Pine Assistant MCP Server
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Pine Assistant MCP Servernegotiate my Comcast internet bill"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Pine Assistant MCP Server
A local MCP server that lets any LLM agent manage Pine AI tasks — negotiate bills, cancel subscriptions, resolve disputes, and make phone calls on your behalf.
Built on the pine-assistant Python SDK.
Installation
pip install pine-mcp-serverOr run directly with uvx (no install needed):
uvx pine-mcp-serverQuick Start
1. Get your Pine AI credentials
You need an access_token and user_id from Pine AI. Either:
Sign up at 19pine.ai and retrieve your credentials, or
Use the built-in auth tools (
pine_auth_request_code/pine_auth_verify_code) to authenticate via email.
2. Configure your MCP client
Claude Desktop — edit claude_desktop_config.json:
{
"mcpServers": {
"pine-assistant": {
"command": "uvx",
"args": ["pine-mcp-server"],
"env": {
"PINE_ACCESS_TOKEN": "your-access-token",
"PINE_USER_ID": "your-user-id"
}
}
}
}Cursor — edit .cursor/mcp.json:
{
"mcpServers": {
"pine-assistant": {
"command": "uvx",
"args": ["pine-mcp-server"],
"env": {
"PINE_ACCESS_TOKEN": "your-access-token",
"PINE_USER_ID": "your-user-id"
}
}
}
}If you prefer pip install, replace "command": "uvx" with "command": "pine-mcp-server" and remove the "args" field.
3. Use it
Ask your LLM agent something like:
"Use Pine AI to negotiate my Comcast internet bill. My account number is 12345."
The agent will create a session, send your request, and check back for updates.
How It Works
The server follows a "load conversation" model — like refreshing a browser page:
Create a session —
pine_session_createSend a message describing the task —
pine_send_messageWait, then check what Pine replied —
pine_get_historyStart the task when ready —
pine_task_startCheck again for results —
pine_get_history
There is no real-time streaming. The agent periodically loads the conversation history to see updates, similar to refreshing the Pine web app.
Available Tools
Authentication
Tool | Description |
| Request a verification code via email |
| Verify the code and obtain credentials |
Sessions
Tool | Description |
| Create a new Pine session |
| List sessions with optional filters |
| Get details about a session |
| Delete a session |
| Get the web URL to view a session |
Conversation
Tool | Description |
| Load conversation history (the core "refresh" tool) |
| Send a text message to Pine |
| Submit a form that Pine sent |
| Submit an OTP/verification code |
| Submit location coordinates |
| Submit a location selection |
Tasks
Tool | Description |
| Start task execution |
| Stop a running task |
Attachments
Tool | Description |
| Upload a local file (bill, screenshot, etc.) |
| Delete an uploaded attachment |
Social & Scheduling
Tool | Description |
| Share results on social media to earn credits |
| Update a scheduled call reminder |
Environment Variables
Variable | Required | Description |
| Yes* | Pine AI access token |
| Yes* | Pine AI user ID |
| No | Pine AI backend URL (default: |
| No | Stable device identifier. Recommended when the server runs as a subprocess (Claude Desktop, Cursor) — otherwise a fresh random ID is generated on each launch if |
* Not required if you authenticate at runtime using the auth tools.
Development
pip install -e ".[dev]"License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/19PINE-AI/pine-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server