Serve ExpertPack knowledge packs over MCP with hybrid search, graph traversal and provenance.
Connect Runs on your machine
claude mcp add ep-mcp -e GEMINI_API_KEY=<GEMINI_API_KEY> -e AZURE_OPENAI_API_KEY=<AZURE_OPENAI_API_KEY> -- uvx ep-mcp==0.7.0
{
"mcpServers": {
"ep-mcp": {
"command": "uvx",
"args": [
"ep-mcp==0.7.0"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"AZURE_OPENAI_API_KEY": "<AZURE_OPENAI_API_KEY>"
}
}
}
}
{
"mcpServers": {
"ep-mcp": {
"command": "uvx",
"args": [
"ep-mcp==0.7.0"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"AZURE_OPENAI_API_KEY": "<AZURE_OPENAI_API_KEY>"
}
}
}
}
{
"servers": {
"ep-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"ep-mcp==0.7.0"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"AZURE_OPENAI_API_KEY": "<AZURE_OPENAI_API_KEY>"
}
}
}
}
Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
GEMINI_API_KEYOptional, secret | Gemini API key for embeddings (or set AZURE_OPENAI_API_KEY when using Azure OpenAI) |
AZURE_OPENAI_API_KEYOptional, secret | Azure OpenAI key, if the config uses the Azure embedding provider |
Details
| Package | [email protected] (PYPI, stdio) |
| First published | 20 Oct 2026 |
| Last updated | 20 Oct 2026 |
| Registry name | io.github.brianhearn/ep-mcp |
More search and web servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
