developer-toolkit-mcp
The documentation, as a tool your agent can call: 950+ AI-dev guides. Search + fetch tools.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'fetch' suggests web access but openWorldHint=falsefetch 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"developer-toolkit-mcp": {
"url": "https://developertoolkit.ai/mcp"
}
}
}リモートエンドポイント
https://developertoolkit.ai/mcpstreamable-httpできること
ツール一覧
ツール（2）
🟢search(query, llm_model)
Search the AI Developer Toolkit documentation: 950+ guides on Cursor, Claude Code and OpenAI Codex, covering setup, agent workflows, hooks, MCP, testing, CI and deployment, in English and Polish. Returns at most 10 ranked results, each with a short snippet rather than the article text; an empty list means the corpus has nothing on the topic. Pass a result id to `fetch` for the full text.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 1024,
"description": "Natural-language query or keywords. Polish queries return Polish articles."
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
}
},
"required": [
"query",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"snippet": {
"type": "string"
},
"lang": {
"type": "string"
}
},
"required": [
"id",
"title",
"url",
"snippet",
"lang"
],
"additionalProperties": false
}
}
},
"required": [
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢fetch(id, llm_model)
Retrieve the complete markdown of one documentation article by the id returned from `search` (for example `en/claude-code/advanced-techniques/hooks-automation`). The text is returned in full; `metadata.gated` only reports whether the article sits behind the paywall on the web. An unknown id is an error — call `search` first.
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Article id from a `search` result."
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
}
},
"required": [
"id",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"text": {
"type": "string"
},
"url": {
"type": "string"
},
"metadata": {
"type": "object",
"properties": {
"lang": {
"type": "string"
},
"section": {
"type": "string"
},
"lastUpdated": {
"type": "string"
},
"gated": {
"type": "boolean"
}
},
"required": [
"lang",
"section",
"lastUpdated",
"gated"
],
"additionalProperties": false
}
},
"required": [
"id",
"title",
"text",
"url",
"metadata"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}コミュニティ
エビデンス