This MCP (Model Context Protocol) server integrates with Epsilla, providing a standardized interface for managing vector storage in AI applications. It enables seamless interaction with Epsilla databases through simple API calls, supporting operations like table management and data manipulation.
Clone the repository:
git clone https://github.com/yourusername/mcp-epsilla.git
cd mcp-epsilla
Install dependencies:
pip install -r requirements.txt
Set up environment variables (optional):
export EPSILLA_HOST=localhost
export EPSILLA_PORT=8888
Run the MCP server:
python main.py
By default, the server runs on port 8000. You can specify a different port:
python main.py --port 8080
curl -X POST http://localhost:8000/table/create \
-H "Content-Type: application/json" \
-d '{
"table_name": "my_vectors",
"dimension": 1536,
"metric": "cosine"
}'
curl -X GET http://localhost:8000/table/list
curl -X DELETE http://localhost:8000/table/delete \
-H "Content-Type: application/json" \
-d '{
"table_name": "my_vectors"
}'
curl -X POST http://localhost:8000/data/insert \
-H "Content-Type: application/json" \
-d '{
"table_name": "my_vectors",
"documents": [
{
"id": "doc1",
"vector": [0.1, 0.2, 0.3, ...],
"metadata": {"source": "example"}
}
]
}'
curl -X POST http://localhost:8000/data/query \
-H "Content-Type: application/json" \
-d '{
"table_name": "my_vectors",
"query_vector": [0.1, 0.2, 0.3, ...],
"top_k": 5
}'
curl -X POST http://localhost:8000/data/get \
-H "Content-Type: application/json" \
-d '{
"table_name": "my_vectors",
"ids": ["doc1", "doc2"]
}'
curl -X POST http://localhost:8000/data/delete \
-H "Content-Type: application/json" \
-d '{
"table_name": "my_vectors",
"ids": ["doc1"]
}'
You can configure the server by setting environment variables:
EPSILLA_HOST
: Hostname of the Epsilla server (default: localhost)EPSILLA_PORT
: Port of the Epsilla server (default: 8888)MCP_PORT
: Port for the MCP server (default: 8000)When querying data, you can use additional parameters:
curl -X POST http://localhost:8000/data/query \
-H "Content-Type: application/json" \
-d '{
"table_name": "my_vectors",
"query_vector": [0.1, 0.2, 0.3, ...],
"top_k": 5,
"filter": {"source": "example"},
"include_metadata": true,
"include_vectors": false
}'
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "epsilla" '{"command":"npx","args":["-y","mcp-epsilla"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"epsilla": {
"command": "npx",
"args": [
"-y",
"mcp-epsilla"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"epsilla": {
"command": "npx",
"args": [
"-y",
"mcp-epsilla"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect