AWS Knowledge Remote MCP Server
AWS's fully-managed public knowledge MCP gives agents access to the latest AWS documentation, API references, What's New posts and architectural guidance across all AWS services. Endpoint verified live on RemoteMCP.net (preflighted 200 OK).
- Provider
- Amazon Web Services โ
- Categories
- ๐ Documentation, Search & Contextโ๏ธ Cloud, Infrastructure & DevOps
ไธญๆ็ฎไป
AWS Knowledge ๅฎๆนๆ็ฎก็่ฟ็จ MCP ๆๅกๅจใAWS ๅฎๆนๅ จๆ็ฎก็ฅ่ฏๅบ MCP๏ผไธบ AI ไปฃ็ๆไพๆๆฐ AWS ๆๆกฃใAPI ๅ่ไธๆถๆๆๅฏผใๅ ฌๅผๅ ้ดๆ๏ผๅผ็ฎฑๅณ็จใ
Maintainer of AWS Knowledge? Claim or update this listing โ
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
Or add to .vscode/mcp.json:
{
"servers": {
"aws-knowledge": {
"type": "http",
"url": "https://knowledge-mcp.global.api.aws"
}
}
}- Open Settings โ Connectors (Integrations) โ Add Custom Connector.
- Paste the endpoint URL:
https://knowledge-mcp.global.api.aws - No authentication needed โ 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 โ 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 โ MCP Servers โ 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 โ httpUrl for Streamable HTTP, url for legacy SSE:
{
"mcpServers": {
"aws-knowledge": {
"httpUrl": "https://knowledge-mcp.global.api.aws"
}
}
}๐งฐ AWS Knowledge MCP Tools & Schema (5)
| Tool | Safety | Description | Parameters |
|---|---|---|---|
| aws___read_documentation ~681 tok | ๐ข 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 | ๐ข 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 | ๐ข Read | Retrieve a list of all AWS regions. | โ |
| aws___get_regional_availability ~557 tok | ๐ข 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 | ๐ข 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 |
๐ก๏ธ Security, Quality & Context Token Audit
Every tool definition (name + description + input schema) is injected into your LLMโs context on every request โ Estimate per-call LLM token cost โ
- No prompt-injection or hidden-character anomalies detected in tool descriptions
- Streamable HTTP primary endpoint (current 2025-03-26 transport)
- Public read-only-friendly endpoint โ no credentials stored client-side
- Official first-party endpoint operated by the vendor
- Manually verified by RemoteMCP.net
๐ OAuth 2.1 & Security
- Auth type
- None (public)
- Dynamic Client Registration
- โ
- PKCE S256
- โ
- Protected resource metadata
- https://knowledge-mcp.global.api.aws/.well-known/oauth-protected-resource (expected location)
๐งฉ Recommended Agent Skills
๐ AWS Knowledge MCP Endpoint Overview & Security Guide
AWS Knowledge โ Remote MCP Server
AWS's fully-managed public knowledge MCP gives agents access to the latest AWS documentation, API references, What's New posts and architectural guidance across all AWS services. The remote endpoint means there is nothing to install โ point your MCP client at the URL and start calling tools right away. Amazon Web Services operates and versions the server themselves, so tool coverage tracks their API surface as it ships.
Official AWS Knowledge Endpoint & Transport Architecture
- Endpoint URL:
https://knowledge-mcp.global.api.aws - Transport: Streamable HTTP
Streamable HTTP is the current MCP transport (2025-03-26 spec): a single URL accepts JSON-RPC POSTs and may stream responses over SSE, so one endpoint serves both simple and streaming workloads. AWS Knowledge does not publish a separate legacy SSE endpoint, so your client must speak Streamable HTTP.
Authentication, Scopes & Permission Boundaries
AWS Knowledge is public and unauthenticated โ no OAuth, no API key, no headers. Any MCP client can connect and call its tools directly, which also makes it a great endpoint for smoke-testing your own MCP client or proxy.
All 3 cataloged tools are read-only โ AWS Knowledge cannot mutate your account data, which makes it safe to connect broadly.
Common Troubleshooting & Connection Tips
- "Session expired" / stale
Mcp-Session-Idโ just re-sendinitialize; stateless clients can ignore session headers entirely. - Global endpoint operated by AWS; no credentials or session management required.
๐ How to Connect
- Copy the AWS Knowledge endpoint URLThe remote endpoint is https://knowledge-mcp.global.api.aws.
- Add it to your MCP clientClaude Code:
claude mcp add --transport http aws-knowledge https://knowledge-mcp.global.api.aws. Cursor: add"aws-knowledge": { "url": "https://knowledge-mcp.global.api.aws" }undermcpServersin ~/.cursor/mcp.json. Other clients work similarly. - Verify with the online inspectorPaste https://knowledge-mcp.global.api.aws into remotemcp.net/inspector, run initialize and tools/list, and confirm AWS Knowledge's 3 tools respond.
โ FAQ
What is the AWS Knowledge remote MCP endpoint?
The primary endpoint is https://knowledge-mcp.global.api.aws. It is an official first-party server operated by Amazon Web Services, speaking the Streamable HTTP transport.
How do I authenticate with AWS Knowledge?
You don't โ AWS Knowledge is public and unauthenticated. Connect and start calling tools; no OAuth flow or API key is needed.
I'm getting a 401 Unauthorized from AWS Knowledge โ what's wrong?
AWS Knowledge is authless, so a 401 is unusual. Check that you're hitting https://knowledge-mcp.global.api.aws exactly (including the path) and not an API endpoint that requires a different credential.
Which MCP clients work with AWS Knowledge?
Any client that supports remote MCP servers: Cursor, Claude Code (`claude mcp add --transport http aws-knowledge https://knowledge-mcp.global.api.aws`), VS Code Copilot, ChatGPT connectors, Windsurf, Kiro (`~/.kiro/settings/mcp.json`), and Claude Desktop via the `mcp-remote` bridge.
What tools does AWS Knowledge expose?
3 tools are cataloged in this directory โ including `search_documentation`, `read_documentation`, `recommend`. Use our online inspector to fetch the live tool list straight from the endpoint.
๐ Connect Guides
๐ Embed Status Badge in README
Related Servers
Claude Skills's hosted remote MCP server. ClaudeSkills.club's public MCP lets agents search and pull from a catalog of 90,000+ Agent Skills (SKILL.md) โ workflow specs, safety scores and one-line install instructions. It is public and unauthenticated โ connect and call tools immediately.
Cloudflare's free, authless documentation MCP server. Agents can search the full Cloudflare docs corpus โ no account or token required.
Microsoft Learn's hosted remote MCP server. Microsoft's official Learn MCP server streams trusted, up-to-date documentation for Azure, .NET, Microsoft 365 and the full Microsoft technical catalog directly into agent context. It is public and unauthenticated โ connect and call tools immediately.
Cognition Devin's free DeepWiki MCP. Ask questions and read AI-generated wiki documentation for any public GitHub repository โ no auth required.