Connect Pipefy to Cursor via MCP: Cards and Phases

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

Pipefy + Cursor

Pipefy work management platform: organizations, pipes (workflows), cards and phases through the GraphQL API. List the pipes an AI assistant can see, track cards as they move through phases, and read card field values.

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:

PIPEFY_API_TOKEN

Step 1 — Get credentials

Setting up takes a few minutes. You need a Pipefy account and an API token.

1. Open https://app.pipefy.com/tokens, click Generate new token, give it a description and save. Use the longer token shown there. For production, Pipefy recommends a Service Account token instead (see the Authentication page in the Pipefy developer docs).
2. Paste the token into PIPEFY_API_TOKEN. The connector sends it as a bearer token on every call.
3. Install the connector and run pipefy_list_organizations: it lists the organizations the token can see and doubles as the check that the token works.

What it reads: your organizations, the pipes (workflows) of an organization, and one pipe with its card counts, phases, start-form fields and labels. It lists the cards of a pipe with title, done flag, update time, current phase and assignees, opens one card with every field value, and shows one phase with its card count and fields. A typical path is pipefy_list_organizations, pipefy_list_pipes, pipefy_get_pipe (to learn the phase ids), pipefy_list_cards and pipefy_get_card.

Ids: all Pipefy ids are numbers. A pipe id is the number in the pipe URL, e.g. 301234567 in https://app.pipefy.com/pipes/301234567, and card, phase and organization ids work the same way.

Limits: pipefy_list_cards returns 25 cards per page by default and at most 50, the most Pipefy returns per request. When pageInfo.hasNextPage is true, the AI passes pageInfo.endCursor as after to get the next page. Pipefy also has a monthly API-call quota that depends on your plan, and one tool call is one API call.

The connector is read-only: it does not create, move or update cards, and it does not search cards (it pages through them instead).

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Cursor

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Cursor reads MCP servers from ~/.cursor/mcp.json. Add this entry:

{
  "mcpServers": {
    "anythingmcp": {
      "url": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart Cursor.
3. Open Cursor → Settings → MCP and check that anythingmcp is listed and connected.
4. Start chatting — the agent can now call the Pipefy tools.

Available tools

FAQ

Does Cursor support custom MCP servers on the free tier? Yes — MCP is available on Hobby, Pro and Business plans.

Next steps

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