leanix-agent 0.33.0

Agent package for communicating with LeanIX Enterprise Architecture Management via REST APIs and GraphQL.

Leanix Agent

CLI or API | MCP | Agent

Version: 0.33.0

Documentation — Installation, deployment, usage across the API, CLI, and MCP interfaces, and the authentication and dynamic-filtering guides 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
• Contribute

---

Overview

Leanix Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Agent package for communicating with LeanIX Enterprise Architecture Management via REST APIs and GraphQL..

---

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 Agent package for communicating with LeanIX Enterprise Architecture Management via REST APIs and GraphQL. 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

Auto-generated — do not edit between the markers below.

MCP Tool	Toggle Env Var	Description
leanix_discover_meta_model	LEANIX_PATHFINDERTOOL	Discover the custom LeanIX meta-model/data-model schema including custom attributes and fields in real-time.
leanix_graphql	GRAPHQLTOOL	Execute raw GraphQL queries and mutations natively on LeanIX Pathfinder API.
leanix_leanix_ai_inventory_builder	LEANIX_AI_INVENTORY_BUILDERTOOL	Manage leanix leanix ai inventory builder operations.
leanix_leanix_apptio_connector	LEANIX_APPTIO_CONNECTORTOOL	Manage leanix leanix apptio connector operations.
leanix_leanix_automations	LEANIX_AUTOMATIONSTOOL	Manage leanix leanix automations operations.
leanix_leanix_discovery_ai_agents	LEANIX_DISCOVERY_AI_AGENTSTOOL	Manage leanix leanix discovery ai agents operations.
leanix_leanix_discovery_linking_v1	LEANIX_DISCOVERY_LINKING_V1TOOL	Manage leanix leanix discovery linking v1 operations.
leanix_leanix_discovery_linking_v2	LEANIX_DISCOVERY_LINKING_V2TOOL	Manage leanix leanix discovery linking v2 operations.
leanix_leanix_discovery_saas	LEANIX_DISCOVERY_SAASTOOL	Manage leanix leanix discovery saas operations.
leanix_leanix_discovery_sap	LEANIX_DISCOVERY_SAPTOOL	Manage leanix leanix discovery sap operations.
leanix_leanix_discovery_sap_extension	LEANIX_DISCOVERY_SAP_EXTENSIONTOOL	Manage leanix leanix discovery sap extension operations.
leanix_leanix_documents	LEANIX_DOCUMENTSTOOL	Manage leanix leanix documents operations.
leanix_leanix_impacts	LEANIX_IMPACTSTOOL	Manage leanix leanix impacts operations.
leanix_leanix_integration_api	LEANIX_INTEGRATION_APITOOL	Manage leanix leanix integration api operations.
leanix_leanix_integration_collibra	LEANIX_INTEGRATION_COLLIBRATOOL	Manage leanix leanix integration collibra operations.
leanix_leanix_integration_servicenow	LEANIX_INTEGRATION_SERVICENOWTOOL	Manage leanix leanix integration servicenow operations.
leanix_leanix_integration_signavio	LEANIX_INTEGRATION_SIGNAVIOTOOL	Manage leanix leanix integration signavio operations.
leanix_leanix_inventory_data_quality	LEANIX_INVENTORY_DATA_QUALITYTOOL	Manage leanix leanix inventory data quality operations.
leanix_leanix_managed_code_execution	LEANIX_MANAGED_CODE_EXECUTIONTOOL	Manage leanix leanix managed code execution operations.
leanix_leanix_metrics	LEANIX_METRICSTOOL	Manage leanix leanix metrics operations.
leanix_leanix_mtm	LEANIX_MTMTOOL	Manage leanix leanix mtm operations.
leanix_leanix_navigation	LEANIX_NAVIGATIONTOOL	Manage leanix leanix navigation operations.
leanix_leanix_pathfinder	LEANIX_PATHFINDERTOOL	Manage leanix leanix pathfinder operations.
leanix_leanix_poll	LEANIX_POLLTOOL	Manage leanix leanix poll operations.
leanix_leanix_reference_data	LEANIX_REFERENCE_DATATOOL	Manage leanix leanix reference data operations.
leanix_leanix_reference_data_catalog	LEANIX_REFERENCE_DATA_CATALOGTOOL	Manage leanix leanix reference data catalog operations.
leanix_leanix_storage	LEANIX_STORAGETOOL	Manage leanix leanix storage operations.
leanix_leanix_survey	LEANIX_SURVEYTOOL	Manage leanix leanix survey operations.
leanix_leanix_synclog	LEANIX_SYNCLOGTOOL	Manage leanix leanix synclog operations.
leanix_leanix_technology_discovery	LEANIX_TECHNOLOGY_DISCOVERYTOOL	Manage leanix leanix technology discovery operations.
leanix_leanix_todo	LEANIX_TODOTOOL	Manage leanix leanix todo operations.
leanix_leanix_transformations	LEANIX_TRANSFORMATIONSTOOL	Manage leanix leanix transformations operations.
leanix_leanix_webhooks	LEANIX_WEBHOOKSTOOL	Manage leanix leanix webhooks operations.

33 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/mcp.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 leanix-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": {
    "leanix-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "leanix-agent[mcp]",
        "leanix-mcp"
      ],
      "env": {
        "LEANIX_WORKSPACE": "your_leanix_workspace_here",
        "LEANIX_API_TOKEN": "your_leanix_api_token_here",
        "SSL_VERIFY": "your_ssl_verify_here",
        "DEBUG": "your_debug_here",
        "PYTHONUNBUFFERED": "your_pythonunbuffered_here",
        "LEANIX_TOKEN": "your_leanix_token_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": {
    "leanix-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "leanix-agent[mcp]",
        "leanix-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "LEANIX_WORKSPACE": "your_leanix_workspace_here",
        "LEANIX_API_TOKEN": "your_leanix_api_token_here",
        "SSL_VERIFY": "your_ssl_verify_here",
        "DEBUG": "your_debug_here",
        "PYTHONUNBUFFERED": "your_pythonunbuffered_here",
        "LEANIX_TOKEN": "your_leanix_token_here"
      }
    }
  }
}

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

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

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name leanix-agent-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e LEANIX_WORKSPACE="your_value" \
  -e LEANIX_API_TOKEN="your_value" \
  -e SSL_VERIFY="your_value" \
  -e DEBUG="your_value" \
  -e PYTHONUNBUFFERED="your_value" \
  -e LEANIX_TOKEN="your_value" \
  knucklessg1/leanix-agent:mcp

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

---

Additional Deployment Options

leanix-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://leanix-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 LEANIX_WORKSPACE="your_value"
export LEANIX_API_TOKEN="your_value"
export SSL_VERIFY="your_value"
export DEBUG="your_value"
export PYTHONUNBUFFERED="your_value"
export LEANIX_TOKEN="your_value"

# Run the agent server
leanix-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:
  leanix-agent-mcp:
    image: knucklessg1/leanix-agent:mcp
    container_name: leanix-agent-mcp
    hostname: leanix-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"

  leanix-agent-agent:
    image: knucklessg1/leanix-agent:latest
    container_name: leanix-agent-agent
    hostname: leanix-agent-agent
    restart: always
    depends_on:
      - leanix-agent-mcp
    env_file:
      - ../.env
    command: [ "leanix-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9004
      - MCP_URL=http://leanix-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/agent.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

Every variable the server reads. Copy .env.example to .env and populate only what you use; blank connector credentials leave the corresponding surface inactive.

Connection & credentials

Variable	Description	Default
LEANIX_WORKSPACE	Base URL or specific workspace URL	https://app.leanix.net
LEANIX_AUTH_METHOD	Auth method: technical, browser, token, api_token	technical
LEANIX_TECHNICAL_USER	Technical user client id	—
LEANIX_TECHNICAL_USER_PASSWORD	Technical user password / secret	—
LEANIX_API_TOKEN	Static API token	—
LEANIX_TOKEN	Generic fallback token	—
LEANIX_BROWSER_LOGIN	Force browser interactive OAuth SSO fallback	False
SSL_VERIFY	Toggle standard SSL certificate verification	True
LEANIX_AGENT_VERIFY	Strict alternate agent validation switch	True

SSO / OAuth (SSO path)

Variable	Description	Default
LEANIX_OAUTH_CLIENT_ID	OAuth application client id	leanix-mcp
LEANIX_OAUTH_SCOPE	Standard OAuth scopes	openid offline_access
LEANIX_OAUTH_REDIRECT_PORT	Local port to receive the auth-code callback	56122

OIDC token delegation (RFC 8693)

Variable	Description	Default
AUDIENCE	Audience URI for delegation	https://app.leanix.net
DELEGATED_SCOPES	Requested scopes for token exchange	api

MCP server / transport

Variable	Description	Default
TRANSPORT	stdio, streamable-http, or sse	stdio
HOST	Bind host (HTTP transports)	0.0.0.0
PORT	Bind port (HTTP transports)	8000
MCP_TOOL_MODE	Tool surface: condensed, verbose, or both	condensed
DEBUG	Verbose logging	False
PYTHONUNBUFFERED	Unbuffered stdout (recommended in containers)	1

Agent identity (full [agent] runtime only)

Variable	Description	Default
DEFAULT_AGENT_NAME	Custom name for downstream LLMs	LeanIX Agent
DEFAULT_AGENT_DESCRIPTION	Custom agent description	Enterprise Architecture Agent
DEFAULT_AGENT_SYSTEM_PROMPT	Custom agent prompt template	—

Telemetry & governance

Variable	Description	Default
ENABLE_OTEL	Enable OpenTelemetry export	True
OTEL_EXPORTER_OTLP_ENDPOINT	OTLP collector endpoint	—
OTEL_EXPORTER_OTLP_PUBLIC_KEY / OTEL_EXPORTER_OTLP_SECRET_KEY	OTLP auth keys	—
OTEL_EXPORTER_OTLP_PROTOCOL	OTLP protocol (e.g. http/protobuf)	—
EUNOMIA_TYPE	Authorization mode: none, embedded, remote	none
EUNOMIA_POLICY_FILE	Embedded policy file	mcp_policies.json
EUNOMIA_REMOTE_URL	Remote Eunomia server URL	—

Tool toggles

Each action-routed tool can be disabled individually via its toggle env var (set to false). The full list is in the Available MCP Tools table above (e.g. LEANIX_DOCUMENTSTOOL, LEANIX_NAVIGATIONTOOL, GRAPHQLTOOL).

---

Installation

Pick the extra that matches what you want to run:

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

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

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

# Everything (development)
uv pip install "leanix-agent[all]"      # or: python -m pip install "leanix-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/leanix-agent:mcp	--target mcp	leanix-agent[mcp] — slim, no engine/pydantic-ai/dspy/llama-index/tree-sitter	leanix-mcp
knucklessg1/leanix-agent:latest	--target agent (default)	leanix-agent[agent] — full agent runtime + epistemic-graph engine	leanix-agent

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

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, extras, prebuilt Docker image
Deployment	run the MCP and agent servers, Compose, Caddy + Technitium, env config
Usage	the MCP tools, the LeanixApi and GraphQL clients, the CLI
Overview	the standardized agent-package pattern and concept registry
Introspection & Filtering	authentication modes and dynamic toolset filtering
Concepts	concept registry (CONCEPT:LIX-*)

---

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 leanix-agent with agent-os-genesis".

Install mode	Command
Bare-metal, prod (PyPI)	uvx leanix-mcp · or uv tool install leanix-agent
Bare-metal, dev (editable)	uv pip install -e ".[all]" · or pip install -e ".[all]"
Container, prod	deploy knucklessg1/leanix-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.