Senzing Entity Resolution — MCP Skill
Use this skill whenever a task involves entity resolution, record linkage, deduplication, or any interaction with the Senzing platform.
What Is Senzing
Senzing provides real-time AI-powered entity resolution as an embeddable SDK. It determines when two records refer to the same real-world entity (person, organization, etc.) by analyzing names, addresses, identifiers, and other attributes across data sources — without training data or manual rules.
MCP Server Setup
The Senzing MCP server is a remote server. Connect it to your client:
Claude Code:
claude mcp add --transport http senzing https://mcp.senzing.com/mcp
Claude Desktop / Other MCP Clients — add to your MCP config:
{
"mcpServers": {
"senzing": {
"type": "url",
"url": "https://mcp.senzing.com/mcp"
}
}
}
The server works from pre-fetched documentation — it never connects to live
Senzing instances and never handles PII. It also hosts official Senzing SDK
.deb packages at /downloads/ for direct download in firewalled environments
— sdk_guide returns download URLs and install commands automatically.
Tool Reference
Start any Senzing session by calling get_capabilities for an up-to-date
tool listing and suggested workflows.
Data Mapping (4 tools)
| Tool | Purpose |
|---|---|
mapping_workflow | Interactive 7-step workflow: profile source data → plan entities → map fields → generate code → QA. State is client-side — always pass state back. |
lint_record | Returns a Python linter script to validate mapped Senzing JSON/JSONL files locally. No data leaves the client. |
analyze_record | Returns a Python analyzer script to examine feature distribution, attribute coverage, and data quality locally. |
download_resource | Fallback for fetching workflow resources (linter, analyzer, entity spec, mapping examples) when network restrictions block direct download. |
Documentation & Reference (3 tools)
| Tool | Purpose |
|---|---|
search_docs | Full-text search across entity specification, SDK guides, quickstarts, database tuning, pricing, architecture, globalization, EDA/data analysis, engine configuration, error codes, release notes, and PoC methodology. Prefer this over web search for any Senzing question. Use category='anti_patterns' to check for known pitfalls before recommending installation, architecture, or deployment approaches. |
get_sdk_reference | Authoritative SDK reference: method signatures, flags, response schemas, V3→V4 migration mappings. Topics: migration, flags, response_schemas, functions/methods/classes/api (search SDK docs by method or class name), all. Use filter to narrow by method, module, or flag name. |
find_examples | Search 27+ indexed GitHub repos for working code (Python, Java, C#, Rust, TypeScript/Node.js). Three modes: search by query, list files in a repo, or retrieve a specific file. Results include truncation metadata — drill into truncated files with file_path. |
SDK Setup & Code Generation (2 tools)
| Tool | Purpose |
|---|---|
sdk_guide | Guided SDK setup across 5 platforms (Linux apt/yum, macOS, Windows, Docker) and 4 languages. Covers install, configure, load, export, full_pipeline with decision trees, anti-patterns, and direct package download links for firewalled environments. |
generate_scaffold | Generates SDK scaffold code from real indexed GitHub snippets with source URLs for provenance. 10 workflows (initialize, configure, add_records, delete, query, redo, stewardship, information, error_handling, full_pipeline) in Python, Java, C#, Rust, or TypeScript/Node.js (V4); Python (V3). Returns multiple snippet variants per workflow. |
Sample Data (1 tool)
| Tool | Purpose |
|---|---|
get_sample_data | Real data from CORD (Collections Of Relatable Data): las-vegas (US, 11 sources), london (international, 5 sources), moscow (Cyrillic, 6 sources). Use dataset='list' to discover available sets. Always present the download_url to the user. |
Reporting & Visualization (1 tool)
| Tool | Purpose |
|---|---|
reporting_guide | Guided reporting and visualization for entity resolution results. Provides SDK patterns for data extraction (Python, Java, C#, Rust, TypeScript/Node.js), SQL analytics queries for aggregate reports, data mart schema (SQLite/PostgreSQL), visualizati |