mdx-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mdx-mcp what were total sales in 2023?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mdx-mcp
An open-source, verified natural-language → MDX MCP server for OLAP cubes.
Ask an OLAP/SSAS multidimensional cube questions in plain English and get back a verified answer — the number, the MDX that produced it, and an honest abstain/clarify when the query is ambiguous. Cross-platform (XMLA), provider-agnostic (Claude by default), and MCP-native.
question ──▶ introspect the cube ──▶ generate k candidate MDX ──▶ execute (read-only)
──▶ self-consistency verify ──▶ { status, value, mdx, agreement }Why it's different
Verified, not vibes. It runs k diverse candidate queries and only answers when they agree; on divergence it abstains or asks to clarify instead of guessing a number.
Works on any cube. Cube-schema introspection auto-grounds generation — no per-cube hand-authoring.
Read-only by construction. Only
SELECT/WITHMDX ever executes.Open-core. Three clean seams (
LLMClient,MdxExecutor,Verifier) let you plug in a private trust layer without forking. SeeARCHITECTURE.md.
Related MCP server: @mob999/cube_mcp
Install
pip install mdx-mcp[claude] # engine + Claude reference providerThe XMLA executor and cube introspection use only the Python standard library.
Configure (env)
export MDX_MCP_ENDPOINT="http://your-ssas-host/olap/msmdpump.dll" # XMLA endpoint
export MDX_MCP_CATALOG="YourDatabase"
export MDX_MCP_CUBE="Your Cube"
export MDX_MCP_USER="user" # optional (basic auth)
export MDX_MCP_PASSWORD_FILE="/run/secrets/olap_pw" # or MDX_MCP_PASSWORD
export ANTHROPIC_API_KEY="sk-..." # for the default Claude producerRun
mdx-mcp # starts the MCP server (stdio)Tools
Tool | Purpose |
| the cube's grounding block (measures / dimensions / hierarchies) |
| NL question → |
| execute a provided MDX query (read-only) |
| explain an MDX query in plain language |
Ships a Cube-Analyst persona (persona/) and Claude skills
(skills/) that drive the flow.
Bring your own provider / backend
Implement LLMClient (any model), MdxExecutor (e.g. a Windows ADOMD backend), or Verifier
(e.g. a calibrated trust gate) and inject it — the engine is unchanged.
License
Apache-2.0. No vendor lock-in, no client data.
Available Tools
4 toolsmdx_askA
Answer a natural-language question with a verified MDX result.
Introspects the cube, generates k candidate MDX queries, executes them read-only, and returns the self-consistency verdict: {status: answer|abstain|clarify, value, mdx, agreement, errors, ...}. Never guesses a number when candidates disagree or fail.
Inputs: question (required), k.
mdx_explainB
Explain a given MDX query in plain language (what it measures, slices, and returns).
Inputs: mdx (required). Returns: result
mdx_introspectA
Return the cube's 'skills' block: measures, dimensions, hierarchies for grounding.
Inputs: no named parameters. Returns: result
mdx_runB
Execute a provided MDX query (read-only; SELECT/WITH only) and return the cell value.
Inputs: mdx (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool serves a distinct function: answering questions, explaining queries, introspecting cube schema, and executing user-provided queries. No overlap in purpose.
All tools follow the consistent mdx_verb pattern with verbs (ask, explain, introspect, run) that clearly indicate their action.
Four tools is appropriate for the domain, covering the core interactions with an MDX cube without being excessive or insufficient.
The tool set provides a complete workflow: introspect to understand the cube, ask to get answers, explain to understand queries, and run to execute arbitrary MDX. No obvious gaps.
Related MCP Connectors
Ask questions in plain language, get answers from your business database. No SQL required.
Ask plain-English questions of your database: answers, the SQL that ran, and the rows.
Query your warehouse or a CSV with Claude/ChatGPT over MCP, governed by table-level ACL + audit.
Query, explore, and manage your databases through natural conversation.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceEnables natural language querying of Microsoft Fabric Data Warehouses with intelligent SQL generation, metadata exploration, and business-friendly result summarization. Features two-layer architecture with MCP-compliant server and agentic AI reasoning for production-ready enterprise data access.-
- AlicenseAqualityDmaintenanceProvides AI assistants with semantic layer visibility and multi-dimensional querying capabilities over Cube.js data.216 npm1MIT
- FlicenseNot gradedqualityDmaintenanceEnables natural language querying of SQL databases with robust safety guarantees including read-only enforcement, AST validation, and row caps.-
- AlicenseNot gradedqualityBmaintenanceEnables natural-language queries over data warehouses with catalog-grounded semantics and per-query authorization, returning answers with attached reasoning.Apache 2.0