How do I use microCMS MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@microCMS MCP Server Get the latest 10 blog article titles from the blog endpoint" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

microCMS MCP Server

by burnworks

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

microCMS MCP サーバ

このプロジェクトは、Model Context Protocol (MCP) を使用して microCMS の API にアクセスするサーバを実装したものです。

概要

microCMS MCP サーバは以下の機能を提供します：

コンテンツ一覧取得：指定したエンドポイントからコンテンツ一覧を取得
特定コンテンツ取得：ID を指定して特定のコンテンツを取得
コンテンツ検索：キーワード検索によるコンテンツの取得
フィルター検索：複雑な条件でのコンテンツのフィルタリング

Related MCP server: microCMS MCP Server

インストール

# リポジトリのクローン
git clone https://github.com/burnworks/microcms-api-mcp-server
cd microcms-api-mcp-server

# 依存関係のインストール
npm install

使用方法

必要なファイルのビルド

# TypeScriptをコンパイル
npm run build

dist/ ディレクトリ内に必要なファイルが生成されます。

MCP クライアントからの使用

このサーバは MCP プロトコルに準拠しており、任意の MCP クライアントから接続して使用できます。

Claude デスクトップアプリでの利用

claude_desktop_config.json に下記のように設定してください。

{
  "mcpServers": {
    "microcms": {
      "command": "node",
      "args": [
        "/[__path__]/microcms-api-mcp-server/dist/index.js"
      ],
      "env": {
        "MICROCMS_API_KEY": "__your_api_key_here__",
        "MICROCMS_BASE_URL": "https://your-service.microcms.io"
      }
    }
  }
}

Windows 環境であれば下記のような設定になるかもしれません。

{
  "mcpServers": {
    "microcms": {
      "command": "C:/Program Files/nodejs/node.exe",
      "args": [
        "C:/[__path__]/microcms-api-mcp-server/dist/index.js"
      ],
      "env": {
        "MICROCMS_API_KEY": "__your_api_key_here__",
        "MICROCMS_BASE_URL": "https://your-service.microcms.io"
      }
    }
  }
}

利用可能なツール

例えば下記のようなプロンプトで microCMS API にアクセスできます。

blog エンドポイントから、最新の記事10件分のタイトルを取得して

`get_contents`

コンテンツ一覧を取得します。

パラメータ:

endpoint: 取得したい microCMS の API エンドポイント（例: 'blog'）
limit: 取得する件数（オプション、デフォルト: 10、最大: 100）
offset: 取得開始位置のオフセット（オプション）
orders: 並び替え（オプション、例: 'publishedAt' または '-publishedAt'）
q: 全文検索クエリ（オプション）
filters: フィルタ条件（オプション、例: 'title[contains]テスト'）
fields: 取得フィールド（オプション、例: 'id,title,publishedAt'）
depth: 参照の深さ（オプション、1-3）

`get_content`

特定のコンテンツを取得します。

パラメータ:

endpoint: 取得したい microCMS の API エンドポイント（例: 'blog'）
contentId: 取得したいコンテンツの ID
fields: 取得フィールド（オプション、例: 'id,title,publishedAt'）
depth: 参照の深さ（オプション、1-3）
draftKey: 下書きコンテンツを取得するためのキー（オプション）

`search_contents`

キーワード検索でコンテンツを取得します。

パラメータ:

endpoint: 検索対象の microCMS の API エンドポイント（例: 'blog'）
q: 検索キーワード
limit: 取得する件数（オプション、デフォルト: 10、最大: 100）
offset: 取得開始位置のオフセット（オプション）
fields: 取得フィールド（オプション、例: 'id,title,publishedAt'）
depth: 参照の深さ（オプション、1-3）

`filter_contents`

複雑な条件でコンテンツをフィルタリングします。

パラメータ:

endpoint: 検索対象の microCMS の API エンドポイント（例: 'blog'）
filters: フィルター条件（例: 'category[equals]news[and]createdAt[greater_than]2023-01-01'）
limit: 取得する件数（オプション、デフォルト: 10、最大: 100）
offset: 取得開始位置のオフセット（オプション）
fields: 取得フィールド（オプション、例: 'id,title,publishedAt'）
depth: 参照の深さ（オプション、1-3）

利用可能なリソース

`microcms://{endpoint}/{contentId}`

特定の ID のコンテンツを取得するためのリソース URI テンプレート。

`microcms://{endpoint}`

コンテンツ一覧を取得するためのリソース URI テンプレート。

ライセンス

MIT

Available Tools

4 tools

filter_contentsD

ParametersJSON Schema

Name	Required	Description
`endpoint`	Yes	検索対象のmicroCMSのAPIエンドポイント (例: 'blog')
`filters`	Yes	フィルター条件 (例: 'category[equals]news[and]createdAt[greater_than]2023-01-01')
`limit`	No	取得する件数 (デフォルト: 10, 最大: 100)
`offset`	No	取得開始位置のオフセット
`fields`	No	取得フィールド (例: 'id,title,publishedAt')
`depth`	No	参照の深さ (1-3)

