Bring Semantic Layer
to LlamaIndex
Learn how to connect Cube.dev to LlamaIndex and start using 15 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Cube.dev MCP Server?
Connect your Cube.dev instance to any AI agent to bridge the gap between natural language and your data warehouse. This server allows your agent to interact with Cube's semantic layer, ensuring consistent metrics and high-performance data retrieval.
What you can do
- Data Querying — Execute complex REST API queries using
load_queryto fetch aggregated data with measures, dimensions, and filters. - SQL Inspection — Use
get_sqlandexecute_cube_sqlto debug or run raw queries against the SQL API for deep data investigation. - Metadata Exploration — Retrieve cube definitions, views, and segments via
get_metato understand your data model without leaving the chat. - Performance Management — Trigger and monitor background pre-aggregation builds with
trigger_pre_aggregation_jobto ensure your dashboards stay fast. - Cloud Management — List deployments and environments if using Cube Cloud to manage your infrastructure context.
How it works
- Subscribe to this server
- Provide your Cube API URL and Secret Token
- Start asking questions about your data metrics and model structure
Who is this for?
- Data Engineers — quickly verify data models and trigger cache refreshes via CLI or AI interface.
- Analytics Engineers — debug generated SQL and inspect metadata to ensure metric consistency.
- Product Managers — get instant answers to data questions by letting the AI query the semantic layer directly.
Built-in capabilities (15)
Check if Cube deployment is live
Check if Cube deployment is ready
Convert a SQL query to a REST API query format
Execute a raw SQL query against the SQL API
Requires CUBE_CLOUD_API_KEY. Generate a JWT for the Metadata API
Get detailed metadata for a specific entity
Get metadata for cubes and views
Get status of pre-aggregation jobs
Useful for debugging. Get generated SQL for a Cube query
List configured data sources
Requires CUBE_CLOUD_API_KEY. List all Cube Cloud deployments
List all cubes and views
Requires CUBE_CLOUD_API_KEY. List environments for a deployment
Use this to get aggregated data. Execute a Cube query and return results
Trigger a pre-aggregation build job
Why LlamaIndex?
LlamaIndex agents combine Cube.dev tool responses with indexed documents for comprehensive, grounded answers. Connect 15 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
- —
Data-first architecture: LlamaIndex agents combine Cube.dev tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain Cube.dev tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query Cube.dev, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what Cube.dev tools were called, what data was returned, and how it influenced the final answer
Cube.dev in LlamaIndex
Cube.dev and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Cube.dev to LlamaIndex through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Cube.dev in LlamaIndex
The Cube.dev MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 15 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LlamaIndex only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Cube.dev for LlamaIndex
Every tool call from LlamaIndex to the Cube.dev MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I see the exact SQL that Cube generates for a specific query?
Yes. You can use the get_sql tool. By providing the query JSON, the agent will return the generated SQL string, which is perfect for debugging or verifying your data logic.
How do I refresh the data cache or pre-aggregations using the AI?
You can use the trigger_pre_aggregation_job tool. You can specify which cubes or data sources to target, and the agent will initiate the background build process for you.
Is it possible to explore the available measures and dimensions?
Absolutely. Use the get_meta tool to fetch all metadata. This allows the AI to understand what data is available to be queried, including views and segments.
How does LlamaIndex connect to MCP servers?
Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.
Can I combine MCP tools with vector stores?
Yes. LlamaIndex agents can query Cube.dev tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.
Does LlamaIndex support async MCP calls?
Yes. LlamaIndex's async agent framework supports concurrent MCP tool calls for high-throughput data processing pipelines.
BasicMCPClient not found
Install: pip install llama-index-tools-mcp
Explore More MCP Servers
View all →
UK ONS Discovery — Search 337+ Statistical Datasets
6 toolsExplore the full ONS dataset catalog: search 337+ datasets by keyword, browse metadata and dimensions, discover available filter options, and query any dataset with flexible parameters covering every aspect of UK statistics.
AbstractAPI
10 toolsEquip your AI agent with AbstractAPI's data enrichment — validate emails, geolocate IPs, check phone numbers, and enrich company data.
Import.io (Web Data Extraction)
10 toolsExtract structured data from any website via Import.io — run extractors, manage bulk crawls, and monitor API usage.
Cloudflare Tunnel
17 toolsManage Cloudflare Tunnels directly from your AI agent — list, create, and configure secure Zero Trust connections to your private infrastructure.