convez.ai
MCP ServerAutomaçãoAvançado
Knuckles-Team

Plane Agent

Knuckles-Team/plane-agent

MCP Server para Plane com ferramentas otimizadas e segurança empresarial

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP Server para integração com Plane, oferecendo ferramentas consolidadas de ação-roteamento que minimizam overhead de tokens e suportam segurança em nível empresarial. Funciona como CLI, API ou agente completo com suporte a OpenTelemetry e Langfuse.

Instalação

$npx convez-ai Knuckles-Team/plane-agent

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
25%
Último commit
há 3 dias
Versão
v2.3.18
Issues abertas
1
Contribuidores
2

Casos de uso

  • Automação de gerenciamento de projetos via agentes IA
  • Integração de Plane com workflows de IA generativa
  • Rastreamento e telemetria de execuções de agentes

Veredito

Ferramenta madura (v0.31.0) e bem documentada para integração deep de Plane com agentes Claude. Exige conhecimento de MCP, Python e arquitetura de agentes, mas oferece segurança e observabilidade enterprise para automação de projeto em escala.

README

A tradução para o português deste README ainda está na fila.

Plane Agent

CLI or API | MCP | Agent

PyPI - Version MCP Server PyPI - Downloads GitHub Repo stars GitHub forks GitHub contributors PyPI - License GitHub GitHub last commit (by committer) GitHub pull requests GitHub closed pull requests GitHub issues GitHub top language GitHub language count GitHub repo size GitHub repo file count (file type) PyPI - Wheel PyPI - Implementation

Version: 0.31.0

Documentation — Installation, deployment, usage across the API, CLI, and MCP interfaces, and guidance for provisioning a self-hosted Plane instance are maintained in the official documentation.


Table of Contents


Overview

Plane Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Plane MCP Agent.


Key Features

  • Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
  • Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
  • Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
  • Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

CLI or API

This agent wraps the Plane MCP Agent API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.


MCP

This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Tool ModuleToggle Env VarEnabled by DefaultDescription & Nested Methods
ProjectsPROJECTS_TOOLTrueManage plane projects operations. Action-routed methods: list_projects, retrieve_project.
Work ItemsWORK_ITEMS_TOOLTrueManage plane work items operations. Action-routed methods: create_work_item, create_work_item_comment, create_work_item_link, create_work_log, delete_work_item, list_work_item_activities, list_work_item_comments, list_work_item_links, list_work_item_relations, list_work_item_types, list_work_items, list_work_logs, retrieve_work_item, retrieve_work_item_by_identifier, search_work_items, update_work_item.
CyclesCYCLES_TOOLTrueManage plane cycles operations. Action-routed methods: add_work_items_to_cycle, create_cycle, delete_cycle, list_cycle_work_items, list_cycles, retrieve_cycle, update_cycle.
EpicsEPICS_TOOLTrueManage plane epics operations. Action-routed methods: create_epic, delete_epic, list_epics, retrieve_epic, update_epic.
MilestonesMILESTONES_TOOLTrueManage plane milestones operations. Action-routed methods: create_milestone, delete_milestone, list_milestones, retrieve_milestone, update_milestone.
ModulesMODULES_TOOLTrueManage plane modules operations. Action-routed methods: create_module, delete_module, list_modules, retrieve_module, update_module.
StatesSTATES_TOOLTrueManage plane states operations. Action-routed methods: create_state, list_states.
UsersUSERS_TOOLTrueManage plane users operations. Action-routed methods: get_me, list_users.
WorkspacesWORKSPACES_TOOLTrueManage plane workspaces operations. Action-routed methods: get_workspace, get_workspace_features, get_workspace_members, update_workspace_features.
InitiativesINITIATIVES_TOOLTrueManage plane initiatives operations. Action-routed methods: create_initiative, list_initiatives.
IntakeINTAKE_TOOLTrueManage plane intake operations. Action-routed methods: create_intake_work_item, list_intake_work_items.
LabelsLABELS_TOOLTrueManage plane labels operations. Action-routed methods: create_label, list_labels.
PagesPAGES_TOOLTrueManage plane pages operations. Action-routed methods: create_project_page, retrieve_project_page.

Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/index.md.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

  • CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
  • Environment Variables: Define standard environment variables:
    • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
    • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
  • HTTP SSE Request Headers: Pass custom headers during transport initialization:
    • x-mcp-enabled-tools / x-mcp-disabled-tools
    • x-mcp-enabled-tags / x-mcp-disabled-tags
  • HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:
    • ?tools=tool1,tool2
    • ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.


