plane-agent 0.34.0

Plane MCP Agent

Plane Agent

CLI or API | MCP | Agent

Version: 0.33.0

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
• Key Features
• CLI or API
• MCP
  • Available MCP Tools
  • MCP Configuration Examples
  • Dynamic Tool Selection & Visibility
• Agent
  • Running the Agent CLI
  • Docker Compose Orchestration
• Security & Governance
• Environment Variables
• Installation
• Documentation
• Repository Owners
• Contribute

---

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

This table is auto-generated from the live server — do not edit by hand.

MCP Tool	Toggle Env Var	Description
plane_cycles	CYCLESTOOL	Manage plane cycles operations.
plane_epics	EPICSTOOL	Manage plane epics operations.
plane_initiatives	INITIATIVESTOOL	Manage plane initiatives operations.
plane_intake	INTAKETOOL	Manage plane intake operations.
plane_labels	LABELSTOOL	Manage plane labels operations.
plane_milestones	MILESTONESTOOL	Manage plane milestones operations.
plane_modules	MODULESTOOL	Manage plane modules operations.
plane_pages	PAGESTOOL	Manage plane pages operations.
plane_projects	PROJECTSTOOL	Manage plane projects operations.
plane_states	STATESTOOL	Manage plane states operations.
plane_users	USERSTOOL	Manage plane users operations.
plane_work_items	WORK_ITEMSTOOL	Manage plane work items operations.
plane_workspaces	WORKSPACESTOOL	Manage plane workspaces operations.

13 action-routed tools (default MCP_TOOL_MODE=condensed). Each is enabled unless its toggle is set false; set MCP_TOOL_MODE=verbose (or both) for the 1:1 per-operation surface. Auto-generated — do not edit.

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

Install the slim [mcp] extra. All examples below install plane-agent[mcp] — the MCP-server extra that pulls only the FastMCP / FastAPI tooling (agent-utilities[mcp]). It deliberately excludes the heavy agent runtime (the epistemic-graph engine, pydantic-ai, dspy, llama-index, tree-sitter), so uvx/container installs are dramatically smaller and faster. Use the full [agent] extra only when you need the integrated Pydantic AI agent (see Installation).

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[mcp]",
        "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[mcp]",
        "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:mcp

The :mcp tag is the slim MCP-server image (built from docker/Dockerfile --target mcp, installing plane-agent[mcp]). The default :latest tag is the full agent image (--target agent, plane-agent[agent]) which also bundles the Pydantic AI agent and the epistemic-graph engine — use it when you run plane-agent (the agent), not just the MCP server. See Container images.

---

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:mcp
    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

Feature	Functionality	Enablement
Tool Guard	Sensitivity inspection with human-in-the-loop validation	Enabled by default
Prompt Injection Defense	Input scanning, repetition monitoring, and recursive loop blocks	Enabled by default
Context Safety Guard	Stuck-loop detectors and contextual overflow preemptive alerts	Enabled by default

Environment Variables

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

Variable	Description
PLANE_BASE_URL	The base URL of the Plane instance.
PLANE_WORKSPACE_SLUG	The workspace slug of the Plane workspace.
PLANE_API_KEY	The API key for authentication with Plane.
MCP_URL	The URL of the MCP server.
MODEL_ID	Default LLM model identifier (e.g. gpt-4o).
PROVIDER	The LLM provider (e.g. openai, anthropic).
ENABLE_WEB_UI	Set to True to enable the built-in Web UI.
ENABLE_OTEL	Set to True to enable OpenTelemetry telemetry.
AGENT_UTILITIES_TESTING	Set to True during testing to bypass production setups.
AUTH_TYPE	The authentication type to use (e.g., jwt, none).
DEFAULT_API_KEY	Default API key for fast server fallback authentication.
OTEL_EXPORTER_OTLP_ENDPOINT	The OpenTelemetry OTLP endpoint.
PROJECTSTOOL	Set to True/False to toggle the Projects tool module.
WORK_ITEMSTOOL	Set to True/False to toggle the Work Items tool module.
CYCLESTOOL	Set to True/False to toggle the Cycles tool module.
EPICSTOOL	Set to True/False to toggle the Epics tool module.
MILESTONESTOOL	Set to True/False to toggle the Milestones tool module.
MODULESTOOL	Set to True/False to toggle the Modules tool module.
STATESTOOL	Set to True/False to toggle the States tool module.
USERSTOOL	Set to True/False to toggle the Users tool module.
WORKSPACESTOOL	Set to True/False to toggle the Workspaces tool module.
INITIATIVESTOOL	Set to True/False to toggle the Initiatives tool module.
INTAKETOOL	Set to True/False to toggle the Intake tool module.
LABELSTOOL	Set to True/False to toggle the Labels tool module.
PAGESTOOL	Set to True/False to toggle the Pages tool module.

