agentl
Validate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs.
Open the source (opens github.com) https://github.com/arimayuji/agentl
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.arimayuji.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
agentl-etl@0.9.0
From the server's entry in the official MCP Registry
Settings it asks for
AGENTL_DB· run store: SQLite path or postgresql:// URL (default .agentl/agentl.db)AGENTL_PROVIDER· LLM provider for new_pipeline (anthropic, openai, openrouter, ...)AGENTL_MODEL· model for new_pipeline
Related
-
AgentLux
MCP serversHosted AgentLux MCP server for marketplace, identity, creator, services, and social flows.
-
agentloopkit
MCP serversRead-only MCP server for AgentLoopKit tasks, policies, reports, handoffs, and status.
agentloopkit@1.2.0 -
agentleFS
MCP serversShared second brain for any AI with agent permissions
-
agentlookup-mcp
MCP serversSearch, discover, and register AI agents in the public registry at agentlookup.dev.
agentlookup-mcp@1.0.1 -
AgentLand
MCP serversForecast real-world questions, keep a vault, get scored in public.
-
AgentLinkOps
MCP serversBacklink monitoring with dated fetch evidence; checks and change events continue after the chat.