Context Atlas
Find llms.txt, docs, MCP servers, skills and CLIs for a tech stack, for coding agents.
使うべきか
品質と安全性
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": {
"contextatlas": {
"url": "https://contextatlas.dev/mcp"
}
}
}リモートエンドポイント
https://contextatlas.dev/mcpstreamable-httpできること
ツール一覧
ツール（3）
🟢search(query, kind, limit)
Full-text search over tools (topics) and their sources. Matches names, roles, regions, detection signals (files, dependencies, env vars), source titles and URLs. Every word must match, as a prefix.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "Words to search for, e.g. \"database\", \"vercel mcp\" or \"turbo.json\""
},
"kind": {
"description": "Only return sources of this kind",
"type": "string",
"enum": [
"llms",
"full",
"docs",
"mcp",
"skill",
"rules",
"guide"
]
},
"limit": {
"description": "Maximum number of topics, default 10",
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"required": [
"query"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_topic(id)
All sources (llms.txt, docs, MCP servers, skills, rules), detection signals and the role of one tool, by id such as `vercel`, `nextjs` or `drizzle`.
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Topic id, as returned by search or list_topics"
}
},
"required": [
"id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_topics(region)
Every tool in the catalog with its id, name, role and region, without sources. Use it to find candidates per role, then get_topic and their llms.txt sources to compare them.
入力スキーマ
{
"type": "object",
"properties": {
"region": {
"description": "Only this region id, e.g. cloud, frameworks, standards or clis",
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}コミュニティ
エビデンス