A powerful RAG (Retrieval-Augmented Generation) system built with LangChain, designed as an MCP server for Cursor, VS Code, and other AI assistants
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add pinrag --env OPENROUTER_API_KEY='<OPENROUTER_API_KEY>' -- uvx pinrag~/.codex/config.toml
[mcp_servers.pinrag]
command = "uvx"
args = ["pinrag"]
env = { OPENROUTER_API_KEY = "<OPENROUTER_API_KEY>" }
# codex mcp add pinrag --env OPENROUTER_API_KEY='<OPENROUTER_API_KEY>' -- uvx pinrag~/.cursor/mcp.json
{
"mcpServers": {
"pinrag": {
"command": "uvx",
"args": [
"pinrag"
],
"env": {
"OPENROUTER_API_KEY": "<OPENROUTER_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"pinrag": {
"type": "stdio",
"command": "uvx",
"args": [
"pinrag"
],
"env": {
"OPENROUTER_API_KEY": "<OPENROUTER_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"pinrag": {
"command": "uvx",
"args": [
"pinrag"
],
"env": {
"OPENROUTER_API_KEY": "<OPENROUTER_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"pinrag": {
"command": "uvx",
"args": [
"pinrag"
],
"env": {
"OPENROUTER_API_KEY": "<OPENROUTER_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"pinrag": {
"command": "uvx",
"args": [
"pinrag"
],
"env": {
"OPENROUTER_API_KEY": "<OPENROUTER_API_KEY>"
}
}
}
}Environment variables
OPENROUTER_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.