Skip to content
HubSpot logo

HubSpot MCP server

Which MCP servers are HubSpot's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-09

← Back to HubSpot

Whose server it is
  • Addresshttps://mcp.scrums.com/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on scrums.com when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools2
  • Server calls itselfScrums.com Catalog
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 446 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: Deploy AI agents and models from a centralized catalog; Measure and govern AI usage across engineering teams.
  • Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it0 of 2 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer1249 ms
  • Space in an agent's context≈ 572 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • cannot · Deploy AI agents and models from a centralized catalog
  • cannot · Measure and govern AI usage across engineering teams
  • not sure · Accelerate software delivery velocity with AI automation

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers2 tools · read 2026-10-27
  • catalog_search

    Search or browse the public Scrums.com product catalog: AI agents, software engineering talent, delivery packages, and cloud infrastructure listings. Returns published listings with title, summary, pricing info where public, and a link to…

  • catalog_get

    Fetch the full public record for one Scrums.com catalog listing — complete description content, tags, public pricing and availability fields, provider, ratings, and the canonical listing page URL on www.scrums.com. Identify the listing by…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "scrums": {
      "type": "http",
      "url": "https://mcp.scrums.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http scrums https://mcp.scrums.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.scrums.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.