mcp-registry/co.subtraq/subtraq · v1.0.0
As of 2026-10-26 18:03 UTC, the Subtraq MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 7 minutes.
Create short links, track clicks and attribute sales — 8 tools backed by the Subtraq API.
Point your MCP client at this streamable-http endpoint: https://subtraq.co/api/mcp
8 of 8 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. How to fix →
3 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. How to fix →
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. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fco.subtraq%2Fsubtraq/fixes
{
"name": "create_link",
"description": "Crée un lien court. Sans `parentId`, c'est un lien parent et `destination` est obligatoire. Avec `parentId`, c'est un placement : il hérite de la destination du parent et porte ses propres UTM. Renvoie `shortUrl`, prêt à publier.",
"inputSchema": {
"type": "object",
"required": [
"space"
],
"properties": {
"slug": {
"type": "string",
"description": "Raccourci souhaité. Tiré au sort s'il est omis."
},
"label": {
"type": "string",
"description": "Nom du placement, par exemple « Pub Meta — mars »."
},
"space": {
"type": "string",
"description": "Raccourci de l'espace client."
},
"domain": {
"type": "string",
"description": "Adresse qui porte le lien (« liens.votresite.fr »). Omise = le même choix que l'écran de création : le domaine de marque réservé à l'espace, sinon l'unique domaine de marque du compte, sinon l'adresse offerte de l'espace (« client.sbtq.link ») ; pour un placement, le domaine de son parent. Pour le domaine partagé, le nommer : « sbtq.link » (la valeur `domain` d'un lien partagé). Un domaine de marque doit être vérifié dans le compte, et libre pour cet espace."
},
"utmTerm": {
"type": "string",
"description": "utm_term du placement."
},
"parentId": {
"type": "string",
"description": "Identifiant du lien parent, pour créer un placement."
},
"utmMedium": {
"type": "string",
"description": "utm_medium du placement."
},
"utmSource": {
"type": "string",
"description": "utm_source du placement."
},
"utmContent": {
"type": "string",
"description": "utm_content du placement."
},
"destination": {
"type": "string",
"description": "URL d'arrivée. Obligatoire pour un parent, interdite pour un placement."
},
"utmCampaign": {
"type": "string",
"description": "utm_campaign du placement."
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "create_space",
"description": "Crée un espace client. Refusé avec le code `space_limit_reached` si la formule est pleine.",
"inputSchema": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Nom affiché, par exemple « Maison Lartigue »."
},
"slug": {
"type": "string",
"description": "Raccourci dans les URL. Déduit du nom s'il est omis."
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "get_analytics",
"description": "Les chiffres d'un espace : clics, prospects, ventes, revenu ATTRIBUÉ et revenu NON attribué, plus le détail placement par placement. Montants en CENTIMES. Subtraq ne convertit pas les devises : si `mixedCurrencies` est vrai, les totaux ne concernent que `currency`. `model` choisit la lecture de l'attribution ; la réponse rappelle toujours lequel a servi.",
"inputSchema": {
"type": "object",
"required": [
"space"
],
"properties": {
"model": {
"type": "string",
"description": "Modèle d'attribution : `first` (premier clic, défaut et référence du produit), `last` (dernier clic avant la conversion) ou `linear` (partage entre tous les placements cliqués, revenu réparti au centime près). Dans les trois cas, attribué + non attribué = revenu total."
},
"space": {
"type": "string",
"description": "Raccourci de l'espace client."
},
"period": {
"type": "string",
"description": "7d, 30d (défaut), 90d ou all."
}
}
},
"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/co.subtraq/subtraq"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/co.subtraq/subtraq"}) over MCP.
create_link ~465 tokensupdate_link ~346 tokenstrack_sale ~278 tokensget_analytics ~257 tokenslist_links ~146 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%2Fco.subtraq%2Fsubtraq?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fco.subtraq%2Fsubtraq?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fco.subtraq%2Fsubtraq.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fco.subtraq%2Fsubtraq.svg :target: https://glimind.com/server/mcp-registry%2Fco.subtraq%2Fsubtraq?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 sha256:30c95c3960dc0e14…, first seen 2026-10-17, included at leaf 14700 of 74,602. Version history · verify what your client received.
Compare: most reliable other servers · most reliable analytics servers · most reliable finance 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 2026-10-26 18:03 UTC, the Subtraq MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 7 minutes.
Subtraq MCP server advertises 8 tools, including create_link, create_space, get_analytics, get_link, list_links.
Point your MCP client at this streamable-http endpoint: https://subtraq.co/api/mcp
Glimind scanned all 8 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.