GoldenMatch

Server Details

Entity resolution toolkit — deduplicate, match records, golden records, PPRL

Status: Healthy
Last Tested: 2026-03-31 06:30
Transport: Streamable HTTP
URL

See and control every tool call

Log every tool call with full inputs and outputs

Control which tools are enabled per connector

Manage credentials once, use from any MCP client

Monitor uptime and get alerted when servers go down

Available Tools

27 tools

agent_approve_rejectInspect

Approve or reject a review queue pair

ParametersJSON Schema

Name	Required	Description	Default
`id_a`	Yes
`id_b`	Yes
`reason`	No
`decision`	Yes
`job_name`	Yes
`decided_by`	Yes

agent_compare_strategiesInspect

Compare ER strategies on your data

ParametersJSON Schema

Name	Required	Description	Default
`file_path`	Yes
`ground_truth`	No

agent_deduplicateInspect

Run full ER pipeline with confidence gating and reasoning

ParametersJSON Schema

Name	Required	Description	Default
`config`	No
`file_path`	Yes

agent_explain_clusterInspect

Explain why records are in the same cluster

ParametersJSON Schema

Name	Required	Description	Default
`cluster_id`	Yes

agent_explain_pairInspect

Natural language explanation for a record pair

ParametersJSON Schema

Name	Required	Description	Default
`exact`	No
`fuzzy`	No
`record_a`	Yes
`record_b`	Yes

agent_match_sourcesInspect

Match two files with intelligent strategy selection

ParametersJSON Schema

Name	Required	Description	Default
`config`	No
`file_a`	Yes
`file_b`	Yes

agent_review_queueInspect

Get borderline pairs awaiting approval

ParametersJSON Schema

Name	Required	Description	Default
`job_name`	Yes

analyze_dataInspect

Profile data, detect domain, recommend ER strategy

ParametersJSON Schema

Name	Required	Description	Default
`file_path`	Yes

auto_configureInspect

Generate optimal matching config from data analysis

ParametersJSON Schema

Name	Required	Description	Default
`file_path`	Yes
`constraints`	No

create_domainInspect

Create a custom domain extraction rulebook. Define patterns for a specific data domain (medical devices, automotive parts, real estate, etc.).

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes	Domain name (e.g. 'medical_devices', 'automotive_parts')
`scope`	No	Save locally (.goldenmatch/domains/) or globally (~/.goldenmatch/domains/). Default: local.	local
`signals`	Yes	Column name keywords that trigger this domain (e.g. ['ndc', 'fda', 'implant'])
`stop_words`	No	Words to strip during name normalization
`brand_patterns`	No	Brand/manufacturer names to extract (e.g. ['Medtronic', 'Abbott'])
`attribute_patterns`	No	Named regex patterns for domain attributes (e.g. {'size': '\\b(\\d+mm)\\b'})
`identifier_patterns`	No	Named regex patterns for domain identifiers (e.g. {'ndc': '\\b(\\d{5}-\\d{4}-\\d{2})\\b'})

explain_matchInspect

Explain why two records match or don't match. Shows per-field score breakdown.

ParametersJSON Schema

Name	Required	Description	Default
`record_a`	Yes	First record fields
`record_b`	Yes	Second record fields

export_resultsInspect

Export matching results to a file (CSV or JSON).

ParametersJSON Schema

Name	Required	Description	Default
`format`	No	Output format (default csv)	csv
`output_path`	Yes	File path to save results

find_duplicatesInspect

Find duplicate matches for a record. Provide field values to search against the loaded dataset.

ParametersJSON Schema

Name	Required	Description	Default
`top_k`	No	Max results to return (default 5)
`record`	Yes	Record fields to match (e.g. {"name": "John Smith", "zip": "10001"})

get_clusterInspect

Get details of a specific cluster: all member records and their field values.

