aris-mcp

Software AG ARIS REST API + MCP Server + A2A Server for Agentic AI.

aris-mcp connects the agent ecosystem to an ARIS tenant (ARIS Connect / ARIS Enterprise / ARIS Cloud). It is the inbound and outbound bridge for the agent-utilities Knowledge Graph's Camunda + ARIS ↔ KG integration:

• Inbound — the KG ARIS extractor (enrichment/extractors/aris.py) consumes this client to lift ARIS models + their EPC structure (functions → BusinessTask, rule operators → gateways, events collapsed, connections → FLOWS_TO) into the canonical ArchiMate ontology, where they reconcile with Camunda/Egeria via ALIGNED_WITH and are reasoned over in OWL/RDF.

• Outbound — the KG process-intelligence writeback (enrichment/process_writeback.py) uses set_model_attributes to write a kg_intelligence attribute back onto ARIS models (gated by ARIS_ENABLE_WRITE).

Available MCP Tools

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

2 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.

Writes require ARIS_ENABLE_WRITE=True.

Related MCP server: Modal MCP Server

Environment Variables

Every variable the server reads, grouped by concern.

Connection & Credentials

Tenant differences. ARIS deployments vary (Connect ABS portal vs the public ARIS API; on-prem vs Cloud). The defaults follow the common ARIS Connect ABS REST layout. If your tenant's paths differ, set ARIS_PATHS_JSON, e.g. {"models":"v2/repository/models","model_objects":"v2/models/{model_id}/objects"}.

MCP server / transport

Tool toggles

The action-routed tools can be disabled via their toggle env var (set to false): ARISTOOL (see the Available MCP Tools table above).

Telemetry & governance

Agent CLI (full [agent] runtime only)

Installation

Install the slim [mcp] extra. Install aris-mcp[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.

Pick the extra that matches what you want to run:

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

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

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

Container images (:mcp vs :agent)

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

docker build --target mcp   -t knucklessg1/aris-mcp:mcp    docker/   # slim MCP server
docker build --target agent -t knucklessg1/aris-mcp: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.

Run

aris-mcp                       # stdio (default)
aris-mcp --transport streamable-http --host 0.0.0.0 --port 8000

Deployment

1. stdio — uv run aris-mcp (see mcp_config.json).

2. streamable-http — aris-mcp --transport streamable-http --port 8000.

3. local container — build from docker/ and run with the env above.

4. remote — point your client at http://aris-mcp.arpa/mcp.

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 aris-mcp with agent-os-genesis".

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