Best MCP Servers for Data & Analytics
Top-ranked MCP servers for data pipelines, analytics, ETL, and data processing. Scored from the AgentRank index.
Data and analytics MCP servers connect AI agents to data pipelines, transformation tools, and analytics platforms. They let agents query processed data, trigger pipeline runs, inspect data quality, and build automated data workflows.
This guide ranks the top data and analytics MCP servers from the AgentRank index — covering dbt, Apache Kafka, Airflow, Spark, Snowflake connectors, and general ETL tooling. These are the tools data engineers reach for when adding AI to their stack.
Top Data & Analytics MCP servers
Ranked by the composite AgentRank score — a weighted blend of stars (10%), freshness (20%), issue health (20%), contributors (8%), and inbound dependents (22%). Average score across these 8 tools: 95.9.
| # | Repository | Score | Stars | Lang | Updated |
|---|---|---|---|---|---|
| 1 | xberg-io/xberg Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, a… | 99.9 | 9.4k | Rust | 7d ago |
| 2 | arcjet/arcjet-js Runtime security for AI apps and agents: prompt injection detection, tool-call authorizati… | 98.1 | 692 | TypeScript | 12d ago |
| 3 | Syngnat/GoNavi High-performance multi-data-source database client — ~30MB, AI & MCP ready, zero Electron … | 97.9 | 2.1k | TypeScript | 7d ago |
| 4 | assafelovic/gpt-researcher An autonomous agent that conducts deep research on any data using any LLM providers | 97.4 | 30k | Python | 9d ago |
| 5 | mark3labs/mcp-go A Go implementation of the Model Context Protocol (MCP), enabling seamless integration bet… | 94.8 | 9.2k | Go | 11d ago |
| 6 | pawurb/hotpath-rs Rust profiler for CPU, memory, SQL, HTTP, and async performance, with Prometheus and Grafa… | 93.8 | 1.9k | Rust | 8d ago |
| 7 | receptron/mulmoclaude Nurture your own AI assistant on your own computer. Local-first and MIT: memories, data an… | 93.0 | 374 | TypeScript | 7d ago |
| 8 | OtterMind/Chat2DB Chat2DB is a free, cross-platform, local-first database client and SQL workspace for devel… | 92.1 | 28k | Java | 11d ago |
Choosing by use case
- dbt & data transformation
- Run dbt models, execute tests, and query compiled SQL from inside your agent.
- Data warehouses (Snowflake, BigQuery)
- Query data warehouses for BI-level aggregations, segmentations, and reporting.
- Streaming & event data (Kafka)
- Produce and consume Kafka events, inspect topic state, and manage consumer groups.
- Visualization & reporting
- Generate charts, trigger dashboard refreshes, and embed analytics outputs in agent workflows.
Quick setup
Most MCP servers follow the same config pattern. Add this to your Claude Desktop, Cursor, or Windsurf MCP config file:
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": ["dbt-mcp"]
}
}
}See the integrations page for platform-specific setup guides for Claude Code, Cursor, VS Code, Windsurf, and Cline.
Reading the AgentRank signals
Each tool in this guide is scored on the core signals that predict long-term reliability:
| Signal | Weight | What it means |
|---|---|---|
| Stars | 15% | Raw popularity — how many developers have found and bookmarked this tool |
| Freshness | 25% | Days since last commit — tools with no recent commits decay hard after 90 days |
| Issue health | 25% | Ratio of closed to total issues — measures maintainer responsiveness |
| Contributors | 10% | More contributors = less bus-factor risk, broader review surface |
| Dependents | 25% | How many other repos depend on this — the strongest signal of real-world adoption |
Query this live from your editor: Install AgentRank in Cursor, VS Code, or Claude Code — your AI agent can query live rankings on demand.
Missing a tool? Submit it to the index — new tools are scored in the next nightly crawl.
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.