ParametersJSON Schema

Name	Required	Description	Default
`cluster_id`	Yes	Cluster ID to look up

get_golden_recordInspect

Get the merged golden (canonical) record for a cluster.

ParametersJSON Schema

Name	Required	Description	Default
`cluster_id`	Yes	Cluster ID

get_statsInspect

Get dataset statistics: record count, cluster count, match rate, cluster sizes.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

list_clustersInspect

List duplicate clusters found in the dataset. Returns cluster IDs, sizes, and member counts.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	Max clusters to return (default 20)
`min_size`	No	Minimum cluster size to include (default 2)

list_domainsInspect

List available domain extraction rulebooks (built-in + user-defined).

ParametersJSON Schema

Name	Required	Description	Default
No parameters

match_recordInspect

Match a single record against the loaded dataset in real-time. Paste a record's fields and instantly see if it matches any existing record. Uses the configured matchkeys, scorers, and thresholds. Example: {"name": "John Smith", "email": "john@test.com", "zip": "10001"}

ParametersJSON Schema

Name	Required	Description
`top_k`	No	Max matches to return (default 5)
`record`	Yes	Record fields to match against the dataset
`threshold`	No	Minimum score to consider a match (default: use config threshold)

pprl_auto_configInspect

Analyze the loaded dataset and recommend optimal PPRL (privacy-preserving record linkage) configuration. Returns recommended fields, bloom filter parameters, threshold, and explanation.

ParametersJSON Schema

Name	Required	Description	Default
`use_llm`	No	Use LLM for enhanced recommendations (requires API key)
`security_level`	No	Security level (default: high)	high

pprl_linkInspect

Run privacy-preserving record linkage between two parties' data. Computes bloom filters, matches records without sharing raw data. Specify fields, threshold, and security level.

ParametersJSON Schema

Name	Required	Description	Default
`fields`	Yes	Field names to match on (e.g. ['first_name', 'last_name', 'zip_code'])
`file_a`	Yes	Path to party A's CSV file
`file_b`	Yes	Path to party B's CSV file
`threshold`	No	Match threshold (default: auto-detected)
`security_level`	No		high

profile_dataInspect

Get data quality profile: column types, null rates, unique counts, sample values.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

shatter_clusterInspect

Break an entire cluster into individual records. All members become singletons. Use when a cluster is completely wrong.

ParametersJSON Schema

Name	Required	Description	Default
`cluster_id`	Yes	Cluster ID to shatter

suggest_configInspect

Analyze bad merges and suggest config changes. Provide examples of incorrect merges (pairs that should NOT have matched) and GoldenMatch will identify which fields/thresholds to tighten. Example: [{"record_a": {...}, "record_b": {...}, "reason": "different people"}]

ParametersJSON Schema

Name	Required	Description	Default
`bad_merges`	Yes	List of bad merge examples with record_a, record_b, and optional reason

suggest_pprlInspect

Check if data needs privacy-preserving matching

ParametersJSON Schema

Name	Required	Description	Default
`file_path`	Yes

test_domainInspect

Test a domain extraction rulebook against sample records. Shows what features would be extracted from the loaded data.

ParametersJSON Schema

Name	Required	Description	Default
`domain_name`	Yes	Name of the domain rulebook to test
`sample_size`	No	Number of records to test (default 10)

unmerge_recordInspect

Remove a record from its cluster. The record becomes a singleton. Remaining cluster members are re-clustered using stored pair scores. Use this to fix bad merges.

ParametersJSON Schema

Name	Required	Description	Default
`record_id`	Yes	Row ID of the record to unmerge

Verify Ownership

Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:

{
  "$schema": "https://glama.ai/mcp/schemas/connector.json",
  "maintainers": [
    {
      "email": "your-email@example.com"
    }
  ]
}

The email address must match the email associated with your Glama account. Once verified, the connector will appear as claimed by you.

Server Details

Available Tools

Verify Ownership

Discussions

Your Connectors

Resources