HubSpotSAFE
A Model Context Protocol (MCP) server that enables AI assistants to interact with HubSpot CRM data, providing built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://hub.docker.com/r/buryhuang/mcp-hubspot) [](https://opensource.org/licenses/MIT)
Overview
A Model Context Protocol (MCP) server that enables AI assistants to interact with HubSpot CRM data. This server bridges AI models with your HubSpot account, providing direct access to contacts, companies, and engagement data. Built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times.
Our implementation prioritizes the most frequently used, high-value HubSpot operations with robust error handling and API stability. Each component is optimized for AI-friendly interactions, ensuring reliable performance even during complex, multi-step CRM workflows.
Why MCP-HubSpot?
- Direct CRM Access: Connect Claude and other AI assistants to your HubSpot data without intermediary steps
- Context Retention: Vector storage with FAISS enables semantic search across previous interactions
- Zero Configuration: Simple Docker deployment with minimal setup
Example Prompts
Create HubSpot contacts and companies from this LinkedIn profile: [Paste LinkedIn profile text]
What's happening lately with my pipeline?
Available Tools
The server offers tools for HubSpot management and data retrieval:
2b260aa5ad2eOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-hubspot --env HUBSPOT_ACCESS_TOKEN=${HUBSPOT_ACCESS_TOKEN} -- uvx mcp-server-hubspot{
"mcpServers": {
"mcp-server-hubspot": {
"command": "uvx",
"args": [
"mcp-server-hubspot"
],
"env": {
"HUBSPOT_ACCESS_TOKEN": "${HUBSPOT_ACCESS_TOKEN}"
}
}
}
}Exposed tools (16)
10 read · 6 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
hubspot_create_company | write | Create a new company in HubSpot |
hubspot_create_contact | write | Create a new contact in HubSpot |
hubspot_create_property | write | Create a new custom property in HubSpot |
hubspot_get_active_companies | read | Get most recently active companies from HubSpot |
hubspot_get_active_contacts | read | Get most recently active contacts from HubSpot |
hubspot_get_company | read | Get a specific company by ID from HubSpot |
hubspot_get_company_activity | read | Get activity history for a specific company |
hubspot_get_contact | read | Get a specific contact by ID from HubSpot |
hubspot_get_property | read | Get details of a specific HubSpot property definition |
hubspot_get_recent_conversations | read | Get recent conversation threads from HubSpot with their messages |
hubspot_get_ticket_conversation_threads | read | Get conversation threads associated with a specific ticket |
hubspot_get_tickets | read | Get tickets from HubSpot based on configurable selection criteria |
hubspot_search_data | read | Search for similar data in stored HubSpot API responses |
hubspot_update_company | write | Update an existing company record in HubSpot |
hubspot_update_contact | write | Update an existing contact record in HubSpot |
hubspot_update_property | write | Update a HubSpot property definition (e.g., add dropdown options) |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
logger.debug(f"Using access token: {'[MASKED]' if token else 'None'}")Gates applied: no_behavioural_pass.
2b260aa5ad2efull audit observations/trust-audit/mcp-server/baryhuang__hubspot.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 2b260aa5ad2e | SAFE | B | 89 | first audit |
Questions
What is the HubSpot MCP server?
A Model Context Protocol (MCP) server that enables AI assistants to interact with HubSpot CRM data, providing built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times.
What tools does HubSpot expose?
16 in total: 10 read-only, 6 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is HubSpot safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does HubSpot need?
It reads HUBSPOT_ACCESS_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does HubSpot run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-server-hubspot.
How current is this page?
The grade is for one exact copy of the source (2b260aa5ad2e), read on 2026-10-07. The repository is watched and re-audited when it changes.