AWS Knowledge リモートMCPを ChatGPT にMCP接続する方法(設定手順)
Amazon Web Services のリモートMCPサーバーを ChatGPT に約1分でMCP接続。OAuth / 401 の問題は先に OAuth 2.1 デバッガーで確認できます。
Streamable HTTPhttps://knowledge-mcp.global.api.aws
Install in Cursor →
Or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"aws-knowledge": {
"url": "https://knowledge-mcp.global.api.aws"
}
}
}claude mcp add --transport http aws-knowledge https://knowledge-mcp.global.api.aws
Install in VS Code →
Or add to .vscode/mcp.json:
{
"servers": {
"aws-knowledge": {
"type": "http",
"url": "https://knowledge-mcp.global.api.aws"
}
}
}- Open Settings → Connectors (Integrations) → Add Custom Connector.
- Paste the endpoint URL:
https://knowledge-mcp.global.api.aws - No authentication needed — tools are available immediately.
Bridge the remote endpoint into stdio with mcp-remote in claude_desktop_config.json:
{
"mcpServers": {
"aws-knowledge": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://knowledge-mcp.global.api.aws"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"aws-knowledge": {
"serverUrl": "https://knowledge-mcp.global.api.aws"
}
}
}Add to ~/.kiro/settings/mcp.json (or .kiro/settings/mcp.json in your workspace), then reopen Kiro's Agent panel to pick up the server:
{
"mcpServers": {
"aws-knowledge": {
"url": "https://knowledge-mcp.global.api.aws"
}
}
}Add to ~/.codex/config.toml — Codex reads remote HTTP servers from [mcp_servers.*] tables:
[mcp_servers.aws-knowledge] url = "https://knowledge-mcp.global.api.aws"
Add to cline_mcp_settings.json (Cline → MCP Servers → Configure), or paste it via Cline's MCP marketplace file:
{
"mcpServers": {
"aws-knowledge": {
"type": "streamableHttp",
"url": "https://knowledge-mcp.global.api.aws"
}
}
}Add to ~/.gemini/settings.json under mcpServers — httpUrl for Streamable HTTP, url for legacy SSE:
{
"mcpServers": {
"aws-knowledge": {
"httpUrl": "https://knowledge-mcp.global.api.aws"
}
}
}接続手順
- 開発者モードを有効化 — ChatGPT → Settings → Connectors → Advanced で Developer Mode をオンにします。
- コネクタを追加 — 新規 Custom Connector を作成し、
https://knowledge-mcp.global.api.awsを MCP Server URL に入力します。 - 認証を完了 — 認証は不要です。AWS Knowledge は公開エンドポイントです。
- 検証 — オンライン Inspector に
https://knowledge-mcp.global.api.awsを貼り付け、initialize と tools/list を実行して接続を確認します。
🧰 ツール一覧(5)
| Tool | Safety | Description | Parameters |
|---|---|---|---|
| aws___read_documentation ~681 tok | 🟢 Read | Fetch full AWS doc pages as markdown. `search_documentation` already returns verbatim page chunks, so don't re-read a URL whose chunk you already have to "confirm" or "round out" an answer -- the chunk is the real page text; treat it as authoritative. Reading the full page is justified ONLY when the chunks genuinely lack the content: - an enumeration or aggregation ("list all X", "how many X") needs the complete set and the chunks show only part of it; - no search result is on-topic after refining the query, and a known doc URL would have the answer. Otherwise, answer from the chunks. Use exact URLs from `search_documentation`; don't guess slugs. Input: `requests: [{url, max_length?, start_index?}]`. Batch 2-5. - `max_length` default 10000. - `start_index` default 0; use prior `end_index` to continue, TOC offset to jump. Allow-listed prefixes: docs.aws.amazon.com; aws.amazon.com (not /marketplace); repost.aws/knowledge-center; docs.amplify.aws; ui.docs.amplify.aws; github.com/{aws-cloudformation/aws-cloudformation-templates, aws-samples/{aws-cdk-examples, generative-ai-cdk-constructs-samples, serverless-patterns}, awsdocs/aws-cdk-guide, awslabs/aws-solutions-constructs, cdklabs/cdk-nag} (README on `main`); constructs.dev/packages/{@aws-cdk-containers, @aws-cdk, @cdk-cloudformation, aws-analytics-reference-architecture, aws-cdk-lib, cdk-amazon-chime-resources, cdk-aws-lambda-powertools-layer, cdk-ecr-deployment, cdk-lambda-powertools-python-layer, cdk-serverless-clamscan, cdk8s, cdk8s-plus-33}; strandsagents.com/latest/documentation/docs/; karpenter.sh/docs/; Amazon Braket: {amazon-braket-sdk-python, amazon-braket-schemas-python, amazon-braket-default-simulator-python, amazon-braket-pennylane-plugin-python, amazon-braket-algorithm-library, qiskit-braket-provider, autoqasm, qirtoqasm}.readthedocs.io and github.com/amazon-braket/* (blob/tree/raw). Output: SUCCESS -- markdown + `total_length, start_index, end_index, truncated, redirected_url?` (truncated includes TOC with char ranges). ERROR -- `error_code` in {not_found, invalid_url, throttled, downstream_error, validation_error}. | requests: array |
| aws___search_documentation ~426 tok | 🟢 Read | AWS docs search. Each result's `context` is verbatim page text -- a real chunk of the actual page, not a short snippet -- and usually already contains the answer, so answer directly from it. Use `read_documentation` only when the chunks genuinely lack the needed detail. Pick ONE topic. Add a 2nd ONLY if query genuinely spans domains. Extra topics dilute ranking. - reference_documentation -- API/SDK/CLI specs, config params - current_awareness -- new/released/announced - troubleshooting -- errors, "how to fix" (NOT for conceptual/feature questions) - amplify_docs -- Amplify (+ language) - cdk_docs -- CDK concepts/guides - cdk_constructs -- CDK code samples, L3 - cloudformation -- CFN/SAM templates - strands_docs -- Strands Agents SDK (its Skills/agents concepts go here, NOT agent_skills) - agent_skills -- this tool's guided skills (load via `retrieve_skill`) - general (default) -- architecture, best practices, tutorials, feature behavior Results: rank_order (lower=better), url, title, context (verbatim page chunk -- answer directly from it). | limit: integersearch_phrase*: stringtopics: array |
| aws___list_regions ~36 tok | 🟢 Read | Retrieve a list of all AWS regions. | — |
| aws___get_regional_availability ~557 tok | 🟢 Read | AWS resource availability per region. - Max 10 regions; multi-region needs `filters`; single-region supports `next_token`. - Status: isAvailableIn | isNotAvailableIn | isPlannedIn | Not Found. - Response key: products | service_apis | cfn_resources. Not for region counts/docs/vague queries -- use `search_documentation` / `list_regions`. Filter values must EXACTLY match AWS's catalog names; guessed, partial, or pluralized names are rejected ("values in filter parameter do not exist"). If unsure of the exact name, first call once for a single region with resource_type set and NO filters to list all valid names, then re-call filtering on the exact match. | regions: arrayresource_type*: stringfilters: arraynext_token: stringregion: string |
| aws___retrieve_skill ~176 tok | 🟢 Read | Retrieve an AWS skill (workflows, references). Returns SKILL.md, or `file` if given. Call `search_documentation` FIRST and copy `skill_name` verbatim -- it is an opaque registry ID. Never guess or fabricate `skill_name` or `file`. | file: stringskill_name*: string |