> ## Documentation Index
> Fetch the complete documentation index at: https://docs.credibledata.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Developer Overview

> Local development — the whole platform in your own toolset

Developers want to work locally — in their own editor, with their own coding agent, on files they control. Credible is built for exactly that. Semantic models are [Malloy](https://malloydata.dev) code in plain files: edit them in your IDE, version them in Git, review them in pull requests, and publish from your terminal or [CI/CD](/platform-admin/cicd). Nothing about your workflow has to change.

And local development is not a side door. Your local agent runs on the **same foundation as every other Credible surface** — the same governed models, the same MCP (Model Context Protocol) tools, the same [open-source skills](/introduction#one-set-of-skills-every-surface). Managed connections mean no credentials ever land on your machine.

<Note>
  **Prefer zero setup?** You can also [build in the app](/how-to/modeling/in-app-development) — entirely in your browser, no IDE required. It's the fastest way to get started; local development is best for engineers who want Git-based workflows and direct control over files. Both produce the same governed packages.
</Note>

## The Local Workflow

Local development with Credible looks like development anywhere else:

1. **Set up your IDE** — Install the [VS Code Extension](/how-to/developers/vscode-extension) (works in VS Code and Cursor, with Claude Code picking up the same workspace config). It equips your agent with managed connections, modeling MCP tools, and modeling skills — the same open tools and skills [Malloy Publisher](https://github.com/malloydata/publisher) provides.
2. **Build in files you own** — Your agent discovers your data and drafts `.malloy` models right in your workspace. Edit, refactor, and iterate like any other code.
3. **Version and review in Git** — Commit models alongside the rest of your codebase; review changes in pull requests.
4. **Publish from anywhere** — From your IDE agent, the [CLI](/platform-admin/cli), or automatically on merge with [CI/CD](/platform-admin/cicd).

## Built on Open Source

The stack you're building on is not a black box. Credible contributed its MCP tools and agent skills to [Malloy Publisher](https://github.com/malloydata/publisher), the open-source server for Malloy models: retrieval tools that let an agent look up what your model actually defines, and skills encoding the discipline to use them well — query patterns, gotchas that trip up frontier models, and the rigor that separates a real answer from a plausible one. These are the **same skills the in-app agent runs**, so how your agent models and analyzes is identical in the app and in your IDE. And because they're open, they're curated with the world's data experts — read them, fork them, or extend them with your organization's institutional knowledge. Read the full story in [We Open Sourced the Thing Everyone Else Is Selling](https://credibledata.com/blog/posts/open-sourcing-skills).

## Set Up Your Tools

<CardGroup cols={2}>
  <Card title="VS Code Extension" icon="puzzle-piece" color="#5C7A93" href="/how-to/developers/vscode-extension">
    Build models in VS Code, Cursor, or Claude Code — managed connections, modeling MCP tools, and skills, no credentials on your machine
  </Card>

  <Card title="Connect your Coding Agent" icon="message-bot" color="#5C7A93" href="/how-to/developers/connect-coding-agent">
    Let any coding agent analyze data with your published models — the same governed access as workspace chat
  </Card>

  <Card title="Embedded Data" icon="file-csv" color="#5C7A93" href="/how-to/developers/embedded-data">
    Ship CSV and Parquet files inside your packages for standalone, versioned models
  </Card>

  <Card title="CLI" icon="terminal" color="#5C7A93" href="/platform-admin/cli">
    Everything the Credible App manages, scriptable from your terminal
  </Card>
</CardGroup>

## Automate and Integrate

<CardGroup cols={3}>
  <Card title="CI/CD Setup" icon="rocket" color="#94793A" href="/platform-admin/cicd">
    Version models in Git and publish automatically on merge
  </Card>

  <Card title="API Access" icon="key" color="#94793A" href="/how-to/integrating/apis">
    Build on the REST APIs
  </Card>

  <Card title="MCP Tools" icon="robot" color="#94793A" href="/how-to/analyzing/ai-assistants-mcp">
    Give your own agents and applications governed access via MCP
  </Card>
</CardGroup>