Orionbelt Analytics MCP Server

The Ontology-based MCP server for your Text-2-SQL convenience. OrionBelt Analytics is an MCP server that analyzes relational database schemas and generates RDF/OWL ontologies with embedded SQL mappings. It provides relationship-aware Text-to-SQL with automatic fan-trap prevention, GraphRAG for intelligent schema discovery, and interactive charting -- all accessible through any MCP-compatible AI client. Its 27 documented tools cover semantic, graphrag, ontology, table.

People connecting database tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-24 · ★ 46 · #37 OF 151 MAINTAINED DATABASE · VERIFIED 2026-08-25

NOASSERTION · Python servers · how we verify → /methodology

01 · Install Orionbelt Analytics

Claude Code

claude mcp add ralfbecher-orionbelt-analytics -- uvx orionbelt-analytics

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "ralfbecher-orionbelt-analytics": {
      "command": "uvx",
      "args": [
        "orionbelt-analytics"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license no standard license detected - usage rights unclear; check the repo before commercial use

pypi package orionbelt-analytics - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.ralfbecher is GitHub-verified and matches the repo owner

03 · What Orionbelt Analytics can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can connect to any supported database using .env credentials, list available schemas in the connected database, analyze schema structure with automatic GraphRAG + ontology generation, and get detailed column, key, and constraint info for a specific table.

Capability map

Tools grouped from the project's README - what Orionbelt Analytics lets an agent do.

Semantic

5 tools - e.g. Detect abbreviations and cryptic names for business-friendly renaming; Apply LLM-suggested semantic names and descriptions to ontology; Save a semantic model (e.g., OBML YAML) to the workspace

suggest_semantic_names · apply_semantic_names · save_semantic_model · get_semantic_model · list_semantic_models

Graphrag

4 tools - e.g. Semantic search + schema overview (auto-initialized by discover_schema); Get optimized context for SQL generation (85-95% token reduction); Discover join paths between tables via graph traversal

graphrag_search · graphrag_query_context · graphrag_find_join_path · GraphRAG

read & search

3 tools - e.g. List available schemas in the connected database; Get detailed column, key, and constraint info for a specific table; Execute SPARQL queries (SELECT, ASK, CONSTRUCT - auto-detected)

list_schemas · get_table_details · query_sparql

Generate

2 tools - e.g. Generate RDF/OWL ontology from schema with SQL mapping annotations; Generate Plotly charts (bar, line, scatter, heatmap) with MCP-UI rendering

generate_ontology · generate_chart

Connect

1 tool - e.g. Connect to any supported database using .env credentials

connect_database

Reset

1 tool - e.g. Clear cached schema and ontology data for the current session

reset_cache

Discover

1 tool - e.g. Analyze schema structure with automatic GraphRAG + ontology generation

discover_schema

Cleanup

1 tool - e.g. Delete all workspace files for the current connection and start fresh

cleanup_workspace

Latest releases

v2.0.0 · 2026-08-08

Database views become first-class, and the ontology learns which columns can actually be aggregated. Both change what execute_sql_query accepts, hence the major version. Tool surface unchanged at 28 tools. · Also fixes…

v1.8.0 · 2026-08-05

Feature release centred on OBQC correctness and GraphRAG schema search. Tool surface grows 26 → 28 (add_semantic_context, cleanup_old_versions). · A detected fan-trap now fails the query. execute_sql_query returns…

v1.7.2 · 2026-07-15

Bug-fix release. No MCP tool surface changes (still 26 tools, same signatures). · Why this matters · pyproject.toml uses unbounded dependency floors, so the lockfile governs this repo and the Docker image - not PyPI…

04 · Who maintains Orionbelt Analytics

orionbelt-analytics is maintained by ralfbecher. We track 2 MCP servers from ralfbecher - 2 actively maintained, 120 combined GitHub stars, oldest repo from Feb 2026. Full record: all servers from ralfbecher.

orionbelt-semantic-layer API-first semantic layer MCP server compiling YAML models into dialect-specific SQL ★ 74

05 · Facts

repository: github.com/ralfbecher/orionbelt-analytics
category: database - ranked #37 of 151 actively-maintained database servers as of 2026-08-25.
release cadence: 9 releases in the last 90 days (latest 2026-08-08)
registry: io.github.ralfbecher/orionbelt-analytics (active, first published 2026-02-19)
packages: pypi:orionbelt-analytics

06 · Orionbelt Analytics FAQ

Is Orionbelt Analytics still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-24 and it shipped 9 releases in the last 90 days. We re-verify nightly.

What can Orionbelt Analytics do?

How do I install Orionbelt Analytics?

Run `uvx orionbelt-analytics`. You can also paste the ready-made client config above.

Does Orionbelt Analytics run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Orionbelt Analytics

Alternatives to Orionbelt Analytics

Maintained database servers if Orionbelt Analytics isn't the fit.

Pairs well with

Servers that cover what Orionbelt Analytics doesn't - only shown when the pairing reason fits the companion.

More database MCP servers · Orionbelt Semantic Layer · SQL Benchmarks Lab · Custom MCP Database · Health Bridge for AI · RTFM

More Python MCP servers · Neuro Stack · Misata · Zotero Library MCP · SharePoint MCP Server · see all