EntityIdentification
MCP (Model Context Protocol) server for identifying whether two sets of data are from the same entity. 识别两组数据是否来自同一主体的MCP服务器
Overview
EntityIdentification is a Model Context Protocol (MCP) server designed to determine whether two sets of data originate from the same entity.
To use EntityIdentification, install the necessary dependencies using pip and utilize the provided functions to compare data sets.
- Text Normalization: Standardizes text by converting it to lowercase, removing punctuation, and normalizing whitespace. - Value Comparison: Compares values both exactly and semantically, ignoring order for lists. - JSON Traversal: Iterates through JSON objects to compare corresponding values. - Language Model Integration: Uses a generative language model to assess semantic similarity and provide a final judgment.
- Identifying duplicate records in databases.
- Merging datasets from different sources.
- Validating data integrity in data pipelines.
Add to your AI client
Use these steps to connect EntityIdentification in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.
Cursor
Add this to your .cursor/mcp.json file in your project root, then restart Cursor.
.cursor/mcp.json
{
"mcpServers": {
"entityidentification-u3588064": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-entityidentification-u3588064"
]
}
}
}Claude Desktop
Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"entityidentification-u3588064": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-entityidentification-u3588064"
]
}
}
}Claude Code
Add this to your project's .mcp.json file. Claude Code will detect it automatically.
.mcp.json (project root)
{
"mcpServers": {
"entityidentification-u3588064": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-entityidentification-u3588064"
]
}
}
}VS Code (Copilot)
Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.
.vscode/mcp.json
{
"servers": {
"entityidentification-u3588064": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-entityidentification-u3588064"
]
}
}
}Windsurf
Add this to your Windsurf MCP config file, then restart Windsurf.
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"entityidentification-u3588064": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-entityidentification-u3588064"
]
}
}
}Cline
Open Cline settings, navigate to MCP Servers, and add this server configuration.
Cline MCP Settings (via UI)
{
"mcpServers": {
"entityidentification-u3588064": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-entityidentification-u3588064"
]
}
}
}FAQ
Can EntityIdentification handle large datasets?
Yes! It is designed to efficiently compare large sets of data.
Is EntityIdentification free to use?
Yes! The project is open-source and free to use.
How accurate is the comparison?
The accuracy depends on the quality of the input data and the effectiveness of the normalization process.