AgensGraph data-modeling MCP server (validate models, generate ingest/constraint Cypher, Arrows/Mermaid).
Listed on its own since 2026-09-26. Until then it was part of mcp-agensgraph-common, where its earlier checks remain.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-agensgraph-data-modeling","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# 🔍📊 AgensGraph Data Modeling MCP Server ## 🌟 Overview A Model Context Protocol (MCP) server implementation that provides tools for creating, visualizing, and managing AgensGraph graph data models. This server enables you to define nodes, relationships, and properties to design graph database schemas that can be visualized interactively. ## 🧩 Features - **Data Model Creation**: Define nodes, relationships, and properties - **Validation Tools**: Ensure structural integrity of data models - **Visualization**: Generate Mermaid diagrams for model visualization - **Arrows.app Integration**: Import/export models from Arrows visual editor - **Cypher Generation**: Create ingest queries and constraint queries - **Example Models**: 7 pre-built real-world data models **No database connection.** Nothing here reads or writes a graph — the server takes a model as JSON, answers about it, and hands back Cypher for somebody else to run. That somebody is usually the cypher server's write tool, in the same conversation. ## 🔧 Installation ```bash uvx mcp-agensgraph-data-modeling # Or from source git clone https://github.com/skaiworldwide-oss/agensgraph-ai.git cd agensgraph-ai/mcp-agensgraph/servers/mcp-agensgraph-data-modeling uv sync ``` Add it to your `claude_desktop_config.json`: ```json "mcpServers": { "agensgraph-data-modeling": { "command": "uvx", "args": [ "mcp-agensgraph-data-modeling" ] } } ``` CLI flags: `--transport` (`stdio`, `http`, `sse`; default `stdio`), `--server-host`, `--server-port`, `--server-path`, `--allow-origins`, `--allowed-hosts`, `--namespace`. Each has an environment variable — `AGENSGRAPH_TRANSPORT`, `AGENSGRAPH_MCP_SERVER_HOST` / `_PORT` / `_PATH`, `AGENSGRAPH_MCP_SERVER_ALLOW_ORIGINS` / `_ALLOWED_HOSTS`, `AGENSGRAPH_NAMESPACE`. `--namespace myapp` prefixes every tool name (`myapp-validate_node`), so several servers can be reached from one client. ## 📖 Usage ### 🛠️ Tools A model is a plain JSON object: `{"nodes": [...], "…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.