New: the hosted MCP server is live. Connect your agent in one command.Read the docs →
registry / software / dlthub
dlt
dlt is an open-source Python library that loads data from various, often messy data sources into well-structured datasets. It provides lightweight Python interfaces to extract, load, inspect and transform the data. dltHub is a managed platform that enables any engineer to ship production data with agents doing the work on infrastructure they run, with every run logged and auditable.
59
DISCOVER100
UNDERSTAND23
ADOPT60
OPERATE53
OverviewGET /v1/profile/dlthub
Overall
59
Discover
100
Understand
23
Adopt
60
Operate
53
21/38 applicable signals pass. Open the Capabilities tab for the full signal breakdown, or Issues for the highest-impact gaps.
Agent compatibility
Claude Code✓ TESTED
Codex✓ TESTED
Cursor✓ TESTED
Installed the published MCP server and ran a call end to end.
Score history+8 · 12mo
Do you work at dlt?
Claim the profile to submit API, MCP, and CLI endpoints, provide test credentials for continuous audits, and embed the badge.
company email · DNS · GitHub org
Badge
agentready59/100
<a href="https://stackresolve.dev/registry/dlthub"><img src="https://api.stackresolve.dev/badge/dlthub.svg" alt="AgentReady score" /></a>
Frequently asked about dlt
What is dlt's AgentReady score?
dlt scores 59/100 on the AgentReady: discovery 100, understanding 23, adoption 60, operability 53. The score rates how ready dlt is for an AI agent to use without a human.
Does dlt have an MCP server?
Yes. dlt publishes an MCP server, so an AI agent can connect to it over the Model Context Protocol.
Does dlt have a free tier?
Yes, dlt has a free tier you can start on without a sales call.
Is dlt good for AI agents?
dlt is partially ready for AI agents, with an AgentReady of 59/100. It is strongest on discovery.