Discourse Connector
Connect Discourse to your data stack with Weld. Fully managed pipelines, set up in minutes, ready for your agents.
Set up in minutes.
No code, no maintenance.
Discourse
Data source
Discourse in your warehouse.
Ready for your agents.
Weld's Discourse connector is fully managed: it extracts data from Discourse, loads it into your warehouse, and keeps it in sync. The data lands in a clean, documented schema with agent context attached, so analysts can query it with SQL or dbt, and agents can query it over the Weld MCP server without guessing at tables or joins.
Ask your agent.
It can reach Discourse.
Connect Claude, Cursor, ChatGPT or your own agent to Weld over MCP. It finds the Discourse tables Weld has synced and queries your warehouse.
- DiscoverSynced tables, columns and freshness
- QuerySQL against your warehouse
- OperateCheck, rerun and refresh syncs
Which Discourse tables do we have, and which one is the largest?
Looking up what the Discourse connection has synced.
Load Discourse into any warehouse.
Set up in minutes, no code.
Everything you need.
To get started.
Discourse setup guide
Step-by-step instructions to configure and start syncing.
MCP serverConnect your agents
Set up Claude, Cursor, ChatGPT or Codex against your Weld workspace.
Weld Connect APIBuild custom connectors
Use the Weld Connect API to build and publish your own connector.
FAQCommon questions
Answers to frequently asked questions about Weld connectors.
Set it up in code.
One REST API.
Use the Weld Connect REST API to create Discourse connections, configure ELT syncs, and manage pipelines entirely through code. Built for embedding, automation, and CI/CD workflows.
▌Common questions.
About connectors.
Something not covered here? A data engineer can walk through your setup with you.
Talk to usPut your Discourse data to work.
Connect Discourse, pick a warehouse, and your agents can query it today. Free for 14 days, no credit card.

