Skip to main content
Glama

Server Details

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

If you are the author of this connector, you can claim ownership with GitHub, an HTTP challenge, or a DNS record. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Unhealthy
Last Tested
Transport
Streamable HTTP
URL
Repository
benseverndev-oss/goldenmatch
GitHub Stars
122

Frequently Asked Questions

Discussions

No comments yet. Be the first to start the discussion!

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    Resolves messy company, customer, and vendor names across CRM, ERP, and ITSM systems to canonical records using fuzzy matching, preventing AI agents from updating or creating wrong or duplicate records.
    5
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Let LLMs analyze sensitive data safely by querying a tokenized, join-preserving copy of the database, with fail-closed PII scanning and provable numeric equivalence.
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Zero-config data quality monitoring as MCP tools. Profiles a warehouse (Postgres, BigQuery, Snowflake, MySQL, DuckDB), detects anomalies, and gates CI — read-only with the connection resolved server-side, never via the model.
    6
    9
    MIT
Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.6/5.0
Disambiguation1/5

Multiple tools are explicit aliases (e.g., dedupe/find_duplicates, match/match_record, explain_cluster/agent_explain_cluster) creating redundant entry points. Additionally, overlapping functionality exists between tools like add_correction and agent_approve_reject for approvals, and between find_duplicates, match_record, and agent_deduplicate for matching, making it difficult for an agent to select the correct tool.

Naming Consistency3/5

Tool names are mostly snake_case and readable, but follow multiple conventions: verb_noun (list_clusters, run_transforms), subject_verb (identity_merge, identity_split), and an agent_ prefix group (agent_approve_reject). This mixing of patterns, while not chaotic, lacks a uniform style.

Tool Count1/5

With 77 tools, the count is extremely high for an entity resolution server. Many are aliases or near-duplicates, inflating the surface unnecessarily. This exceeds the typical well-scoped range and creates a heavy, cluttered interface.

Completeness4/5

The server covers a wide range of entity resolution tasks: ingestion, profiling, configuration, matching, analysis, identity management, corrections, auditing, and exports. Minor gaps exist, such as no tool to list uploaded datasets or delete runs cleanly, but overall coverage is comprehensive for the domain.