The Moonage Content MCP Server exposes blog, changelog, roadmap, search, and asset tools over the Model Context Protocol. Any MCP-compatible client can connect and manage content programmatically.

Connection

Property	Value
Transport	Streamable HTTP
Endpoint	`https://content.moonage.ai/mcp`
Server name	Moonage Content
Version	1.0.0

Connecting with curl

# 1. Initialize a session
curl -X POST https://content.moonage.ai/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "initialize",
    "params": {
      "protocolVersion": "2025-03-26",
      "capabilities": {},
      "clientInfo": { "name": "my-client", "version": "1.0.0" }
    }
  }'

# 2. Save the Mcp-Session-Id header from the response

# 3. Send initialized notification
curl -X POST https://content.moonage.ai/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Mcp-Session-Id: SESSION_ID" \
  -d '{"jsonrpc": "2.0", "method": "notifications/initialized"}'

# 4. Call tools
curl -X POST https://content.moonage.ai/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Mcp-Session-Id: SESSION_ID" \
  -d '{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/call",
    "params": {
      "name": "list_blog_posts",
      "arguments": { "limit": 5 }
    }
  }'

Connecting with the MCP TypeScript SDK

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const transport = new StreamableHTTPClientTransport(
  new URL("https://content.moonage.ai/mcp")
);

const client = new Client({
  name: "my-app",
  version: "1.0.0",
});

await client.connect(transport);

// List available tools
const { tools } = await client.listTools();

// Call a tool
const result = await client.callTool("list_blog_posts", { limit: 5 });

Tools

The server exposes 15 tools organized by content type.

Blog tools

`list_blog_posts`

List published blog posts with optional filtering.

Parameter	Type	Required	Description
`limit`	number	No	Max posts (1-100, default 20)
`tag`	string	No	Filter by tag
`cursor`	string	No	ISO date for pagination

`get_blog_post`

Get a single blog post by slug, including full markdown content.

Parameter	Type	Required	Description
`slug`	string	Yes	The blog post slug
`include_drafts`	boolean	No	Include non-published posts (default false)

`create_blog_post`

Create a new blog post (draft by default).

Parameter	Type	Required	Description
`title`	string	Yes	Post title
`content`	string	No	Markdown content
`description`	string	No	SEO description (50-160 chars)
`author_name`	string	No	Author name
`tags`	string[]	No	Tags array
`status`	string	No	`draft` or `published` (default: draft)

`update_blog_post`

Update an existing blog post by slug.

Parameter	Type	Required	Description
`slug`	string	Yes	Post slug
`title`	string	No	New title
`content`	string	No	New markdown content
`description`	string	No	New SEO description
`tags`	string[]	No	New tags array

`publish_blog_post`

Publish a blog post (changes status to published).

Parameter	Type	Required	Description
`slug`	string	Yes	Post slug

Changelog tools

`list_changelog_entries`

List published changelog entries with optional type filter.

Parameter	Type	Required	Description
`limit`	number	No	Max entries (1-100, default 20)
`type`	string	No	`release`, `hotfix`, `beta`, or `alpha`

`get_changelog_entry`

Get a single changelog entry by slug or version.

Parameter	Type	Required	Description
`identifier`	string	Yes	Slug or version string

`create_changelog_entry`

Create a new changelog entry.

Parameter	Type	Required	Description
`version`	string	Yes	Version string (e.g. `v2.3.0`)
`title`	string	No	Entry title
`summary`	string	No	Short summary
`content`	string	No	Full markdown content
`type`	string	No	`release`, `hotfix`, `beta`, `alpha`
`highlights`	string[]	No	Key highlights
`status`	string	No	`draft` or `published`

Roadmap tools

`list_roadmap_items`

List public roadmap items with optional filters.

Parameter	Type	Required	Description
`status`	string	No	`all`, `planned`, `in_progress`, `shipped`, `cancelled`, `considering`
`category`	string	No	`product`, `platform`, `integrations`, `api`, `dx`
`limit`	number	No	Max items (1-100, default 50)

Returns items sorted by priority and a by_status count summary.

`get_roadmap_item`

Get a single roadmap item by slug.

Parameter	Type	Required	Description
`slug`	string	Yes	Roadmap item slug

`create_roadmap_item`

Create a new roadmap item.

Parameter	Type	Required	Description
`title`	string	Yes	Item title
`description`	string	No	Full description (markdown)
`summary`	string	No	Short summary
`category`	string	No	`product`, `platform`, `integrations`, `api`, `dx`
`status`	string	No	`planned`, `in_progress`, `shipped`, `cancelled`, `considering`
`priority`	string	No	`low`, `medium`, `high`, `critical`
`quarter`	string	No	Target quarter (e.g. `Q2 2026`)

`update_roadmap_item`

Update an existing roadmap item.

Parameter	Type	Required	Description
`slug`	string	Yes	Item slug
`title`	string	No	New title
`description`	string	No	New description
`summary`	string	No	New summary
`status`	string	No	New status
`priority`	string	No	New priority
`quarter`	string	No	New target quarter

Search tool

`search_content`

Search across blog posts, changelog entries, and roadmap items.

Parameter	Type	Required	Description
`query`	string	Yes	Search query
`type`	string	No	`all`, `blog`, `changelog`, `roadmap` (default: all)
`limit`	number	No	Max results per type (1-50, default 10)

Returns results grouped by content type.

Asset tool

`get_asset_upload_url`

Get information about how to upload images to the content R2 bucket. Returns the upload endpoint, accepted fields, and the public URL base.

No parameters required.

Activity tool

`get_activity_log`

Query the activity log for content changes.

Parameter	Type	Required	Description
`resource`	string	No	Filter: `blog`, `changelog`, `roadmap`
`limit`	number	No	Max entries (1-200, default 50)

Architecture

The MCP server runs on the same Cloudflare Worker as the REST API. Each request creates a stateless server instance with access to the D1 database and R2 bucket.

Client (Claude, Cursor, custom agent)
  │
  ▼ Streamable HTTP
┌───────────────────────────┐
│  Cloudflare Worker        │
│  /mcp → MCP Handler      │
│  /blog, /changelog, ...   │
│          → Hono REST API  │
│                           │
│  ┌─────┐  ┌────────────┐ │
│  │ D1  │  │ R2 (media) │ │
│  └─────┘  └────────────┘ │
└───────────────────────────┘

The MCP tools perform the same operations as the REST endpoints but are optimized for agent consumption — they return structured JSON text content directly rather than HTTP response objects.

MCP Server

On this page