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_contentD

ParametersJSON Schema

Name	Required	Description
`endpoint`	Yes	取得したいmicroCMSのAPIエンドポイント (例: 'blog')
`contentId`	Yes	取得したいコンテンツのID
`fields`	No	取得フィールド (例: 'id,title,publishedAt')
`depth`	No	参照の深さ (1-3)
`draftKey`	No	下書きコンテンツを取得するためのキー

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_contentsD

ParametersJSON Schema

Name	Required	Description
`endpoint`	Yes	取得したいmicroCMSのAPIエンドポイント (例: 'blog')
`limit`	No	取得する件数 (デフォルト: 10, 最大: 100)
`offset`	No	取得開始位置のオフセット
`orders`	No	並び替え (例: 'publishedAt' or '-publishedAt')
`q`	No	全文検索クエリ
`filters`	No	フィルタ条件 (例: 'title[contains]テスト')
`fields`	No	取得フィールド (例: 'id,title,publishedAt')
`depth`	No	参照の深さ (1-3)

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_contentsD

ParametersJSON Schema

Name	Required	Description
`endpoint`	Yes	検索対象のmicroCMSのAPIエンドポイント (例: 'blog')
`q`	Yes	検索キーワード
`limit`	No	取得する件数 (デフォルト: 10, 最大: 100)
`offset`	No	取得開始位置のオフセット
`fields`	No	取得フィールド (例: 'id,title,publishedAt')
`depth`	No	参照の深さ (1-3)

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

4 tool updatesv1.0.0Jun 24, 2026
- First observedfilter_contents
- First observedget_content
- First observedget_contents
- First observedsearch_contents

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

D1.6/5.0

Scored 2026-06-24 08:25 across 4 tools

Disambiguation3/5

Tool names suggest different operations (filter, get single, get all, search), but without descriptions, potential overlap between 'search_contents' and 'filter_contents' or 'get_contents' introduces ambiguity.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern (filter_contents, get_content, get_contents, search_contents) with no mixing of conventions.

Tool Count2/5

Only 4 tools for a CMS server is far too few; typical CMS operations (create, update, delete, content type management) are missing, making the scope too narrow.

Completeness2/5

The tool set covers only read operations (get, filter, search), lacking essential CRUD operations (create, update, delete) and content lifecycle management.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Garchi CMS MCPOAuth
uk.co.garchi
Manage structured website content in Garchi CMS through MCP.
Content Management Systems App Automation Autonomous Agents
2
ComplianceAutomator Public MCP A
com.complianceautomator
Public read-only MCP for products, frameworks, guides, methodology, and blog metadata.
Documentation Access Knowledge & Memory
92
mcp-serverOAuth
com.agilitycms
An MCP server that provides access to Agility CMS. See https://mcp.agilitycms.com for more details.
Content Management Systems Developer Tools
2
SRG+OAuth
io.github.srgplus
Manage SRG+ hubs, channels, content, assets, users, and workspaces from any MCP-aware AI agent.
Content Management Systems Workplace & Productivity
2

Related MCP Servers

Strapi MCP Server
Content Management Systems Databases
l33tdawg
A
license
Not graded
quality
D
maintenance
Provides access to Strapi CMS content through the MCP protocol, allowing users to create, read, update, and delete content entries via Claude.
Updated a year ago (2025-07-25 09:47 UTC)
1,425 npm
25
MIT
microCMS MCP Server
Search Content Management Systems
SpringMT
A
license
B
quality
D
maintenance
A Model Context Protocol (MCP) compliant server that allows Large Language Models (LLMs) to search and retrieve content from microCMS APIs.
Updated 2 years ago (2025-03-19 01:52 UTC)
2
MIT
contentstack-mcp
API Testing Content Management Systems RAG Systems
darekrossman
A
license
A
quality
C
maintenance
An MCP server for interacting with Contentstack's Content Management API
Updated a year ago (2025-07-05 02:26 UTC)
15
7 npm
2
TypeScript
MIT
Storyblok MCP Serverofficial
Content Management Systems Developer Tools
storyblok
A
license
Not graded
quality
F
maintenance
Provides access to the Storyblok Management API via MCP, enabling content management and operations on Storyblok spaces through natural language. Note: This repository is archived; use the hosted version at mcp.labs.storyblok.com.
Updated 6 months ago (2026-03-30 05:40 UTC)
60 npm
8
MIT

microCMS MCP サーバ

概要

インストール

使用方法

必要なファイルのビルド

MCP クライアントからの使用

Claude デスクトップアプリでの利用

利用可能なツール

get_contents

get_content

search_contents

filter_contents

利用可能なリソース

microcms://{endpoint}/{contentId}

microcms://{endpoint}

ライセンス

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Storyblok MCP Serverofficial

`get_contents`

`get_content`

`search_contents`

`filter_contents`

`microcms://{endpoint}/{contentId}`

`microcms://{endpoint}`