Analyze and Share
Which Credible surface to use for each job (chat clients, coding agents, your own agent, chat in the app, reports, data apps, shared workspaces, Slack, APIs) and how answers are grounded in your data model
People and agents ask questions of a published package from several places. Each surface below reads the same published models and runs each query as the person or API key asking, so the same question gets the same answer everywhere.
Choose a Surface
| Surface | Use it to | Guide |
|---|---|---|
| Chat clients | Ask from Claude, ChatGPT or another MCP chat client | Chat Clients |
| Coding agents | Query published models from Claude Code, Codex, Cursor and other coding tools | Coding Agents |
| Your own agent | Connect an agent or service to the MCP server with an API key | MCP Server and Tools |
| Chat in the app | Ask the in-app agent and see the query behind each answer | Chat with Your Data |
| Reports | Save dashboards and notebooks with filter controls that anyone with access can reopen | Reports |
| Data apps | Ship a custom HTML and JavaScript app inside a package | Data Apps |
| Shared workspaces | Give a team its packages, chats and reports in one place, with its own MCP URL | Share with a Workspace |
| Slack | Ask the Credible bot in a channel or a direct message | Slack |
| REST APIs | Run queries, read model context or manage Credible from code | REST APIs |
How It Works
Every surface answers a question the same way: retrieve the relevant part of the model, write a Malloy query against it, and run that query under the caller's access rules.
At publish: index the model
When a package is published, Credible indexes what its models declare: sources, dimensions, measures and views, the #(doc) descriptions on them, and the values of dimensions tagged #(index). Retrieval searches that index. Descriptions and Value Search covers how to write those tags.
At question time: retrieve, write, run
- Retrieve. The agent calls
get_contextwith the concepts the question needs. Retrieval matches them by meaning as well as by exact name, and returns the matching sources, fields, views and indexed values with their descriptions. It returns only the part of the model that matches, and it does not return a query. - Write. The agent writes a Malloy query from the fields
get_contextreturned, using the field names exactly as returned. - Run. The agent calls
execute_query. Credible compiles the query against the published model and runs it on your database as the caller, so the model's row and column access rules apply to every result.
The agent repeats these steps as the conversation goes on. In the Credible app, the chat shows each step, including the Malloy query an answer ran.
Improving answers
Retrieval can only find what the model declares and describes. When an agent picks the wrong field or can't find a concept, the fix is usually in the model: add or sharpen a #(doc) description, or tag a dimension #(index) so its values can be found, then publish a new version. Every surface picks up the change.
Next Steps
Chat Clients
Connect Claude, ChatGPT and other MCP chat clients
Chat with Your Data
Ask questions in the Credible app
Reports
Dashboards and notebooks saved as Malloy files
Data Apps
Custom HTML and JavaScript pages shipped in a package
Share with a Workspace
Give a team its packages, chats and reports
MCP Server and Tools
Endpoints, authentication and the tool reference