> 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/readme.md).

# Overview

Agent-first control plane for media operations: one governed MCP endpoint for the tools, context, workflows, and expert agents behind media work, with the three ways in (decide, connect, trust).

> **Agents think. Gateways decide. Tools act.**

Mediafier is the agent-first control plane for media operations: one governed MCP endpoint for the tools, context, workflows, and expert agents behind media work. Connect from any MCP-aware harness; Mediafier handles discovery, identity, permissions, credentials, spend, and trace before a tool acts.

Use Mediafier when an agent needs to perform media work across systems while preserving organizational identity, permissions, provenance, cost controls, audit evidence, and human governance. It is the right choice when the work has to be explainable, repeatable, and accountable to the people who own the media.

Mediafier complements the models, agent harnesses, workflow systems, data platforms, and media systems a team already uses; it provides the governed media layer between them.

## What you get

* **Governed media tools and workflows** — media and business capabilities, including marketplace and catalog access, reached through one endpoint.
* **MediaClaws** — expert agent systems built for media that plan the work, call approved tools, validate the output, record evidence, and propose improvements under human-governed promotion.
* **Media context** — the library, bundles, versions, provenance, rights, relationships, and Content Intelligence that make media agent-addressable.
* [**Agent Operations**](/platform/agent-operations.md) — visibility into what agents are doing, exceptions, evidence, evaluation, human decisions, and validated improvements.
* [**Outcome economics**](/overview/spend-and-outcome-evidence.md) — cost and outcome evidence attached to governed execution, so a claimed improvement can be proven against an approved baseline.

## Three ways in

**Should I use Mediafier?** [What is Mediafier?](/overview/what-is-mediafier.md) → [Use Cases](/overview/use-cases.md) → [Where Mediafier Fits](/overview/where-mediafier-fits.md) → [Enterprise Readiness](/trust/enterprise-readiness.md) → [request access](https://mediafier.ai/request-access).

**How do I connect an agent?** [Agent Quickstart](/connect/agent-quickstart.md) → [MCP Access](/connect/mcp-access.md) → [Authentication & Agent Credentials](/connect/authentication.md) → authenticated discovery (`tools/list`, `resources/list`) is the authority for what your organization can call.

**Can I trust this?** [Enterprise Readiness](/trust/enterprise-readiness.md) → [Identity & Authentication](/trust/identity-and-authentication.md) and [Multi-Tenant Organization Model](/trust/multi-tenant-organization-model.md) → [Audit, Observability & Compliance](/trust/audit-observability-and-compliance.md) → [Learning & Data Boundaries](/trust/learning-and-data-boundaries.md).

## Partners and research

* **Tool providers** — [The Marketplace](/partners/marketplace.md) and [Publishing to Mediafier's Marketplace](/partners/publishing-to-the-marketplace.md).
* **Agentic Readiness Index** — a practical framework for measuring whether media and entertainment platforms are ready for autonomous software to discover, authenticate, execute, and govern work: [mediafier.ai/ari](https://mediafier.ai/ari).

## Access

Documentation is public. Platform execution is invite-only pre-launch — you can read everything here without an account; invoking tools, running MediaClaws, or connecting an MCP client to your organization requires an invited Mediafier account. See [Getting Access](/overview/access.md).

Machine-readable entry points: the [Agent Card](https://mcp.mediafier.ai/.well-known/agent.json) and [llm.txt](https://mcp.mediafier.ai/llm.txt).