{"id":"pine-mcp-server","name":"pine-mcp-server","homepage":"https://pypi.org/project/pine-mcp-server/","repo_url":"https://github.com/19PINE-AI/pine-mcp-server","category":"automation","subcategories":[],"tags":["mcp","assistant","automation","bill-negotiation","python","sessions","tasks","attachments","client-tools","local-server"],"what_it_does":"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.","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)"],"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.","alternatives":["Direct use of the underlying pine-assistant Python SDK (if available and sufficient)","Using any official web/Pine UI flows manually","Building a custom MCP server wrapper around Pine APIs/SDK with additional safety, retries, and structured error mapping"],"af_score":52.8,"security_score":57.0,"reliability_score":20.0,"package_type":"mcp_server","discovery_source":["pypi"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T21:48:28.069642+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":true,"sdk_languages":["python"],"openapi_spec_url":null,"webhooks":false},"auth":{"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":false,"scopes":false,"notes":"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":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information is provided for pine-mcp-server itself; costs likely depend on Pine AI usage."},"requirements":{"requires_signup":true,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":52.8,"security_score":57.0,"reliability_score":20.0,"mcp_server_quality":75.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":70.0,"rate_limit_clarity":10.0,"tls_enforcement":70.0,"auth_strength":70.0,"scope_granularity":20.0,"dependency_hygiene":50.0,"secret_handling":70.0,"security_notes":"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.","uptime_documented":0.0,"version_stability":30.0,"breaking_changes_history":20.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":"The README describes a load/poll pattern but does not mention idempotent behavior for session creation, message sending, or task start/stop.","pagination_style":"none","retry_guidance_documented":false,"known_agent_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)."]}}