Local MCP server for package metadata
See the codeMCP server for querying package ecosystem data from ecosyste.ms.
Queries a local SQLite database of critical packages for fast lookups, with API fallback for packages not in the database.
npm install -g @ecosyste-ms/mcp
Or run directly with npx:
npx @ecosyste-ms/mcp
The database is bundled via @ecosyste-ms/critical. No additional setup required.
To use a custom database, set ECOSYSTEMS_DB_PATH or place critical-packages.db in your working directory.
ECOSYSTEMS_DB_PATH is authoritative when set: the server uses exactly that file, or runs API-only if it is missing. Set it to none to skip the local database entirely.
Open a terminal and run:
claude mcp add ecosystems -- npx @ecosyste-ms/mcp
With a custom database path:
claude mcp add ecosystems -- env ECOSYSTEMS_DB_PATH=/path/to/db.sqlite npx @ecosyste-ms/mcp
From within Claude Code, use the /mcp command to verify the server is running.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
With custom database path:
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"],
"env": {
"ECOSYSTEMS_DB_PATH": "/path/to/critical-packages.db"
}
}
}
}
Add to .cursor/mcp.json in your project or ~/.cursor/mcp.json globally:
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
Open a terminal and run:
code --add-mcp '{"type":"stdio","name":"ecosystems","command":"npx","args":["@ecosyste-ms/mcp"]}'
Or manually add to .vscode/mcp.json:
{
"servers": {
"ecosystems": {
"type": "stdio",
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
Then open the .vscode/mcp.json file in VS Code and click "Start server".
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
Add to Zed settings (cmd+,):
{
"context_servers": {
"ecosystems": {
"command": {
"path": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
}
Note: ChatGPT requires remote MCP servers. Run the server with a tunnel or deploy it.
For local development with a tunnel:
npx @anthropic-ai/mcp-proxy --port 8080 -- npx @ecosyste-ms/mcp
Then in ChatGPT:
Add to ~/.codex/config.toml:
[mcp_servers.ecosystems]
command = "npx"
args = ["@ecosyste-ms/mcp"]
Add to ~/.gemini/settings.json:
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
Ask your LLM:
npm, pypi, rubygems, cargo, go, maven, nuget, packagist, hex, pub, hackage, cocoapods, conda, clojars, puppet, homebrew, docker, bower, cpan, cran, julia, swiftpm, elm, deno, alpine, actions, openvsx, spack, adelie, vcpkg, racket, bioconductor, carthage, postmarketos, elpa
git clone https://github.com/ecosyste-ms/mcp
cd mcp
npm install
npm test
Run locally:
node index.js
MIT
Local MCP server for package metadata
See the codeMCP server for querying package ecosystem data from ecosyste.ms.
Queries a local SQLite database of critical packages for fast lookups, with API fallback for packages not in the database.
npm install -g @ecosyste-ms/mcp
Or run directly with npx:
npx @ecosyste-ms/mcp
The database is bundled via @ecosyste-ms/critical. No additional setup required.
To use a custom database, set ECOSYSTEMS_DB_PATH or place critical-packages.db in your working directory.
ECOSYSTEMS_DB_PATH is authoritative when set: the server uses exactly that file, or runs API-only if it is missing. Set it to none to skip the local database entirely.
Open a terminal and run:
claude mcp add ecosystems -- npx @ecosyste-ms/mcp
With a custom database path:
claude mcp add ecosystems -- env ECOSYSTEMS_DB_PATH=/path/to/db.sqlite npx @ecosyste-ms/mcp
From within Claude Code, use the /mcp command to verify the server is running.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
With custom database path:
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"],
"env": {
"ECOSYSTEMS_DB_PATH": "/path/to/critical-packages.db"
}
}
}
}
Add to .cursor/mcp.json in your project or ~/.cursor/mcp.json globally:
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
Open a terminal and run:
code --add-mcp '{"type":"stdio","name":"ecosystems","command":"npx","args":["@ecosyste-ms/mcp"]}'
Or manually add to .vscode/mcp.json:
{
"servers": {
"ecosystems": {
"type": "stdio",
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
Then open the .vscode/mcp.json file in VS Code and click "Start server".
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
Add to Zed settings (cmd+,):
{
"context_servers": {
"ecosystems": {
"command": {
"path": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
}
Note: ChatGPT requires remote MCP servers. Run the server with a tunnel or deploy it.
For local development with a tunnel:
npx @anthropic-ai/mcp-proxy --port 8080 -- npx @ecosyste-ms/mcp
Then in ChatGPT:
Add to ~/.codex/config.toml:
[mcp_servers.ecosystems]
command = "npx"
args = ["@ecosyste-ms/mcp"]
Add to ~/.gemini/settings.json:
{
"mcpServers": {
"ecosystems": {
"command": "npx",
"args": ["@ecosyste-ms/mcp"]
}
}
}
Ask your LLM:
npm, pypi, rubygems, cargo, go, maven, nuget, packagist, hex, pub, hackage, cocoapods, conda, clojars, puppet, homebrew, docker, bower, cpan, cran, julia, swiftpm, elm, deno, alpine, actions, openvsx, spack, adelie, vcpkg, racket, bioconductor, carthage, postmarketos, elpa
git clone https://github.com/ecosyste-ms/mcp
cd mcp
npm install
npm test
Run locally:
node index.js
MIT
609 followers · starred Aug 2026