Google PageRank for AI agents. 25,000+ tools indexed.

Best MCP Servers for Data Processing in 2026

109 tools indexed · avg score 72.4 · sorted by AgentRank score

The AgentRank index tracks 109 data processing tools. The top-ranked entry is kubeflow/mcp-apache-spark-history-server at 83.9 points. Across the 10 shown here, the average AgentRank score is 72.4, and 9 had a commit in the last 30 days. The most common primary language is Python.

Data processing MCP servers and tools connect AI agents to data pipeline infrastructure: Apache Kafka streams, Spark clusters, dbt models, Airflow DAGs, and ETL workflows. These tools enable a new class of AI-assisted data engineering where agents can monitor, debug, and even modify data pipelines in response to natural language instructions.

Beyond traditional data engineering tools, this category includes document processing utilities (PDF extraction, OCR, format conversion) and data transformation tools that let agents reshape structured data between formats. These are the plumbing that makes AI-powered analytics workflows possible.

Data processing tools often require careful permissioning — an agent with write access to a production Kafka topic or dbt project can cause serious downstream damage. Look for tools with dry-run modes, explicit schema validation, and audit logging before granting write access in production environments.

Top 10 Data Processing MCP Servers

  1. #1
    kubeflow/mcp-apache-spark-history-server

    MCP Server and CLI for Apache Spark History Server. Debug Spark applications from AI agents, scripts, or the terminal.

    83.9
    Ranks here on 202 GitHub stars and a commit within the last week.
    Freshness
    30.8
    Issue health
    20.9
    Stars
    11.8
    Contributors
    11.5
    License
    4.6
    ★ 202 commit 2d ago Python
  2. #2
    Extelligence-ai/bagel

    Query robotics, drone, and IoT data in plain English through an MCP server, with an intelligent edge data reduction pipeline that keeps only the data that matters.

    78.8
    Ranks here on 397 GitHub stars and a commit within the last week.
    Freshness
    25.6
    Issue health
    16.2
    Stars
    11.1
    Downloads
    8.9
    Contributors
    8.1
    ★ 397 commit today Python
  3. #3
    pragunbhutani/dbt-llm-agent

    LLM based AI Agent to automate Data Analysis for dbt projects with remote MCP server

    76.6
    Ranks here on an active commit 20 days ago and 71% of issues closed.
    Freshness
    26.1
    Issue health
    22.0
    Stars
    11.6
    Contributors
    7.9
    License
    4.6
    ★ 180 commit 19d ago Python
  4. #4
    dbt-labs/dbt-mcp

    A MCP (Model Context Protocol) server for interacting with dbt.

    76.3
    Ranks here on adopted by 3 downstream projects and 608 GitHub stars, plus a commit within the last week.
    Freshness
    20.0
    Issue health
    13.6
    Downloads
    13.0
    Stars
    9.3
    Contributors
    8.0
    ★ 608 commit today Python 3 dependents
  5. #5
    drt-hub/drt

    Reverse ETL for the code-first data stack

    74.8
    Ranks here on a commit within the last week and 91% of issues closed.
    Freshness
    25.6
    Issue health
    23.3
    Contributors
    10.3
    Stars
    6.5
    Downloads
    3.8
    ★ 32 commit 3d ago Python
  6. #6
    liam-machine/erd-studio

    Visual ERD designer for dbt — design your data warehouse on a canvas, in your repo, where your AI assistant can read it. Free and open source.

    74.8
    Ranks here on a commit within the last week and 75% of issues closed.
    Freshness
    30.8
    Issue health
    23.1
    Stars
    11.2
    Contributors
    4.4
    Description
    4.3
    ★ 154 commit today TypeScript
  7. #7
    redbase-app/redb-route

    Apache Camel-style integration framework for .NET. 30+ EIP patterns, 29 transports (Kafka, RabbitMQ, MQTT, S3, gRPC, SFTP, SQL...), fluent C# DSL.

    67.7
    Ranks here on a commit within the last week.
    Freshness
    30.8
    Issue health
    15.4
    Stars
    8.2
    License
    4.6
    Contributors
    4.4
    ★ 38 commit today C#
  8. #8
    Zipstack/unstract

    LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

    65.4
    Ranks here on adopted by 12 downstream projects and 7.3k GitHub stars, plus a commit within the last week.
    Freshness
    20.0
    Dependents
    12.2
    Stars
    10.0
    Contributors
    8.0
    Issue health
    6.1
    ★ 7.3k commit today Python 12 dependents
  9. #9
    tooluse-labs/wpa-mcp

    C# MCP server exposing Windows ETW (.etl) trace analyzers — CPU, scheduler waits, image loads, file/disk/mmap/network I/O, memory resources, CLR runtime — over Claude Code, Codex, and other MCP cli...

    64.2
    Ranks here on an active commit 49 days ago and 94% of issues closed.
    Issue health
    29.1
    Freshness
    15.0
    Stars
    6.4
    Description
    6.2
    License
    4.6
    ★ 17 commit 1mo ago C#
  10. #10
    nijosmsft/etw-mcp

    MCP server for analyzing Windows ETW (.etl) traces — xperf / native ETW / .NET sidecar + WPR & pktmon capture authoring

    61.2
    Ranks here on an active commit 14 days ago.
    Freshness
    28.2
    Issue health
    12.3
    Contributors
    6.5
    Stars
    5.1
    License
    4.6
    ★ 9 commit 14d ago Python

More Data Processing MCP Servers

# Tool Score Stars Last Commit Language
11 confluentinc/quickstart-streaming-agents 56.4 90 1mo ago Python
12 hermes-labs-ai/csv-quality-gate 55.1 1 today Python
13 k3nn3dy-ai/Dataset-genie 55.1 1 7d ago Python
14 jbdrak/ssb-for-agents 54.2 2 3d ago JavaScript
15 JohnnyQ-commits/aqueduct-data-agent 54.2 2 1d ago Python
16 07prajwal2000/streamer 53.5 2 14d ago TypeScript
17 malkreide/swiss-housing-mcp 53.3 1 1d ago Python
18 vgossiaux/dataform-context-mcp 53.3 1 4d ago Python
19 datenwissenschaften/agentic-data-analyst 53.3 1 3d ago Python
20 nic01asFr/QgisRemoteMCP 52.7 11 1d ago Python
21 CharlieDigital/runjs 52.1 31 1y ago C#
22 EF08/andy2_crawler 51.4 1 3d ago TypeScript
23 c-cf/BI-Chart-MCP-Server 50.2 13 1y ago Python
24 dragonejt/iceberg-mcp-data 49.0 1 1d ago Jupyter Notebook
25 OpenDQV/OpenDQV 48.2 12 4d ago Python
26 DasClown/drug-pipeline-mcp 48.2 5 10d ago HTML
27 armalite/data-product-hub 47.8 9 11mo ago Python
28 iamsocool24/dbt-core-mcp 47.7 4 today Python
29 puxti-labs/puxti 47.4 3 5d ago Python
30 yangkyeongmo/mcp-server-apache-airflow 47.4 178 6mo ago Python
31 abhishekbhakat/airflow-mcp-server 47.1 33 11mo ago Python
32 yadneshSalvi/datahub-repair-agent 46.8 3 9d ago Python
33 lensesio/agentic-engineering-for-apache-kafka 46.8 59 1mo ago Python
34 wklee610/kafka-mcp 45.4 13 1mo ago Python
35 NiclasOlofsson/dbt-anvil-vscode 45.0 1 9d ago TypeScript