---

Installation

Pick the extra that matches what you want to run:

Extra	Installs	Use when
plane-agent[mcp]	Slim MCP server only (agent-utilities[mcp] — FastMCP/FastAPI)	You only run the MCP server (smallest install / image)
plane-agent[agent]	Full agent runtime (agent-utilities[agent,logfire] — Pydantic AI + the epistemic-graph engine)	You run the integrated agent
plane-agent[all]	Everything (mcp + agent + logfire)	Development / both surfaces

# MCP server only (recommended for tool hosting — slim deps)
uv pip install "plane-agent[mcp]"

# Full agent runtime (Pydantic AI + epistemic-graph engine)
uv pip install "plane-agent[agent]"

# Everything (development)
uv pip install "plane-agent[all]"      # or: python -m pip install "plane-agent[all]"

Container images (:mcp vs :agent)

One multi-stage docker/Dockerfile builds two right-sized images, selected by --target:

Image tag	Build target	Contents	Entrypoint
knucklessg1/plane-agent:mcp	--target mcp	plane-agent[mcp] — slim, no engine/pydantic-ai/dspy/llama-index/tree-sitter	plane-mcp
knucklessg1/plane-agent:latest	--target agent (default)	plane-agent[agent] — full agent runtime + epistemic-graph engine	plane-agent

docker build --target mcp   -t knucklessg1/plane-agent:mcp    docker/   # slim MCP server
docker build --target agent -t knucklessg1/plane-agent:latest docker/   # full agent

docker/mcp.compose.yml runs the slim :mcp server; docker/agent.compose.yml runs the agent (:latest) with a co-located :mcp sidecar.

Knowledge-graph database (epistemic-graph)

The full agent ([agent] / :latest) embeds the epistemic-graph engine (pulled in transitively via agent-utilities[agent]). For production — or to share one knowledge graph across multiple agents — run epistemic-graph as its own database container and point the agent at it instead of embedding it. Deployment recipes (single-node + Raft HA), connection config, and the full database architecture (with diagrams) are documented in the epistemic-graph deployment guide. The slim [mcp] server does not require the database.

---

Documentation

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

Page	Contents
Installation	pip, source, uv, prebuilt Docker image
Deployment	run the MCP server and agent, Compose, Caddy + Technitium, env config
Usage	the MCP tools, the Api client, the CLI
Backing Platform	deploy a self-hosted Plane instance with Docker
Overview	ecosystem role, enterprise posture, architecture
Concepts	concept registry (CONCEPT:PLANE-*)

---

Repository Owners

---

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

Deploy with agent-os-genesis

This package can be provisioned for you — skill-guided — by the agent-os-genesis universal skill (its single-package deploy mode): it picks your install method, seeds secrets to OpenBao/Vault (or .env), trusts your enterprise CA, registers the MCP server, and verifies it — the same machinery that stands up the whole Agent OS, narrowed to just this package. Ask your agent to "deploy plane-agent with agent-os-genesis".

Install mode	Command
Bare-metal, prod (PyPI)	uvx plane-mcp · or uv tool install plane-agent
Bare-metal, dev (editable)	uv pip install -e ".[all]" · or pip install -e ".[all]"
Container, prod	deploy knucklessg1/plane-agent:latest via docker-compose / swarm / podman / podman-compose / kubernetes
Container, dev (editable)	deploy docker/compose.dev.yml (source-mounted at /src; edits live on restart)

Secrets are read-existing + seeded via vault_sync — you are only prompted for what's missing.