AI content creation

Beyond serving content to client apps, Metabind lets AI agents read and write content directly. The content-management MCP server exposes a set of tools that an agent can call to discover content types, query entries, draft new content, and update existing entries, under the same schema validation and role permissions as everything else.

What’s exposed

The content-management MCP server organizes its tools into three groups:

Group	Tools	Purpose
Context	`set_project`, `get_current_project`, `list_projects`	Tell the AI which project it’s working in
Discovery	`search_types`, `get_type`, `search_content`, `get_content`, `search_assets`	Read-only inspection of project content
Creation	`create_content`, `update_content`	Drafting and editing entries

A connected AI host (Claude, ChatGPT, and others) calls these tools over the same protocol as Metabind’s MCP App tools: JSON-RPC, schema-validated.

Use cases

Drafting product descriptions with AI. The AI reads existing product entries, drafts copy in your house voice, creates a draft entry. A human editor reviews and publishes. Bulk migration from another CMS. A planning agent maps fields from the source CMS to your Metabind content type schema. A worker agent iterates source records and creates Metabind entries via create_content. Have the worker record each failed call and its error for review. Content operations. “Tag every article published before 2024 as archive-candidate” or “Find any entries missing a hero image and flag them.” Reads + filtered updates on a schedule, with each entry’s version history showing what changed. Editor assistance. An editor in a custom in-app assistant asks the AI to “summarize this article in 3 sentences” or “rewrite the intro to match the tone of last month’s post.” The AI uses content tools to read context and update the draft.

Connecting

The content-management MCP server is exposed at:

https://mcp.metabind.ai/YOUR_ORG_ID

Configure it in your MCP host the same way you configure project-scoped MCP Apps:

{
  "mcpServers": {
    "metabind-cms": {
      "url": "https://mcp.metabind.ai/YOUR_ORG_ID"
    }
  }
}

The host signs in with OAuth when it connects; this endpoint does not accept API keys. The token’s scope determines what the AI can access — at the moment, it inherits the user’s organization role and the projects that role gives access to.

Governance and safety

All the platform-wide governance applies:

Schema validation. Every create_content and update_content call is validated against the content type’s schema before writing.
Permissions. The AI acts under the user’s role. A Viewer-scoped token can read but not write. An Editor-scoped token can draft. Publishing remains a human action by default.
Version history. Content writes create new versions of the entry, so you can see what changed and restore an earlier version. Content tool calls aren’t recorded in the project’s tool-call execution history.

For projects in regulated industries: consider keeping AI tokens scoped to Editor (drafts only) and requiring a human to publish.

Managing content

Editor workflow in Metabind Studio.

Querying content

Read-only access via REST, GraphQL, SDKs.

MCP server reference

Every content-management tool and its parameters.

Tools and Types

The MCP App platform’s tool model.

Overview

Managing Content

Querying Content