# Mediafier Docs

## Mediafier Platform

- [Overview](https://docs.mediafier.ai/readme.md): 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).
- [Mediafier Overview](https://docs.mediafier.ai/overview/mediafier-in-brief.md): Mediafier on one page: an agent-first media factory that turns creative intent into finished media, with permissions, usage tracking and an audit trail built into execution.
- [What is Mediafier?](https://docs.mediafier.ai/overview/what-is-mediafier.md): The problem Mediafier solves, what it is (three layers, one enforcement chain), and who it is for.
- [Use Cases](https://docs.mediafier.ai/overview/use-cases.md): Who Mediafier is for and representative media use cases, from first-touch asset onboarding to outcome-priced MediaClaw operations.
- [Where Mediafier Fits](https://docs.mediafier.ai/overview/where-mediafier-fits.md): How Mediafier sits as the vertical media layer alongside the models, agent runtimes, workflow, and data platforms a team already uses.
- [Core Philosophy](https://docs.mediafier.ai/overview/core-philosophy.md): Agents think, gateways decide, tools act — the operating principle behind every governed call.
- [Credits & Billing](https://docs.mediafier.ai/overview/credits-and-billing.md): Per-call metering governed at the gateway: engagement shapes, what is billed, wallets, spend controls, and what happens at zero balance.
- [Spend & Outcome Evidence](https://docs.mediafier.ai/overview/spend-and-outcome-evidence.md): Cost per successful outcome: verified-not-estimated spend, mastery scorecards, human touches, and declared, versioned baselines.
- [Getting Access](https://docs.mediafier.ai/overview/access.md): Documentation is public; platform execution is invite-only pre-launch. How to tell whether you have access and how to request it.
- [Platform Architecture](https://docs.mediafier.ai/platform/platform-architecture.md): Three layers, one enforcement chain, one trace ID — the shape of the platform without the internals.
- [The Gateway](https://docs.mediafier.ai/platform/gateway.md): What the gateway enforces on every call: identity, organization context, authorization, rate limits, billing, audit, dispatch.
- [Governed Resources & Discovery](https://docs.mediafier.ai/platform/governed-resource-substrate.md): Everything invocable is a governed resource; discovery is authenticated and authorization-scoped.
- [MediaClaw Super-Agents](https://docs.mediafier.ai/platform/mediaclaw-super-agents.md): MediaClaws: bounded, observable expert agents with a Cognitive Rig, Evidence Cards, human-controlled skill promotion, and mastery scorecards.
- [Media Library](https://docs.mediafier.ai/platform/media-library.md): Bundles, versions, files, and provenance — the media context agents act on.
- [Content Intelligence](https://docs.mediafier.ai/platform/content-intelligence.md): Governed AI capability families that turn raw media into structured, searchable, rights-aware context.
- [Decision Tracing & Learning Loop](https://docs.mediafier.ai/platform/decision-tracing-and-learning-loop.md): Every approval, override, and edit becomes searchable precedent; the learning loop proposes, humans approve.
- [Agent Operations](https://docs.mediafier.ai/platform/agent-operations.md): See what agents did, decide what happens next, keep the evidence — human supervision built into the platform (private beta).
- [Where Agents Run](https://docs.mediafier.ai/platform/slack-and-teams.md): Where agents run: the agent-first MCP surface, team chat, and the Pippa control room on one gateway and one audit trail.
- [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.
- [Enterprise Readiness](https://docs.mediafier.ai/trust/enterprise-readiness.md): The five questions enterprise reviews focus on — identity, tenancy, authorization, audit, governance — and what is in place for each.
- [Identity & Authentication](https://docs.mediafier.ai/trust/identity-and-authentication.md): How identity is issued and verified, how organization context is derived server-side, and what an identity failure returns.
- [Multi-Tenant Organization Model](https://docs.mediafier.ai/trust/multi-tenant-organization-model.md): One platform, many organizations, hard isolation enforced at the data layer.
- [Per-User Connector Authorization](https://docs.mediafier.ai/trust/per-user-connector-authorization.md): When a connector acts as the individual user, what is authorized, and what is charged.
- [Audit, Observability & Compliance](https://docs.mediafier.ai/trust/audit-observability-and-compliance.md): Every call leaves a trace; every trace is reconstructable; audit is append-only by enforcement.
- [Learning & Data Boundaries](https://docs.mediafier.ai/trust/learning-and-data-boundaries.md): Organization learning stays in the organization; platform hardening carries no customer content; network intelligence is not offered today.
- [The Marketplace](https://docs.mediafier.ai/partners/marketplace.md): Composable governed resources under one enforcement chain, from first-party tools to partner-published listings.
- [Publishing to Mediafier's Marketplace](https://docs.mediafier.ai/partners/publishing-to-the-marketplace.md): Build to the contract, get listed, earn per call: what publishing requires and what the review promises.
- [Provider Earnings & Marketplace Economics](https://docs.mediafier.ai/partners/provider-earnings-and-marketplace-economics.md): How tool publishers earn per call and how the platform clears against the same ledger customers see.