How to Connect Harvest to Gemini — via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Harvest, paste your credentials, mint an MCP API key — done. No Docker, no git clone, no local server.

Harvest + Gemini

Manage Harvest (time tracking, projects, clients, invoices, expenses) from any AI agent. 10 tools, Bearer auth with account-ID header.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

HARVEST_ACCESS_TOKEN, HARVEST_ACCOUNT_ID

Step 1 — Get credentials

This connector wraps the Harvest API v2 (api.harvestapp.com/v2).

Setup:

1. Log into https://id.getharvest.com → bottom-left avatar → Developers → Create new personal access token.
2. Copy the token and the Account ID shown on the same page (a 7-digit number like 1234567).
3. Set both: HARVEST_ACCESS_TOKEN and HARVEST_ACCOUNT_ID.

Authentication: every request requires BOTH:

• Authorization: Bearer ${HARVEST_ACCESS_TOKEN}
• Harvest-Account-Id: ${HARVEST_ACCOUNT_ID}
• A User-Agent header (Harvest API requires it — the adapter sets AnythingMCP (support@anythingmcp.com)).

…(continued in the in-app connector instructions)

Step 2 — Install the adapter

git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d

Step 3 — Add the connector in Gemini

Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
    }
  }
}

1. Get your MCP API key from AnythingMCP → Profile → MCP API Keys → New Key.
2. Save the file and restart gemini.
3. Run /mcp inside the Gemini CLI — Harvest should be listed as available.
4. Vertex AI Studio: pass https://cloud.anythingmcp.com/mcp to the tools array of your request with the same Bearer header.

Available tools

FAQ

Does Gemini 1.5 Pro or 2.x support MCP? Yes — Gemini CLI ≥ 0.4 and Vertex AI tools API both accept MCP httpUrl connectors with Bearer headers.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor