Skip to main content

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

Project description

LeanIX Agent - A2A | AG-UI | MCP

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: 0.8.0

Overview

LeanIX Agent MCP Server + A2A Agent

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

This repository is actively maintained - Contributions are welcome!

Features

Core Capabilities

  • FactSheet Management: Create, read, update FactSheets (Applications, Components, etc.)
  • GraphQL Queries: Execute flexible GraphQL queries with variables and operations
  • Metrics & KPIs: Access custom metrics, KPIs, and performance data
  • Discovery Integration: SaaS, SAP, and AI agent discovery services
  • Architecture Relations: Query FactSheet relationships and hierarchies
  • User & Workspace Management: Manage users, permissions, and workspace settings
  • Authentication: Automatic OAuth token management and session handling

API Coverage

The agent provides access to 30+ LeanIX API services with 500+ methods:

  • Pathfinder API: FactSheet operations, relations, and resource models
  • Metrics API: Schema management, KPI tracking, and data points
  • MTM API: Account management, workspace administration, and OAuth
  • Discovery APIs: SaaS, SAP, and AI agent discovery
  • Integration APIs: Collibra, ServiceNow, and Signavio connectors
  • Support APIs: Documents, impacts, navigation, polls, and webhooks

MCP

Using as an MCP Server

The MCP Server can be run in two modes: stdio (for local testing) or http (for networked access).

Environment Variables

  • LEANIX_WORKSPACE: The URL of the target service.
  • LEANIX_API_TOKEN: The API token or access token.

Run in stdio mode (default):

export LEANIX_WORKSPACE="http://localhost:8080"
export LEANIX_API_TOKEN="your_token"
leanix-mcp --transport "stdio"

Run in HTTP mode:

export LEANIX_WORKSPACE="http://localhost:8080"
export LEANIX_API_TOKEN="your_token"
leanix-mcp --transport "http" --host "0.0.0.0" --port "8000"

A2A Agent

Run A2A Server

export LEANIX_WORKSPACE="http://localhost:8080"
export LEANIX_API_TOKEN="your_token"
leanix-agent --provider openai --model-id gpt-4o --api-key sk-...

Docker

Build

docker build -t leanix-agent .

Run MCP Server

docker run -d \
  --name leanix-agent \
  -p 8000:8000 \
  -e TRANSPORT=http \
  -e LEANIX_WORKSPACE="http://your-service:8080" \
  -e LEANIX_API_TOKEN="your_token" \
  knucklessg1/leanix-agent:latest

Deploy with Docker Compose

services:
  leanix-agent:
    image: knucklessg1/leanix-agent:latest
    environment:
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=http
      - LEANIX_WORKSPACE=http://your-service:8080
      - LEANIX_API_TOKEN=your_token
    ports:
      - 8000:8000

Configure mcp.json for AI Integration (e.g. Claude Desktop)

{
  "mcpServers": {
    "leanix": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "leanix-agent",
        "leanix-mcp"
      ],
      "env": {
        "LEANIX_WORKSPACE": "http://your-service:8080",
        "LEANIX_API_TOKEN": "your_token"
      }
    }
  }
}

Install Python Package

python -m pip install leanix-agent
uv pip install leanix-agent

Repository Owners

GitHub followers GitHub User's stars

Graph Architecture

This agent uses pydantic-graph orchestration for intelligent routing and optimal context management.

---
title: LeanIX Agent Graph Agent
---
stateDiagram-v2
  [*] --> RouterNode: User Query
  RouterNode --> DomainNode: Classified Domain
  RouterNode --> [*]: Low confidence / Error
  DomainNode --> [*]: Domain Result
  • RouterNode: A fast, lightweight LLM (e.g., nvidia/nemotron-3-super) that classifies the user's query into one of the specialized domains.
  • DomainNode: The executor node. For the selected domain, it dynamically sets environment variables to temporarily enable ONLY the tools relevant to that domain, creating a highly focused sub-agent (e.g., gpt-4o) to complete the request. This preserves LLM context and prevents tool hallucination.

MCP Configuration Examples

1. Standard IO (stdio) Deployment

{
  "mcpServers": {
    "leanix-agent": {
      "command": "uv",
      "args": [
        "run",
        "leanix-mcp"
      ],
      "env": {
        "AGENT_DESCRIPTION": "<YOUR_AGENT_DESCRIPTION>",
        "AGENT_SYSTEM_PROMPT": "<YOUR_AGENT_SYSTEM_PROMPT>",
        "DEFAULT_AGENT_NAME": "<YOUR_DEFAULT_AGENT_NAME>",
        "GRAPHQLTOOL": "True",
        "LEANIX_AGENT_VERIFY": "<YOUR_LEANIX_AGENT_VERIFY>",
        "LEANIX_AI_INVENTORY_BUILDERTOOL": "True",
        "LEANIX_API_TOKEN": "<YOUR_LEANIX_API_TOKEN>",
        "LEANIX_APPTIO_CONNECTORTOOL": "True",
        "LEANIX_AUTOMATIONSTOOL": "True",
        "LEANIX_DISCOVERY_AI_AGENTSTOOL": "True",
        "LEANIX_DISCOVERY_LINKING_V1TOOL": "True",
        "LEANIX_DISCOVERY_LINKING_V2TOOL": "True",
        "LEANIX_DISCOVERY_SAASTOOL": "True",
        "LEANIX_DISCOVERY_SAPTOOL": "True",
        "LEANIX_DISCOVERY_SAP_EXTENSIONTOOL": "True",
        "LEANIX_DOCUMENTSTOOL": "True",
        "LEANIX_IMPACTSTOOL": "True",
        "LEANIX_INTEGRATION_APITOOL": "True",
        "LEANIX_INTEGRATION_COLLIBRATOOL": "True",
        "LEANIX_INTEGRATION_SERVICENOWTOOL": "True",
        "LEANIX_INTEGRATION_SIGNAVIOTOOL": "True",
        "LEANIX_INVENTORY_DATA_QUALITYTOOL": "True",
        "LEANIX_MANAGED_CODE_EXECUTIONTOOL": "True",
        "LEANIX_METRICSTOOL": "True",
        "LEANIX_MTMTOOL": "True",
        "LEANIX_NAVIGATIONTOOL": "True",
        "LEANIX_PATHFINDERTOOL": "True",
        "LEANIX_POLLTOOL": "True",
        "LEANIX_REFERENCE_DATATOOL": "True",
        "LEANIX_REFERENCE_DATA_CATALOGTOOL": "True",
        "LEANIX_STORAGETOOL": "True",
        "LEANIX_SURVEYTOOL": "True",
        "LEANIX_SYNCLOGTOOL": "True",
        "LEANIX_TECHNOLOGY_DISCOVERYTOOL": "True",
        "LEANIX_TODOTOOL": "True",
        "LEANIX_TOKEN": "<YOUR_LEANIX_TOKEN>",
        "LEANIX_TRANSFORMATIONSTOOL": "True",
        "LEANIX_URL": "<YOUR_LEANIX_URL>",
        "LEANIX_VERIFY": "<YOUR_LEANIX_VERIFY>",
        "LEANIX_WEBHOOKSTOOL": "True",
        "LEANIX_WORKSPACE": "<YOUR_LEANIX_WORKSPACE>",
        "SSL_VERIFY": "<YOUR_SSL_VERIFY>"
      }
    }
  }
}

2. Streamable HTTP (SSE) Deployment

{
  "mcpServers": {
    "leanix-agent": {
      "command": "uv",
      "args": [
        "run",
        "leanix-mcp",
        "--transport",
        "http",
        "--host",
        "0.0.0.0",
        "--port",
        "8000"
      ],
      "env": {
        "AGENT_DESCRIPTION": "<YOUR_AGENT_DESCRIPTION>",
        "AGENT_SYSTEM_PROMPT": "<YOUR_AGENT_SYSTEM_PROMPT>",
        "DEFAULT_AGENT_NAME": "<YOUR_DEFAULT_AGENT_NAME>",
        "GRAPHQLTOOL": "True",
        "LEANIX_AGENT_VERIFY": "<YOUR_LEANIX_AGENT_VERIFY>",
        "LEANIX_AI_INVENTORY_BUILDERTOOL": "True",
        "LEANIX_API_TOKEN": "<YOUR_LEANIX_API_TOKEN>",
        "LEANIX_APPTIO_CONNECTORTOOL": "True",
        "LEANIX_AUTOMATIONSTOOL": "True",
        "LEANIX_DISCOVERY_AI_AGENTSTOOL": "True",
        "LEANIX_DISCOVERY_LINKING_V1TOOL": "True",
        "LEANIX_DISCOVERY_LINKING_V2TOOL": "True",
        "LEANIX_DISCOVERY_SAASTOOL": "True",
        "LEANIX_DISCOVERY_SAPTOOL": "True",
        "LEANIX_DISCOVERY_SAP_EXTENSIONTOOL": "True",
        "LEANIX_DOCUMENTSTOOL": "True",
        "LEANIX_IMPACTSTOOL": "True",
        "LEANIX_INTEGRATION_APITOOL": "True",
        "LEANIX_INTEGRATION_COLLIBRATOOL": "True",
        "LEANIX_INTEGRATION_SERVICENOWTOOL": "True",
        "LEANIX_INTEGRATION_SIGNAVIOTOOL": "True",
        "LEANIX_INVENTORY_DATA_QUALITYTOOL": "True",
        "LEANIX_MANAGED_CODE_EXECUTIONTOOL": "True",
        "LEANIX_METRICSTOOL": "True",
        "LEANIX_MTMTOOL": "True",
        "LEANIX_NAVIGATIONTOOL": "True",
        "LEANIX_PATHFINDERTOOL": "True",
        "LEANIX_POLLTOOL": "True",
        "LEANIX_REFERENCE_DATATOOL": "True",
        "LEANIX_REFERENCE_DATA_CATALOGTOOL": "True",
        "LEANIX_STORAGETOOL": "True",
        "LEANIX_SURVEYTOOL": "True",
        "LEANIX_SYNCLOGTOOL": "True",
        "LEANIX_TECHNOLOGY_DISCOVERYTOOL": "True",
        "LEANIX_TODOTOOL": "True",
        "LEANIX_TOKEN": "<YOUR_LEANIX_TOKEN>",
        "LEANIX_TRANSFORMATIONSTOOL": "True",
        "LEANIX_URL": "<YOUR_LEANIX_URL>",
        "LEANIX_VERIFY": "<YOUR_LEANIX_VERIFY>",
        "LEANIX_WEBHOOKSTOOL": "True",
        "LEANIX_WORKSPACE": "<YOUR_LEANIX_WORKSPACE>",
        "SSL_VERIFY": "<YOUR_SSL_VERIFY>"
      }
    }
  }
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

leanix_agent-0.8.0.tar.gz (64.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

leanix_agent-0.8.0-py3-none-any.whl (101.3 kB view details)

Uploaded Python 3

File details

Details for the file leanix_agent-0.8.0.tar.gz.

File metadata

  • Download URL: leanix_agent-0.8.0.tar.gz
  • Upload date:
  • Size: 64.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for leanix_agent-0.8.0.tar.gz
Algorithm Hash digest
SHA256 c9680ecc0de3ddd911916500997f7b5a4f62118dc368e9ef267a67b892e38591
MD5 32a70d16b505af282e3593aec024a290
BLAKE2b-256 c6f88622027c3078c53510b2a64b75e7995f8555e87cf107ca7dfabf3c704f5a

See more details on using hashes here.

File details

Details for the file leanix_agent-0.8.0-py3-none-any.whl.

File metadata

  • Download URL: leanix_agent-0.8.0-py3-none-any.whl
  • Upload date:
  • Size: 101.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for leanix_agent-0.8.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6450f6e7cac904712e3f47fd5314999373ee298a0837619507a9499cc5bed222
MD5 f97c9575bb83ebb1849a042bd98d79a7
BLAKE2b-256 ac69435463ec8ccaf59122c5d12eb78f6385564b7ba1bc4d7cffb2c6d296efa5

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page