security model
Contributing β Development workflow and guidelines
Prompt Template β Creating prompt files
Available Tools
1 toolpingA
Simple ping tool that returns pong
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The single 'ping' tool is unambiguous.
Only one tool exists, so naming consistency is not an issue. The name 'ping' follows a common, clear convention.
A single 'ping' tool is far too minimal for a server named 'mcp-prompt-server'. The server does not fulfill its implied purpose of providing prompt-related functionality.
The server completely lacks any prompt-related tools. A single ping-pong tool leaves a vast gap in functionality for a server that should handle prompts.
Related MCP Connectors
Read-only catalog of prompt packs and rule files: Cursor, CLAUDE.md, AGENTS.md, SKILL.md.
Portable AI memory shared across models and harnesses - plain markdown you own.
Your prompt library in any MCP client: list, fetch, save and version prompt templates.
Research-backed lint + generation for agent context files (CLAUDE.md, AGENTS.md) + prompt enhancer.
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol server for managing prompt templates as markdown files with YAML frontmatter, allowing users and LLMs to easily add, retrieve, and manage prompts.522 npm17MIT
- AlicenseNot gradedqualityDmaintenanceProvides custom prompts for Amazon Q by serving markdown files from the local filesystem as prompt templates through the Model Context Protocol.8 npmMIT
- AlicenseNot gradedqualityFmaintenanceEnables loading and serving markdown files as prompts from local folders or GitHub repositories. Supports automatic repository synchronization and YAML frontmatter for prompt metadata.3MIT
- AlicenseAqualityBmaintenanceExposes local markdown documentation, notes, and knowledge bases to AI tools via the Model Context Protocol without embeddings or uploading.41MIT