pine-mcp-server

pine-mcp-server is a local MCP server (Python) that exposes tools for managing Pine AI assistant sessions and task execution. It supports authentication via Pine access token/user id or via an email-based code flow, and provides MCP tools for creating/listing/getting/deleting sessions, sending conversation messages/forms/location responses, starting/stopping tasks, uploading/deleting attachments, and handling call reminders/social sharing.

Evaluated Apr 04, 2026 (27d ago)
Homepage ↗ Repo ↗ Automation mcp assistant automation bill-negotiation python sessions tasks attachments client-tools local-server
⚙ Agent Friendliness
53
/ 100
Can an agent use this?
🔒 Security
57
/ 100
Is it safe for agents?
⚡ Reliability
20
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
75
Documentation
70
Error Messages
0
Auth Simplicity
70
Rate Limits
10

🔒 Security

TLS Enforcement
70
Auth Strength
70
Scope Granularity
20
Dep. Hygiene
50
Secret Handling
70

Security is largely dependent on the underlying pine-assistant and Pine AI services. The README indicates token/user id via environment variables (generally safer than hardcoding) and an OTP-based runtime auth option. However, scope granularity, least-privilege model, and rate limit details are not described. Also, local MCP servers expose credentials via process environment, so agents/hosts must ensure logs/process introspection don’t leak env vars.

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
20
Error Recovery
30
AF Security Reliability

Best When

You want a local MCP integration for Pine AI workflows and your agent can follow a load-conversation polling pattern (create session → send message → poll history → start task → poll results).

Avoid When

You need real-time streaming updates, strict idempotent semantics for retries, or comprehensive published interface specs/error codes beyond what’s described in the README.

Use Cases

  • Automating bill negotiation workflows through an LLM agent using MCP
  • Canceling or managing subscriptions on behalf of a user via an agent workflow
  • Resolving disputes with Pine AI by providing instructions and attachments (e.g., screenshots, bills)
  • Guiding an agent to schedule/prepare phone calls and update call reminders
  • Uploading supporting documents to an assistant session via MCP tools

Not For

  • Performing actions without user consent or review (e.g., canceling subscriptions)
  • High-trust automation in sensitive scenarios without guardrails/idempotency controls
  • Use as a generic Pine AI REST API replacement (it is specifically an MCP server wrapper)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
Yes
Webhooks
No

Authentication

Methods: PINE_ACCESS_TOKEN + PINE_USER_ID via environment variables pine_auth_request_code (email verification code request) pine_auth_verify_code (verify code and obtain credentials)
OAuth: No Scopes: No

Auth is described as either supplying access token/user id via env vars or authenticating at runtime using MCP auth tools (email OTP/code flow). No OAuth scopes are mentioned.

Pricing

Free tier: No
Requires CC: No

No pricing information is provided for pine-mcp-server itself; costs likely depend on Pine AI usage.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • No real-time streaming; agents must periodically poll pine_get_history to observe updates.
  • Polling/refresh loops can cause duplicate actions if the agent retries without idempotency guarantees (not documented).
  • Task start/stop are stateful operations; without documented state transitions, agents may need additional checks via session/task details (not described).

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for pine-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered