mcp-registry/io.github.benseverndev-oss/goldenmatch · v1.28.1
Also listed as mcp-registry/io.github.benseverndev-oss/goldenanalysis
As of 2026-10-15 00:28 UTC, the Benseverndev Oss Goldenmatch MCP server is unknown with a Glimind reliability score of 69/100 (grade C). It is reachable and asks for credentials (normal for servers that need an account or API key). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 4 outages in 90 days, with a median recovery of 3 minutes.
Find duplicate records in 30 seconds. Zero-config entity resolution, 97.2% F1 out of the box.
Claude Code
claude mcp add --transport http benseverndev-oss-goldenmatch-mcp-server https://goldenmatch-mcp-production.up.railway.app/mcp/
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"benseverndev-oss-goldenmatch-mcp-server": {
"type": "http",
"url": "https://goldenmatch-mcp-production.up.railway.app/mcp/"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
77 of 77 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones.
77 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter.
112 parameter(s) across 42 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call.
4 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads.
Handshake + tools/list takes ~1,965 ms.
Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably.
Requires authentication; tool definitions could not be read anonymously.
If discovery should be public, allow initialize + tools/list without credentials and gate only tools/call. Directories and routers can then list your tools.
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 42 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.benseverndev-oss%2Fgoldenmatch/fixes
{
"name": "add_correction",
"description": "Add a Learning Memory correction. Two shapes:\n - pair-level: decision='approve' or 'reject', requires id_a + id_b\n - field-level (v1.18.2+): decision='field_correct', requires cluster_id + field_name + corrected_value\nSource is 'agent' with trust=0.5 (lower than human steward 1.0). Pair (id_a, id_b) is canonicalized to (min, max) before storage.",
"inputSchema": {
"type": "object",
"required": [
"decision",
"dataset"
],
"properties": {
"id_a": {
"type": "integer",
"description": "Pair-level: first row id. Field-level: ignored."
},
"id_b": {
"type": "integer",
"description": "Pair-level: second row id. Field-level: ignored."
},
"path": {
"type": "string",
"description": "SQLite memory DB path. Default: .goldenmatch/memory.db"
},
"reason": {
"type": "string"
},
"dataset": {
"type": "string",
"description": "Dataset identifier (e.g. file path). Required, non-empty."
},
"decision": {
"enum": [
"approve",
"reject",
"field_correct"
],
"type": "string"
},
"cluster_id": {
"type": "integer",
"description": "Field-level: cluster_id the correction targets."
},
"field_name": {
"type": "string",
"description": "Field-level: the column being corrected."
},
"matchkey_name": {
"type": "string"
},
"original_value": {
"type": "string",
"description": "Field-level: the value build_golden_record chose."
},
"corrected_value": {
"type": "string",
"description": "Field-level: the value the reviewer changed it to."
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "agent_approve_reject",
"description": "Approve or reject a review queue pair",
"inputSchema": {
"type": "object",
"required": [
"job_name",
"id_a",
"id_b",
"decision",
"decided_by"
],
"properties": {
"id_a": {
"type": "integer"
},
"id_b": {
"type": "integer"
},
"reason": {
"type": "string"
},
"decision": {
"type": "string"
},
"job_name": {
"type": "string"
},
"decided_by": {
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "agent_compare_strategies",
"description": "Compare ER strategies on your data",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"encoding": {
"enum": [
"base64",
"text"
],
"type": "string",
"description": "Encoding of *_content (default base64)"
},
"filename": {
"type": "string",
"description": "Original filename when using file_content"
},
"file_path": {
"type": "string"
},
"file_content": {
"type": "string",
"description": "Alternative to file_path: file bytes (base64 default, or raw with encoding='text')"
},
"ground_truth": {
"type": "string"
},
"ground_truth_name": {
"type": "string"
},
"ground_truth_content": {
"type": "string",
"description": "Alternative to ground_truth: base64/text bytes"
}
}
},
"annotations": {
"readOnlyHint": true
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/io.github.benseverndev-oss/goldenmatch"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.benseverndev-oss/goldenmatch"}) over MCP.
retrieve_similar ~417 tokensadd_correction ~383 tokenscreate_domain ~344 tokenspprl_link ~305 tokenssensitivity ~296 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fio.github.benseverndev-oss%2Fgoldenmatch?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.benseverndev-oss%2Fgoldenmatch?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.benseverndev-oss%2Fgoldenmatch.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.benseverndev-oss%2Fgoldenmatch.svg :target: https://glimind.com/server/mcp-registry%2Fio.github.benseverndev-oss%2Fgoldenmatch?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:28e93791f96940b7…, first seen 2026-10-17, included at leaf 14908 of 17,717. Version history · verify what your client received.
Compare: most reliable knowledge servers · most reliable other servers · most reliable data servers · most reliable ml servers · most reliable code servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-15 00:28 UTC, the Benseverndev Oss Goldenmatch MCP server is unknown with a Glimind reliability score of 69/100 (grade C). It is reachable and asks for credentials (normal for servers that need an account or API key). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 4 outages in 90 days, with a median recovery of 3 minutes.
Benseverndev Oss Goldenmatch MCP server advertises 79 tools, including add_correction, agent_approve_reject, agent_compare_strategies, agent_deduplicate, agent_explain_cluster.
Point your MCP client at this streamable-http endpoint: https://goldenmatch-mcp-production.up.railway.app/mcp/
Glimind scanned all 77 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.