Data AgentsBLOCK
Data Agents are intelligent assistants built by data engineers to help non-data professionals navigate the organization’s data infrastructu
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
https://github.com/user-attachments/assets/f591bc23-3a19-43eb-9c92-e4b5bb3ba57f
💬 Data Agents, Really! Data Agent is an agentic AI harnessing GenAI to automate and streamline data engineering workflows. By delivering complete, well-prepared data requests, it saves time and reduces bottlenecks across teams.
✨ Features
- 🤖 Multi-agent collaboration - Engage with specialized data engineering agents
- 🔄 Multiple backend support - Connect to OpenAI, Claude, Gemini or Ollama for private deployments
- 🔗 n8n integration - Use n8n workflows for agent orchestration
- 🎯 Strategy-based approach - Different strategies for various data engineering tasks
- 🌙 Modern dark UI - Beautiful, responsive interface inspired by LobeChat
- 🚀 Docker ready - Easy deployment with Docker Compose
🚀 Quick Start
The fastest way to get started is using Docker Compose:
# Clone the repository git clone https://github.com/HotTechStack/dataagents.git cd dataagents # Start the application docker-compose up -d
🔧 Setup Steps
- Once the containers are running, go to n8n at http://localhost:5678
- Upload the workflow from the
agents/n8n/conversationsdirectory - Configure your API keys:
- In Docker Compose: update OpenAI/Claude/Gemini key
- In n8n workflow: click on OpenAI/Claude/Gemini model block and add your key
- See n8n documentation for more details
- Visit http://localhost:3000 and start interacting with your age
ad1c5088f268OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add data-engineering-agents --env NEXTAUTH_SECRET=${NEXTAUTH_SECRET} --env NEXTAUTH_URL=${NEXTAUTH_URL} --env NEXT_PUBLIC_AGENT_API_KEY=${NEXT_PUBLIC_AGENT_API_KEY} --env NEXT_PUBLIC_ANTHROPIC_API_KEY=${NEXT_PUBLIC_ANTHROPIC_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"data-engineering-agents": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"NEXTAUTH_SECRET": "${NEXTAUTH_SECRET}",
"NEXTAUTH_URL": "${NEXTAUTH_URL}",
"NEXT_PUBLIC_AGENT_API_KEY": "${NEXT_PUBLIC_AGENT_API_KEY}",
"NEXT_PUBLIC_ANTHROPIC_API_KEY": "${NEXT_PUBLIC_ANTHROPIC_API_KEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Collaborative | read | Agents work together to generate a comprehensive solution |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (7)
DATABASE_URL="postgresql://postgres:postgres@localhost:5432/data_agents_db"
DATABASE_URL: "postgresql://postgres:postgres@db:5432/data_agents_db"
console.log('Validating Gemini API key, exists:', !!apiKey);console.log('Gemini API key exists:', !!apiKey);{message.agentAvatar || "👨💼"}avatar: "👨💻",
@prisma/client, @radix-ui/react-avatar, @radix-ui/react-dialog, @radix-ui/react-dropdown-menu, @radix-ui/react-hover-card, @radix-ui/react-icons, @radix-ui/react-label, @radix-ui/react-radio-group
Gates applied: no_behavioural_pass.
ad1c5088f268full audit observations/trust-audit/mcp-server/hottechstack__data-agents.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | ad1c5088f268 | BLOCK | D | 69 | first audit |
Questions
What is the Data Agents MCP server?
Data Agents are intelligent assistants built by data engineers to help non-data professionals navigate the organization’s data infrastructu
What tools does Data Agents expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Data Agents safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Data Agents need?
It reads NEXTAUTH_SECRET, NEXTAUTH_URL, NEXT_PUBLIC_AGENT_API_KEY, NEXT_PUBLIC_ANTHROPIC_API_KEY, NEXT_PUBLIC_AZURE_OPENAI_API_KEY, NEXT_PUBLIC_GEMINI_API_KEY and NEXT_PUBLIC_OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (ad1c5088f268), read on 2026-10-09. The repository is watched and re-audited when it changes.