fastmcp
🚀 The fast, Pythonic way to build MCP servers and clients.
MCP server by PerryLink · ★ 109 · updated 4 days ago
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
Choose your AI client and copy the config.
Add to claude_desktop_config.json — macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Then restart Claude. Setup guide
{
"mcpServers": {
"jevcore": {
"command": "npx",
"args": [
"-y",
"jevcore-mcp"
]
}
}
}Or add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project). Setup guide
{
"mcpServers": {
"jevcore": {
"command": "npx",
"args": [
"-y",
"jevcore-mcp"
]
}
}
}Or add to .vscode/mcp.json in your workspace. Setup guide
{
"servers": {
"jevcore": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"jevcore-mcp"
]
}
}
}Cascade → Actions → Open MCP config file (often ~/.config/devin/mcp_config.json). Setup guide
{
"mcpServers": {
"jevcore": {
"command": "npx",
"args": [
"-y",
"jevcore-mcp"
]
}
}
}Run in your terminal: Setup guide
claude mcp add jevcore -- npx -y jevcore-mcpCLI or add to ~/.codex/config.toml. Setup guide
codex mcp add jevcore -- npx -y jevcore-mcp[mcp_servers.jevcore]
command = "npx"
args = ["-y", "jevcore-mcp"]Cline panel → Configure MCP Servers, or ~/.cline/data/settings/cline_mcp_settings.json. Setup guide
{
"mcpServers": {
"jevcore": {
"command": "npx",
"args": [
"-y",
"jevcore-mcp"
]
}
}
}Run the server directly:
npx -y jevcore-mcp"env") in the config.🚀 The fast, Pythonic way to build MCP servers and clients.
The official Python SDK for Model Context Protocol servers and clients
The official TypeScript SDK for Model Context Protocol servers and clients
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
Visual testing tool for MCP servers
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.