Find duplicate records in 30 seconds. Zero-config entity resolution, 97.2% F1 out of the box.
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.
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 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 whichPrivacy — preserving record linkage.** Match across organizations without sharing raw data — Bloom-filter PPRL, 92.4% F1 on FEBRL4, with HMAC-saltedSelf — verifying.** Every step runs preflight + postflight checks and returns an inspectable report instead of failing silently — the "advanced, neverSQL — 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 dataShape — Arrow at bulk boundaries, Rust-authoritative kernelsJob — Block, score, cluster — throughput, vectorized, deterministic per runState — Stateless per call; measurement-driven kernelizationBackends — DataFusion · Ray · Sail are replaceable execution backends, none synonymous with GoldenMatchBoundary — VerdictPackage — LangThe 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.
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.
| Tool | What it does |
|---|---|
| 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 survivorship strategy picked it — with the values it *didn't* pick kept |
| Privacy | preserving record linkage.** Match across organizations without sharing raw data — Bloom-filter PPRL, **92.4% F1 on FEBRL4**, with HMAC-salted encodings. |
| Self | verifying.** 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. |
| SQL | native, 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 · |
| Pipeline | native.** 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-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 |
| Library | Replaces |
{
"mcpServers": {
"goldenmatch": {
"command": "npx",
"args": ["-y", "infermap"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.