Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/amin-ale/hubspot-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/amin-ale/hubspot-mcp-server/hubspot)<a href="https://agentmods.dev/mcp/amin-ale/hubspot-mcp-server/hubspot"><img src="https://agentmods.dev/badge/mcp/amin-ale/hubspot-mcp-server/hubspot/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/amin-ale/hubspot-mcp-server/hubspot"><img src="https://agentmods.dev/badge/mcp/amin-ale/hubspot-mcp-server/hubspot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
hubspot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"hubspot": {
"command": "uvx",
"args": [
"mcp-hubspot"
]
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 8 lines scan A 659b3f5f9517
hubspot is an MCP server published in the GitHub repository amin-ale/hubspot-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
gtmos-mcp
Read-only CRM audit for Claude over MCP: score data integrity, find duplicate clusters and stalled revenue, in your environment through your own token. Runs locally from the gtmos-mcp Python package. Needs 1 environment variable to run.
hubspot-multi-mcp
Local, read-only MCP server that connects Claude to MANY HubSpot portals at once, by name. Unofficial, not affiliated with HubSpot. Runs locally from the hubspot-multi-mcp npm package.
pipedrive-mcp-server
MCP server for Pipedrive CRM. 155 tools for deals, persons, organizations, activities, and more. Runs locally from the @ckalima/pipedrive-mcp-server npm package. Needs 4 environment variables to run.
hubspot-mcp
MCP server "hubspot-mcp" as configured in ohneben/Hubspot-MCP. Runs in Docker (ghcr.io/ohneben/hubspot-mcp:1.0.1). Needs 3 environment variables to run.
livespace-crm-mcp
Unofficial local MCP server for Livespace CRM with read tools and guarded writes. Runs locally from the livespace-crm-mcp npm package. Needs 7 environment variables to run.
investor-relations-mcp
MCP server "investor-relations-mcp" as configured in adelaidasofia/investor-relations-mcp. Launched with https://github.com/adelaidasofia/investor-relations-mcp/releases/download/v0.1.0. Needs 1 environment variable to run.