Skip to content
Agentmart
Submit a tool

AI agent tools for data pipelines

In this catalog, a data pipelines tool is one that moves and transforms data between systems (ETL/ELT, warehouses, streams). Our enrichment pass tags 60 listings with it: 17 MCP servers, 30 agent skills, 4 plugins, 4 agent frameworks and 5 AI agents. By listing rank, the top MCP server is Jitsu, the top agent skill is ai-pipeline-orchestration and the top AI agent is marvis-risk-agent. 6 of the 60 are published by the vendor behind the product, and 48 were active in the last 30 days. 4 of the 17 MCP servers run only as remote servers, with nothing to install locally. Each entry below links to its listing page, with grades, install commands and sources.

Updated Oct 26, 2026 · Built from catalog data; how we rank and grade

What the job is

Tagged listings
60
By type
17 MCP servers, 30 agent skills, 4 plugins, 4 agent frameworks and 5 AI agents
Published by the vendor
6 of 60
Active in the last 30 days
48 of 60
Open source
49 of 60
MCP servers that run only remotely
4 of 17
Hosts named by the MCP servers
Claude Code (15), Cursor (15), VS Code (15)

Building blocks by type

The top entries of each type, by listing rank. Open a listing for its install command, grades and sources.

MCP servers 17 tagged

  1. 1
    Jitsu

    jitsu.comOfficial

    Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.

    • Published by the vendor
    • 5.1K GitHub stars
    • Remote server, no local install

    ★ 5.1KLast active Oct 23, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  2. 2
    walkerOS Flow

    walkeros.ioOfficial

    Build, validate, simulate, and deploy walkerOS event pipelines

    • Published by the vendor
    • Active in the last 30 days
    • Open source (MIT)

    ★ 347Last active Oct 22, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  3. 3
    OpenMetadata

    open-metadata

    Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

    • Most GitHub stars here (15,567)
    • Remote server, no local install
    • Active in the last 30 days

    ★ 15.6KLast active Oct 22, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  4. 4
    Marmot Data Catalog

    marmotdata

    Open-source data catalog.

    • Remote server, no local install
    • Active in the last 30 days
    • Open source (MIT)

    ★ 623Last active Oct 23, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  5. 5
    Sling CLI

    slingdata.io

    Sling CLI MCP server for querying any database, running data pipelines and managing replications

    • Most weekly downloads here (52.3K)
    • Active in the last 30 days

    ↓ 52.3K/wkLast active Sep 28, 2025Local (stdio)Claude Code, Codex, VS Code, Cursor +2

Search MCP servers for data pipelines → All connectors

Agent skills 30 tagged

  1. 1
    ai-pipeline-orchestration

    devops-skills

    Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.

    • Largest repository here (48,428 stars)
    • Active in the last 30 days
    • Open source (MIT)

    ★ 48.4KLast active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6

  2. 2
    cdf-auto-labeling

    NVIDIA <opensource@nvidia.com>

    Use when a user needs to get started with CDF Auto-Labeling, plan a scenario, run or debug a shipped cookbook, author prompts or cookbooks, migrate a…

    • Repository has 3.7K stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 3.7KLast active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6

  3. 3
    basin

    cloudflareOfficial

    Build and troubleshoot Cloudflare Basin analytics workflows with Basin Pipelines, Basin Catalog, and Basin SQL.

    • Published by the vendor
    • Repository has 3.2K stars
    • Active in the last 30 days

    ★ 3.2KLast active Oct 1, 2026Claude Code, Claude apps, Codex, Cursor +6

  4. 4
    i4h-workflow-dataset-convert

    Isaac for Healthcare Team <isaac-for-healthcare-support@nvidia.com>

    Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection.

    • Repository has 3.7K stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 3.7KLast active Sep 30, 2026Claude Code, Claude apps, Codex, Cursor +6

  5. 5
    bom

    aklofas

    BOM (Bill of Materials) management for electronics projects — the workflow skill that coordinates DigiKey, Mouser, LCSC, element14, JLCPCB, PCBWay, and KiCad…

    • Repository has 1.5K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 1.5KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

Search agent skills for data pipelines → All skills

Plugins 4 tagged

  1. 1
    Power User for dbt

    Altimate Inc.

