Route HugeGraph MCP operational checks to status, schema, MCP read-only state, AI availability, and read-only verification tools. Use when the user asks to check the current graph, schema, MCP connection, readonly state, HugeGraph-AI state, counts, indexes, or readiness.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
| Goal | Tool |
|---|---|
| Quick check connection, status, MCP read-only state | inspect_graph_tool(include_raw_schema=false) |
| Fetch vertex/edge counts | inspect_graph_tool(include_counts=true) |
| Inspect full schema, primary keys, indexes, edge endpoints | inspect_graph_tool(include_raw_schema=true) |
| Check readonly, graph, or graphspace | inspect_graph_tool(include_raw_schema=false) |
| Verify whether graph data exists | query_graph_data_tool (bounded page or exact ID query) |
| Get schema context before query | inspect_graph_tool(include_raw_schema=true) |
| Check schema before import | inspect_graph_tool(include_raw_schema=true) |
| Check schema before schema design | inspect_graph_tool(include_raw_schema=true) |
| Check AI generation readiness | inspect_graph_tool(include_raw_schema=false), then optionally generate_gremlin_tool(query, execute=false) |
inspect_graph_tool reports hugegraph_ai_status, but does not expose the
HUGEGRAPH_MCP_ALLOW_AI or HUGEGRAPH_MCP_ADMIN_MODE configuration values.
Check those environment variables in the server process when diagnosing a
disabled AI call or an admin-gated tool.
Status check: inspect_graph_tool
Schema audit: inspect_graph_tool(include_raw_schema=true)
Data verification: inspect_graph_tool(include_counts=true) -> query_graph_data_tool
When AI is disabled by configuration, hugegraph_ai_status="disabled" is normal; no AI service check is needed. unavailable means an enabled AI service check failed.
Structured query and plan lifecycle tools require the default core toolset. For a legacy deployment, enable HUGEGRAPH_MCP_TOOLSET=core and restart before using them.
These skills describe current source. Published 1.7.1 uses v2_core / v1; see the migration guide.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Route HugeGraph MCP graph data extraction and controlled import/delete tasks to stable public tools. Use when the user asks to extract graph data from text, import structured vertices or edges, verify an import, or asks whether table, SQL, update, or delete graph writes are available.
The English summary is being prepared. Showing the original description.
Route HugeGraph MCP structured graph query tasks to stable read-only tools. Use when the user asks graph questions, asks to generate Gremlin, provides Gremlin to explain, or needs read-only graph exploration.
The English summary is being prepared. Showing the original description.
Route HugeGraph MCP regression testing tasks to the current public tool surface, including inspection, read-only queries, Gremlin generation, extraction, controlled import, schema validate/dry-run, safety guards, and admin-gated tool checks.
The English summary is being prepared. Showing the original description.
Route HugeGraph MCP schema design, validation, and dry-run preview tasks to stable public tools. Use when the user asks to design vertex labels, edge labels, properties, primary keys, indexes, or preview schema operations.
The English summary is being prepared. Showing the original description.