MCP Configuration Examples

stdio Transport (Recommended for local IDEs e.g., Cursor, Claude Desktop)

Configure your IDE's mcp.json to launch the MCP server via uvx:

{
  "mcpServers": {
    "plane-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "plane-agent",
        "plane-mcp"
      ],
      "env": {
        "PLANE_BASE_URL": "your_plane_base_url_here",
        "PLANE_WORKSPACE_SLUG": "your_plane_workspace_slug_here",
        "DEBUG": "your_debug_here",
        "PYTHONUNBUFFERED": "your_pythonunbuffered_here",
        "PLANE_API_KEY": "your_plane_api_key_here"
      }
    }
  }
}

Streamable-HTTP Transport (Recommended for production deployments)

Configure your client's mcp.json to launch the Streamable-HTTP server via uvx with explicit host and port definition:

{
  "mcpServers": {
    "plane-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "plane-agent",
        "plane-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "PLANE_BASE_URL": "your_plane_base_url_here",
        "PLANE_WORKSPACE_SLUG": "your_plane_workspace_slug_here",
        "DEBUG": "your_debug_here",
        "PYTHONUNBUFFERED": "your_pythonunbuffered_here",
        "PLANE_API_KEY": "your_plane_api_key_here"
      }
    }
  }
}

Alternatively, connect to a pre-deployed remote or local Streamable-HTTP instance:

{
  "mcpServers": {
    "plane-agent": {
      "url": "http://localhost:8000/plane-agent/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name plane-agent-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e PLANE_BASE_URL="your_value" \
  -e PLANE_WORKSPACE_SLUG="your_value" \
  -e DEBUG="your_value" \
  -e PYTHONUNBUFFERED="your_value" \
  -e PLANE_API_KEY="your_value" \
  knucklessg1/plane-agent:latest

Additional Deployment Options

plane-agent can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

  • Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.
  • Remote URL — connect to a server deployed behind Caddy at http://plane-mcp.arpa/mcp using the "url" key.

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Set credentials
export PLANE_BASE_URL="your_value"
export PLANE_WORKSPACE_SLUG="your_value"
export DEBUG="your_value"
export PYTHONUNBUFFERED="your_value"
export PLANE_API_KEY="your_value"

# Run the agent server
plane-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:

version: '3.8'

services:
  plane-agent-mcp:
    image: knucklessg1/plane-agent:latest
    container_name: plane-agent-mcp
    hostname: plane-agent-mcp
    restart: always
    env_file:
      - ../.env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  plane-agent-agent:
    image: knucklessg1/plane-agent:latest
    container_name: plane-agent-agent
    hostname: plane-agent-agent
    restart: always
    depends_on:
      - plane-agent-mcp
    env_file:
      - ../.env
    command: [ "plane-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9004
      - MCP_URL=http://plane-agent-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9004:9004"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9004/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/overview.md and docs/index.md.


Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

  • Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
  • OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
  • Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

FeatureFunctionalityEnablement
Tool GuardSensitivity inspection with human-in-the-loop validationEnabled by default
Prompt Injection DefenseInput scanning, repetition monitoring, and recursive loop blocksEnabled by default
Context Safety GuardStuck-loop detectors and contextual overflow preemptive alertsEnabled by default

Environment Variables

The Plane Agent supports the following environment variables for configuration and integration:

VariableDescription
PLANE_BASE_URLThe base URL of the Plane instance.
PLANE_WORKSPACE_SLUGThe workspace slug of the Plane workspace.
PLANE_API_KEYThe API key for authentication with Plane.
MCP_URLThe URL of the MCP server.
MODEL_IDDefault LLM model identifier (e.g. gpt-4o).
PROVIDERThe LLM provider (e.g. openai, anthropic).
ENABLE_WEB_UISet to True to enable the built-in Web UI.
ENABLE_OTELSet to True to enable OpenTelemetry telemetry.
AGENT_UTILITIES_TESTINGSet to True during testing to bypass production setups.
AUTH_TYPEThe authentication type to use (e.g., jwt, none).
DEFAULT_API_KEYDefault API key for fast server fallback authentication.
OTEL_EXPORTER_OTLP_ENDPOINTThe OpenTelemetry OTLP endpoint.
PROJECTSTOOLSet to True/False to toggle the Projects tool module.
WORK_ITEMSTOOLSet to True/False to toggle the Work Items tool module.
CYCLESTOOLSet to True/False to toggle the Cycles tool module.
EPICSTOOLSet to True/False to toggle the Epics tool module.
MILESTONESTOOLSet to True/False to toggle the Milestones tool module.
MODULESTOOLSet to True/False to toggle the Modules tool module.
STATESTOOLSet to True/False to toggle the States tool module.
USERSTOOLSet to True/False to toggle the Users tool module.
WORKSPACESTOOLSet to True/False to toggle the Workspaces tool module.
INITIATIVESTOOLSet to True/False to toggle the Initiatives tool module.
INTAKETOOLSet to True/False to toggle the Intake tool module.
LABELSTOOLSet to True/False to toggle the Labels tool module.
PAGESTOOLSet to True/False to toggle the Pages tool module.

Installation

Install the Python package locally:

# Using uv (highly recommended)
uv pip install plane-agent[all]

# Using standard pip
python -m pip install plane-agent[all]

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

PageContents
Installationpip, source, uv, prebuilt Docker image
Deploymentrun the MCP server and agent, Compose, Caddy + Technitium, env config
Usagethe MCP tools, the Api client, the CLI
Backing Platformdeploy a self-hosted Plane instance with Docker
Overviewecosystem role, enterprise posture, architecture
Conceptsconcept registry (CONCEPT:PLANE-*)

Repository Owners

GitHub followers GitHub User's stars


Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

  • Format code using ruff format .
  • Lint code using ruff check .
  • Validate type-safety with mypy .
  • Execute test suites using pytest
Ver o original no GitHub

Bom para

Relacionados