LocalFree

agentl MCP server

arimayuji/agentl

Validate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs.

Source code Website

Install agentl in Claude Code

Claude Code
claude mcp add agentl -- uvx agentl-etl
mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)
{
  "mcpServers": {
    "agentl": {
      "command": "uvx",
      "args": [
        "agentl-etl"
      ]
    }
  }
}

Frequently asked questions

What does the agentl MCP server do?

Validate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs.

Is the agentl MCP server free?

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Does agentl run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add agentl to Claude Code?

Run: claude mcp add agentl -- uvx agentl-etl

More ai agents & coding agents MCP servers

View all

Agentpay

sdeanesh-png/agentpay

Spending controls for AI agents: per-agent budgets, vendor allowlists, full audit trail.

LocalAccount needed

Agentic Target Evidence

0

athril/agentic-target-evidence

Read-only biomedical evidence tools for drug-target validation: DepMap, gnomAD, OpenTargets, PubMed…

LocalFree

AgentPool

0

sidduHERE/agentpool

See each coding-agent subscription's live limits and offload work to one with headroom.

LocalPaid service

AgentGuard

MerchantGuard/agentguard-mcp

Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.

LocalFree

AgentPump

0

pact-layer/agentpump-mcp

Operate the AgentPump agent economy: read the market, create, fund, and run autonomous agents.

LocalFree

agentfenster

0

clemensjl/agentfenster-mcp

Windows GUI automation on a hidden second desktop, driven from Claude Code over MCP.

LocalFree