GraphRAG

MCP tool from Orionbelt Analytics by ralforion

How to use it

GraphRAG is exposed by the Orionbelt Analytics MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the GraphRAG tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Orionbelt Analytics

$claude mcp add orionbelt-analytics http://localhost:9000/mcp

FULL ORIONBELT ANALYTICS LISTING

Other tools in Orionbelt Analytics (26)

add_rdf_knowledge

Add custom metadata triples to the RDF store

apply_semantic_names

Apply LLM-suggested semantic names and descriptions to ontology

cleanup_workspace

Delete all workspace files for the current connection and start fresh

connect_database

Connect to any supported database using .env credentials

discover_schema

Analyze schema structure with automatic GraphRAG + ontology generation

download_artifact

Download ontology or R2RML mapping as a Turtle file

execute_sql_query

Execute SQL with OBQC validation, security checks, and fan-trap detection

Generate Plotly charts (bar, line, scatter, heatmap) with MCP-UI rendering

generate_ontology

Generate RDF/OWL ontology from schema with SQL mapping annotations

get_semantic_model

Retrieve a stored semantic model by name

get_table_details

Get detailed column, key, and constraint info for a specific table

graphrag_find_join_path

Discover join paths between tables via graph traversal

graphrag_query_context

Get optimized context for SQL generation (85-95% token reduction)

graphrag_search

Semantic search + schema overview (auto-initialized by discoverschema)

List available schemas in the connected database

list_semantic_models

List all stored semantic models for the current connection

load_my_ontology

Load a custom .ttl ontology file from an import folder

measurable_from

Measure-capable tables for an anchor grain (one-to-many closure)

plan_composite_query

Advise a fan-trap-safe Composite Fact Layer (UNION ALL) decomposition

Execute SPARQL queries (SELECT, ASK, CONSTRUCT — auto-detected)

Dimension-capable tables for an anchor grain (many-to-one closure)

Clear cached schema and ontology data for the current session

sample_table_data

Preview table data with row limit and injection protection

save_semantic_model

Save a semantic model (e.g., OBML YAML) to the workspace

store_ontology_in_rdf

Persist ontology in Oxigraph for SPARQL access

suggest_semantic_names

Detect abbreviations and cryptic names for business-friendly renaming