HubSpot MCP in Claude Code

Quick answer: Install the HubSpot MCP server with npx -y @hubspot/mcp-server, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on @hubspot/mcp-server as of April 15, 2026.

The HubSpot MCP server hands Claude Code a tool surface on the HubSpot CRM API. After setup, the model can search contacts, create deals, update company records, fetch engagement history, and manage pipelines. The server is published by HubSpot as @hubspot/mcp-server and uses a private app access token for auth.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the HubSpot server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside HubSpot day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed include search_contacts, get_contact, create_contact, update_contact, search_deals, create_deal, update_deal, list_pipelines, search_companies, get_engagements. The batch endpoints reduce call counts dramatically for imports - ask Claude to use batch_create when inserting more than a handful of records.

Prerequisites

A HubSpot account, a private app created under Settings > Integrations > Private Apps with the scopes you need (contacts, deals, companies). The access token from that private app. Node 20 or later.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y @hubspot/mcp-server

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "hubspot": {
      "command": "npx",
      "args": ["-y", "@hubspot/mcp-server"],
      "env": {
        "HUBSPOT_ACCESS_TOKEN": "pat-XXX"
      }
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• Find the contact with email alice@example.com and tell me their lifecycle stage, owner, and last interaction date.
• Create a new deal in pipeline Sales stage Appointment Scheduled with amount 50000 and associate it with company Acme Inc.
• List every contact created in the last 7 days and show name, email, and company for each.
• Update company HubID 12345 to set industry SaaS and employee count 120.
• Search for deals in the Closed Won stage with amount over 10000 in the last 90 days and sum the values.
• Read the engagement history (emails, calls, notes) for contact ID 9876 in the last 30 days.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

The token lives in HUBSPOT_ACCESS_TOKEN and starts with pat-. Private app tokens are tied to the app's scope set - edit the app at Settings > Integrations > Private Apps to add or remove permissions. Rotate by regenerating the token from the same page. Never commit; keep it in your shell profile.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Tool calls return 401. The token is wrong, revoked, or from a different HubSpot portal. Verify the portal ID in the URL matches, regenerate the token, and update the env var.

Tool calls return 403 Missing scope. The private app does not have the scope the operation needs. Open the app config, enable the scope (e.g., crm.objects.contacts.write), and save - the token keeps working with the new scopes.

Search returns only 100 results. HubSpot search endpoint paginates at 100 per call with a cursor. Ask Claude to use the paging.next.after cursor to fetch subsequent pages rather than trying to bump the limit.

Rate limit errors at 100 per 10 seconds. HubSpot daily call limits also apply (typically 250K per day on Pro). For bulk updates, use the batch endpoints - they count as one call per batch of 100 records.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the HubSpot server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.