aris-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ARIS_TOKEN | No | Static bearer token | |
| ARIS_TENANT | No | ARIS tenant identifier | |
| ARIS_API_BASE | No | ARIS REST base URL (tenant API root) | http://localhost/abs/api |
| ARIS_PASSWORD | No | Basic auth password | |
| ARIS_USERNAME | No | Basic auth username | |
| ARIS_CLIENT_ID | No | OAuth2 client ID | |
| ARIS_OAUTH_URL | No | OAuth2 token URL | |
| ARIS_SSL_VERIFY | No | Verify TLS | True |
| ARIS_ENABLE_WRITE | No | Allow attribute writes | False |
| ARIS_CLIENT_SECRET | No | OAuth2 client secret |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| aris_ingest_modelsB | Natively ingest ARIS models into epistemic-graph as typed nodes. Lists via the real ARIS client and pushes typed OWL nodes + links through the
fast engine client. Best-effort: returns |
| aris_ingest_model_exportB | Store a raw ARIS model export (bytes) as a content-addressed KG blob. The export bytes are supplied base64-encoded (rendered/exported out-of-band by
the caller), stored via |
| aris_get_modelB | Get a single model's metadata (including its attributes). |
| aris_list_model_attributesB | Get a model's attributes (used for writeback idempotency read-back). |
| aris_list_model_connectionsB | List the directed control-flow connections between a model's objects. |
| aris_list_model_objectsB | List the EPC objects (functions/events/rule operators) of a model. |
| aris_list_modelsB | List models in the tenant/database (process + architecture). |
| aris_set_model_attributesC | Write/update attributes on a model (e.g. the |
| aris_set_object_attributesC | Write/update attributes on a single object. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| connector-status | Ask for this connector server's current operational status. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| _connector_status_resource | Native resource exposing this server's static status payload. |
| ontology://aris-mcp/aris.ttl | |
| connector-resources | Data sources, ontology mappings and resources of this connector. |
| aris-process-modeling/SKILL.md | Read Software AG ARIS process models over the aris-mcp MCP server — list the model inventory, fetch one model's metadata/attributes, and read its EPC objects (functions/events/rule operators) and directed control-flow connections. Use when the agent must inventory ARIS models, open one model by GUID, or inspect a model's EPC structure. Do NOT use for ingesting models into the knowledge graph (use aris-kg-ingestion) or for control-flow / bottleneck analysis of a whole repository (use aris-process-mining). |
| aris-process-modeling/_manifest | File listing for aris-process-modeling |
| aris-process-mining/SKILL.md | Analyze the control flow of Software AG ARIS EPC models over the aris-mcp MCP server — trace event→function→event paths, find splits/joins at rule operators, spot disconnected or dead-end objects, and reason about a model's structure. Use when the agent must explain how a process flows, validate an EPC's connectedness, or compare paths through a model. Do NOT use to merely list/read models (use aris-process-modeling) or to ingest them into the knowledge graph (use aris-kg-ingestion). |
| aris-process-mining/_manifest | File listing for aris-process-mining |
| aris-kg-ingestion/SKILL.md | Natively ingest Software AG ARIS process models into the epistemic-graph knowledge graph over the aris-mcp MCP server — push models as typed :ProcessModel nodes, a single model's EPC objects as :EPCFunction/:EPCEvent/ :EPCRule with :flowsTo control-flow edges, and raw model exports as content-addressed :ModelExport (:MediaAsset) blobs. Use when the agent must mirror ARIS content into the KG for cross-source querying. Do NOT use to merely read models (use aris-process-modeling) or to analyze a single model's flow in place (use aris-process-mining). |
| aris-kg-ingestion/_manifest | File listing for aris-kg-ingestion |
| aris-mcp-development/SKILL.md | Develop and maintain the Software AG ARIS connector while preserving its Connector boundary, REST client contract, authentication policy, KG source declarations, package contents, and release evidence. |
| aris-mcp-development/_manifest | File listing for aris-mcp-development |
TDQS
Scored across 9 tools
Most tools target distinct resource+action pairs (list models, list objects, list connections, set attributes), so selection is generally clear. However, aris_get_model (metadata including attributes) overlaps meaningfully with aris_list_model_attributes, and the two ingest tools (ingest_models vs ingest_model_export) require reading descriptions to distinguish bulk ingestion from blob storage.
All tools use a consistent snake_case aris_ prefix followed by verb_noun patterns (aris_list_models, aris_get_model, aris_set_model_attributes). The convention is predictable throughout, with only minor stylistic variance in the longer ingest names.
Nine tools is well-scoped for an ARIS-to-KG bridge: reads, writes, and ingestion paths each have a clear purpose. No tool appears redundant enough to remove, and nothing feels thin.
The surface covers listing models, inspecting metadata/attributes/objects/connections, writing model and object attributes, and both bulk and blob ingestion. Minor gaps exist: no get_object or object-level create/delete, no model delete, and no tenant/database listing, but core ingestion and writeback workflows are covered.