GoldenMatch MCP Server

Find duplicate records in 30 seconds. Zero-config entity resolution, 97.2% F1 out of the box.

Local serverstdioPython

What is the GoldenMatch MCP server?

Most database access work still happens through a UI a human drives. GoldenMatch MCP server moves it into the conversation instead. Find duplicate records in 30 seconds. Zero-config entity resolution, 97.2% F1 out of the box.

The short version

Zero-config matching that beats expert-tuned Splink head-to-head on messy customer records, in an Arrow-native, Rust-authoritative engine verified from a laptop CSV to a 100M-row dedupe in 9.2 minutes. The identities it produces live in a transaction-native control plane — stable entity_ids, per-field provenance, merge/split, and a tamper-evident audit log — one call away as a Customer 360. It even owns its primitives: byte-identical, faster-than-rapidfuzz / jellyfish / FAISS Rust kernels, not rented dependencies.

The tools it exposes

The server publishes 13 tools. What each one is for:

  • Whole — record provenance.** Every field of the golden record traces back to the source record that won it — which source, when it was last seen, and which
  • Privacy — preserving record linkage.** Match across organizations without sharing raw data — Bloom-filter PPRL, 92.4% F1 on FEBRL4, with HMAC-salted
  • Self — verifying.** Every step runs preflight + postflight checks and returns an inspectable report instead of failing silently — the "advanced, never
  • SQL — native, at parity.** The same functions run inside PostgreSQL (pgrx extension) and DuckDB: dedupe · match · score · auto-config + telemetry ·
  • Pipeline — native.** A dbt package (dedupe/match materializations, quality tests, identity-graph reads), a GitHub Action (fail PRs on data-quality regressions)
  • Privacy-preserving — PPRL 92.4% F1 on FEBRL4, matching across parties with no shared raw data
  • Shape — Arrow at bulk boundaries, Rust-authoritative kernels
  • Job — Block, score, cluster — throughput, vectorized, deterministic per run
  • State — Stateless per call; measurement-driven kernelization
  • Backends — DataFusion · Ray · Sail are replaceable execution backends, none synonymous with GoldenMatch
  • Boundary — Verdict
  • Package — Lang

Getting it running

The server ships on npm as infermap, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. GoldenMatch's toolset — Whole, Privacy, Self and 10 more — is a fair guide to whether it matches your workflow. It is maintained by benseverndev-oss; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch GoldenMatch.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Wholerecord provenance.** Every field of the golden record traces back to the source record that won it — which source, when it was last seen, and which survivorship strategy picked it — with the values it *didn't* pick kept
Privacypreserving record linkage.** Match across organizations without sharing raw data — Bloom-filter PPRL, **92.4% F1 on FEBRL4**, with HMAC-salted encodings.
Selfverifying.** Every step runs preflight + postflight checks and returns an inspectable report instead of failing silently — the "advanced, never black-box" contract that makes an automated identity layer safe to build on.
SQLnative, at parity.** The same functions run inside **PostgreSQL** (pgrx extension) and **DuckDB**: dedupe · match · score · auto-config + telemetry · identity-graph reads · profiling · evaluate · Fellegi-Sunter scoring ·
Pipelinenative.** A dbt package (dedupe/match materializations, quality tests, identity-graph reads), a GitHub Action (fail PRs on data-quality regressions), and 13 drop-in Airflow DAGs ([Deploy](#deploy)).
Privacy-preservingPPRL **92.4%** F1 on FEBRL4, matching across parties with no shared raw data.
ShapeArrow at bulk boundaries, Rust-authoritative kernels
JobBlock, score, cluster — throughput, vectorized, deterministic per run
StateStateless per call; measurement-driven kernelization
BackendsDataFusion · Ray · Sail are *replaceable* execution backends, none synonymous with GoldenMatch
BoundaryVerdict
PackageLang
LibraryReplaces

How to install the GoldenMatch MCP server

{
  "mcpServers": {
    "goldenmatch": {
      "command": "npx",
      "args": ["-y", "infermap"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use GoldenMatch to Whole.
  • Use GoldenMatch to Privacy.
  • Use GoldenMatch to Self.

Frequently asked questions

It connects GoldenMatch to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (Whole, Privacy, Self, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with GoldenMatch directly.