    Makes VS Code work seamlessly with dbt core and dbt cloud: auto-complete, preview, column lineage, AI docs generation, health checks, cost estimation etc

    • Most GitHub stars here (586)
    • Active in the last 30 days
    • Open source (MIT)

    ★ 586Last active Oct 23, 2026VS Code, Cursor, Windsurf, VSCodium

  2. 2
    Google Cloud Data Agent Kit

    googlecloudtools

    Bring the full power of Google Cloud Data Agent Kit to your IDE

    VS Code, Cursor, Windsurf, VSCodium

  3. 3
    TOON Tool Kit - Best tools to work with TOON format

    patricio0312rev

    Preview, convert, minify, prettify, validate, and analyze TOON files for LLM workflows.

    • Open source (MIT)

    ★ 3Last active Nov 16, 2025VS Code, Cursor, Windsurf, VSCodium

  4. 4
    DataFlint Copilot

    DataFlint

    End of life on October 31, 2026: connect your AI agent to DataFlint's MCP directly at https://mcp.dataflint.io/mcp.

    VS Code, Cursor, Windsurf, VSCodium

Search plugins for data pipelines → All plugins

Agent frameworks 4 tagged

  1. 1
    datachain

    datachain-ai

    Python library that turns files in S3, GCS and Azure into versioned, typed datasets for pipelines and agents.

    • 2.8K GitHub stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 2.8K↓ 4.5K/wkLast active Oct 23, 2026

  2. 2
    Marvin

    Prefect

    Python framework for structured LLM outputs and agentic workflows built from tasks, agents and threads.

    • Most GitHub stars here (6,207)
    • Most weekly downloads here (61.8K)
    • Open source (Apache-2.0)

    ★ 6.2K↓ 61.8K/wkLast active Sep 23, 2026

  3. 3
    CGraph

    ChunelFeng

    Cross-platform C++ DAG framework with a Python version, for running task graphs with no third-party dependencies.

    • 2.3K GitHub stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 2.3K↓ 118/wkLast active Oct 24, 2026

  4. 4
    Adala

    HumanSignal

    Python framework for data labeling agents that learn skills from a ground-truth dataset through iterative feedback.

    • 1.6K GitHub stars
    • Open source (Apache-2.0)
    • For Python

    ★ 1.6K↓ 13/wkLast active Sep 3, 2026

Search agent frameworks for data pipelines → All harnesses & sdks

AI agents 5 tagged

  1. 1
    marvis-risk-agent

    eddyzzl

    Local-first credit-risk agent that turns data files into governed analysis, models, strategy code and audit-ready reports.

    • Most GitHub stars here (390)
    • Active in the last 30 days
    • Open source (MIT)

    ★ 390Last active Oct 12, 2026

  2. 2
    Senzing Entity Resolution

    Senzing, Inc.

    Senzing entity resolution finds, deduplicates, links, and resolves person and organization records within and across data sources — building an…

  3. 3
    Taskpush

    Taskpush

    Agent-to-agent marketplace for machine-checked work, mainly data enrichment: send records and the fields to add, and a provider's delivery is checked (row…

  4. 4
    MCP Data Converter

    mcp-converter.tnkng.com

    Converts data between 72+ format pairs: JSON, CSV, XML, YAML, TOML, HTML tables, Markdown tables, Properties, and TSV.

  5. 5
    GISGP

    GISGP

    Hosted geospatial tool server for AI agents: coordinate conversion, format conversion (GeoJSON/Shapefile/KML/GPX/DXF/CSV), open-data discovery, terrain, land…

Search AI agents for data pipelines → All agents

Questions

What are the top tools for data pipelines?
By listing rank, the top MCP server is Jitsu, the top agent skill is ai-pipeline-orchestration and the top AI agent is marvis-risk-agent. Rank weighs adoption, freshness, documentation and publisher identity; money never changes it.
How many tools does the catalog list for data pipelines?
60 listings are tagged for it: 17 MCP servers, 30 agent skills, 4 plugins, 4 agent frameworks and 5 AI agents. Tags come from an automated enrichment pass over the top-ranked listings, so tools outside that pass are not counted.
Which AI apps do the MCP servers work with?
Of the 17 MCP servers, 15 list Claude Code, 15 list Cursor and 15 list VS Code as a supported host. Open a listing for its install command and the other hosts it names.
Which of these are published by the vendor itself?
6 of the 60 are published by the vendor behind the product, including basin, Jitsu and k2.

60 listings are tagged for this use case; the lists above show the top entries.

Related