AgentScout / By role / Data engineers

AI agents for data engineers (2026)

Database MCP servers, scrapers and workflow tools that help data engineers move, query and clean data with agents. We picked the top tools for 5 jobs data engineers do every day: 26 tools in all, 24 of them free or with a free tier.

Jump to: Databases · Data analysis · Scrape websites · Pipelines and workflows · Documents and RAG

Free tools from AgentScout for data engineers: AI API cost calculator · Token counter

How we picked: each section takes the tools matched to that task in our directory, putting tools whose category and stated use cases fit the task first, then ordering by tracked GitHub stars. No paid placements.

Databases

Database MCP servers, vector stores and text-to-SQL tools that let agents query, manage and store data in Postgres, MySQL, MongoDB and more. All 22 tools →

PrivateGPT Open source
Open-source API layer that turns local models into private AI applications, with RAG, tools, skills, MCP and text-to-SQL on any OpenAI-compatible server. · ★ 57,594
Chroma Open source + cloud
Open-source search and vector database widely used for agent memory and RAG. · ★ 29,512
Teable Open source + cloud
AI spreadsheet and database for business with built-in agents. · ★ 21,892
WrenAI Open source + cloud
Generative BI for agents: governed text-to-SQL with a semantic context layer. · ★ 17,881
MCP Toolbox for Databases Open source
Open-source MCP server from Google for connecting agents to databases. · ★ 16,669
InsForge Open source + cloud
Open-source backend platform that gives coding agents a database, auth and storage. · ★ 13,129

Data analysis

Agents that query, clean and chart data and explain what it shows. All 93 tools →

Graphify Open source
Turns a codebase plus its docs, SQL schemas, configs and PDFs into a knowledge graph that coding agents can query. · ★ 127,237
PrivateGPT Open source
Open-source API layer that turns local models into private AI applications, with RAG, tools, skills, MCP and text-to-SQL on any OpenAI-compatible server. · ★ 57,594
LlamaIndex Open source + cloud
Framework for agents over your data (RAG, document agents). · ★ 52,485
Kong Gateway Open source + cloud
Cloud-native API, LLM and MCP gateway that adds routing, auth, multi-LLM support, semantic security and MCP traffic analytics through plugins. · ★ 44,278
MindsHub Open source + cloud
MindsDB's agent workspace for research, analysis, documents and coding, with a model router, a scoped vault for connected data and swappable open-source agent harnesses. · ★ 39,800
ScrapeGraphAI Open source + cloud
Python library that uses LLMs and graph logic to build scraping pipelines: describe the data you want and it extracts it from websites or documents. · ★ 31,882

Scrape websites

Tools that turn websites into clean data or text an agent can use, from single pages to whole sites. All 15 tools →

Scrapling Open source
Python web-scraping framework with fast HTTP requests, stealth browsers, adaptive parsing and concurrent crawling, plus an MCP server for agents. · ★ 88,372
Crawl4AI Open source
Open-source crawler that turns websites into clean, LLM-ready Markdown for agents and RAG pipelines. · ★ 85,667
ScrapeGraphAI Open source + cloud
Python library that uses LLMs and graph logic to build scraping pipelines: describe the data you want and it extracts it from websites or documents. · ★ 31,882
Moli Open source
Lightweight Rust headless browser for AI agents that fetches pages, searches and extracts content, usable via CLI, CDP or WebDriver. · ★ 19,349
Apify MCP Server Open source + cloud
Apify's MCP server giving agents access to thousands of scrapers for social media, search and maps. · ★ 11,578
Wigolo Open source
Local-first web search, fetch and crawl for coding agents over MCP, with no API keys. · ★ 5,479

Pipelines and workflows

Platforms for chaining apps, triggers and AI steps into workflows that run on their own. All 157 tools →

Dify Source-available + cloud
Open-source platform for building LLM apps and agents visually. · ★ 158,410
Langflow Open source + cloud
Visual drag-and-drop builder for AI agents and workflows that you can run locally, deploy as an API or expose as an MCP server. · ★ 155,757
FastGPT Source-available + cloud
AI agent building platform with knowledge-base RAG, data processing and a visual workflow editor for deploying question-answering and automation apps. · ★ 29,851
Sim Studio Open source + cloud
Workspace for visually building, deploying and monitoring AI agents and workflows. · ★ 29,835
Activepieces Open source + cloud
Open-source automation platform with AI agents and hundreds of pieces usable as MCP servers. · ★ 25,073
Astron Agent Open source
iFlytek's enterprise agentic workflow platform for building super agents. · ★ 8,910

Documents and RAG

Tools that let agents read, search and answer questions over your documents and files. All 59 tools →

MarkItDown Open source
Microsoft's Python tool and MCP server that converts PDFs, Office documents, images, audio and web pages to Markdown for LLM and agent pipelines. · ★ 190,824
Graphify Open source
Turns a codebase plus its docs, SQL schemas, configs and PDFs into a knowledge graph that coding agents can query. · ★ 127,237
RAGFlow Open source + cloud
Open-source RAG engine with deep document parsing and agent features for building grounded question-answering over your files. · ★ 92,335
Crawl4AI Open source
Open-source crawler that turns websites into clean, LLM-ready Markdown for agents and RAG pipelines. · ★ 85,667
Headroom Open source
Library, proxy and MCP server that compresses tool outputs, logs, files and RAG chunks locally before they reach the LLM, cutting tokens for coding agents. · ★ 75,629
AnythingLLM Open source + cloud
Local-first desktop and server app for chatting with your documents, running agents and connecting any LLM. · ★ 67,210