{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_xj8ykgf9v7m8","handle":"siemens-graph-studio-mcp-server","url":"https://wellknown.network/agents/siemens-graph-studio-mcp-server","links":{"self":"https://wellknown.network/agents/siemens-graph-studio-mcp-server/record.json","html":"https://wellknown.network/agents/siemens-graph-studio-mcp-server","markdown":"https://wellknown.network/agents/siemens-graph-studio-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/siemens-graph-studio-mcp-server","status":"https://wellknown.network/api/v1/agents/siemens-graph-studio-mcp-server/status","claim":"https://wellknown.network/agents/siemens-graph-studio-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/siemens-graph-studio-mcp-server/claim.json","badge":"https://wellknown.network/agents/siemens-graph-studio-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/siemens-graph-studio-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/siemens-graph-studio-mcp-server/tools"},"ard":{"identifier":"urn:air::server:siemens-graph-studio-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"siemens-graph-studio-mcp-server","summary":"An MCP server for Altair Graph Studio (AGS) providing intelligent SPARQL query capabilities via the Model Context Protocol.","description":"# RMGS MCP Server\n\nAn MCP (Model Context Protocol) server for **Altair Graph Studio (AGS)** that provides intelligent SPARQL query capabilities, ontology management, and graphmart construction tools — all accessible from AI coding assistants like GitHub Copilot, Claude Code, and other MCP-compatible clients.\n\n## Features\n\n- **SPARQL Query Execution** — Run SPARQL queries against AGS graphmarts\n- **Knowledge Discovery** — Explore ontologies, classes, and properties\n- **Ontology Management** — Create, modify, and delete ontologies\n- **Graphmart Construction** — Build and manage transformation layers and steps\n- **Agent Memory** — Persistent and ephemeral memory for context retention\n- **Dual Modes** — `explore` (read-only, 13 tools) and `create` (all 51 tools)\n- **Multiple Transports** — stdio, SSE, and streamable-http\n\n## Installation\n\n```bash\npip install siemens-graph-studio-mcp-server\n```\n\n### Default setup (recommended)\n\nUse this as the baseline setup when installing from PyPI.\n\n1. Create a Python virtual environment:\n\n```bash\npython -m venv graph_mcp_env\n```\n\n2. Activate the environment:\n\n```bash\nsource /.../howtomcp/graph_mcp_env/bin/activate\n```\n\n3. Install from PyPI:\n\n```bash\npip install siemens-graph-studio-mcp-server\n```\n\n4. Start MCP as two separate servers (recommended):\n\n```bash\nsiemens-graph-studio-mcp-server --config ags-config.json --mode explore --transport sse --port 8000\nsiemens-graph-studio-mcp-server --config ags-config.json --mode create --transport sse --port 8001\n```\n\n> **Note:** This also installs `rdflib`, which adds `rdfpipe` and `rdfgraphisomorphism` executables to your environment. These are standard rdflib CLI utilities and can be safely ignored.\n\n### From Source\n\n```bash\ngit clone <repository-url>\ncd rmgs-mcp-server\npip install -e .\n```\n\n---\n\n## Quick Start\n\n### 1. Create a config file\n\nSave this as `ags-config.json` (e.g., in your home directory or project):\n\n```json\n{\n  \"servers\": {\n    \"my-server\": {\n      \"host\": \"your-ags-server.ex…","publisher":{"name":"Boris Shalumov","url":null},"homepage":null,"repository":null,"version":"0.6.3","license":null,"protocols":["mcp"],"tags":["ags","altair-graph-studio","graphmart","knowledge-graph","mcp","sparql"],"pricing":null,"endpoints":[{"url":"pypi:siemens-graph-studio-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"}],"categories":["dev","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"siemens-graph-studio-mcp-server","registry":"pypi","observedAt":"2026-10-28T22:24:33.822Z","publishedAt":"2026-05-30T20:59:34.602727Z","latestVersion":"0.6.3"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"siemens-graph-studio-mcp-server","url":"https://pypi.org/project/siemens-graph-studio-mcp-server/","firstSeenAt":"2026-09-10T12:22:03.039Z","fetchedAt":"2026-10-28T22:23:22.791Z","normalizedAt":"2026-10-28T22:23:22.791Z"}]},"firstSeenAt":"2026-09-10T12:22:03.039Z","updatedAt":"2026-10-28T22:24:33.822Z"}