> For the complete documentation index, see [llms.txt](https://docs.mediafier.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mediafier.ai/connect.md).

# Connect

- [Agent Quickstart](https://docs.mediafier.ai/connect/agent-quickstart.md): The fastest path from an MCP-aware agent to a first governed call: endpoint, authentication, discovery, first call.
- [Getting Started](https://docs.mediafier.ai/connect/getting-started.md): Connect your agent or IDE to the Mediafier MCP endpoint, sign in, and make your first call.
- [MCP Access](https://docs.mediafier.ai/connect/mcp-access.md): Connect any MCP harness to the canonical endpoint, discover what your organization can call, and correlate every call by trace.
- [Authentication & Agent Credentials](https://docs.mediafier.ai/connect/authentication.md): Browser sign-in for interactive sessions; Agent Credentials exchanged for access tokens for headless use; scopes and rotation.
- [Agent-First Access](https://docs.mediafier.ai/connect/agent-first-access.md): Access from any agent platform, IDE, harness, or pipeline through one MCP endpoint.
- [Troubleshooting](https://docs.mediafier.ai/connect/troubleshooting.md): Structured errors, retry guidance, and trace-id correlation for every refused call.
- [Compatibility](https://docs.mediafier.ai/connect/compatibility.md): Which agent harnesses, IDEs, connectors, SDKs and cloud runtimes connect to Mediafier today, how each was verified, and when.
- [Releases & Deprecation](https://docs.mediafier.ai/connect/release-and-deprecation.md): How Mediafier ships change, what deprecated means for a tool or surface, and where an agent learns about it first.
- [Protocol Changes](https://docs.mediafier.ai/connect/protocol-changes.md): Dated record of changes to how the Mediafier MCP endpoint behaves that an integration may need to act on: what changed, who is affected, and what to do.