Should my agent depend on the MCP server io.github.benseverndev-oss/goldenmatch?

Verdict: allow — rich-solo — safe to depend on As of 2026-08-15T11:28:18Z: a dated observation with receipts, not a warranty.

GoldenMatch

io.github.benseverndev-oss/goldenmatch

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

— the operator's own registry description reported

Publisher io.github.benseverndev-oss · first seen 2026-08-12 · endpoint https://goldenmatch-mcp-production.up.railway.app/mcp/

allow

verdict

rich-solo

cluster

ok_tools

answers

tools served

Dependency rating derived

allow — rich-solo — safe to depend on

Cluster rich-solo · distinctiveness 0.745 (unusual). Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.

Reach — can an agent get to it?

answersalive_tools

latency100 ms

vs populationtypical

protocolcurrent

authopen

Use — can it use it?

tools77

vs populationhigh

capabilities4

harnessA

Trust — can it rely on it?

identitysolo

servers on its host1

verifiabilityunassessed

duplicate inventoryno

drift events0

answers trueno primary

🔏 Signed receipt rr_553c6a423c8ab8dc4599ecb2 · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Tools last seen

add_correction agent_approve_reject agent_compare_strategies agent_deduplicate agent_explain_cluster agent_explain_pair agent_match_sources agent_review_queue analyze_blocking analyze_data auto_configure certify_recall compare_clusters config_weaknesses controller_telemetry create_domain dedupe documents_ingest documents_suggest_schema evaluate explain_cluster explain_match explain_pair explain_routing export_results find_duplicates fix_quality get_cluster get_golden_record get_stats identity_audit identity_audit_seal identity_audit_verify identity_claim identity_conflicts identity_history identity_list identity_merge identity_profile identity_resolve identity_resolve_conflict identity_show identity_split identity_stats identity_worklist incremental learn_thresholds lineage lint_routing list_clusters list_corrections list_domains list_plugins list_runs match match_record memory_export memory_import memory_stats plan_routing pprl_auto_config pprl_link profile profile_data retrieve_similar review_config rollback run_transforms scan_quality schema_match sensitivity shatter_cluster suggest_config suggest_pprl test_domain unmerge_record upload_dataset

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band A — an agent can pick and call these reliably.

legibility check	tools passing	ok
name is clear & specific	77/77	✓
has a description	77/77	✓
description is substantive	74/77	74/77
parameters are typed	77/77	✓
parameters are described	35/77	35/77

77 of 77 tools graded · 77 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2025-06-18

protocol version

—

session model

1.28.1

server version GoldenMatch

Capabilities: experimental prompts resources tools

Drift

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)

date	type	what changed
2026-08-12	outcome	first probe: ok_tools

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-08-14T19:59:24Z	ok_tools	200	100	2025-06-18
2026-08-12T05:34:37Z	ok_tools	200	92	2025-06-18

Watch or embed this verdict

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/io.github.benseverndev-oss/goldenmatch.svg)](https://robinsaige.com/s/io.github.benseverndev-oss/goldenmatch)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview