AWS Knowledge MCP server

Endpoint: https://knowledge-mcp.global.api.aws · Authentication: No auth

Searches and reads AWS documentation, API references, What's New posts, and regional service availability. No authentication is required.

Test it live Run the release-readiness report

How do I authenticate?

Add the endpoint directly in your client. The catalog records no authentication requirement; no OAuth sign-in or API key is configured in this setup. The live server may change.

Authentication and connection guide

Connection specification

Remote endpoint: https://knowledge-mcp.global.api.aws
Live-validated endpoint: https://knowledge-mcp.global.api.aws/
Browser access: Not yet measured
Declared MCP transport: Streamable HTTP
Live-validated MCP transport: Streamable HTTP — Observed by the latest catalog validation
Declared authentication: No authentication
Detected authentication: No authentication detected or retained from publisher evidence
Protocol lifecycle: Stateful MCP · 2025-03-26
Category: Documentation

Product documentation · Source repository · Official listing documentation

More Documentation MCP servers · Browse all MCP servers · Test this endpoint in the MCP Playground

Authorization setup

No app registration needed

This catalog entry does not require authorization or provider app registration.

Connect it

Live-validated endpoint: https://knowledge-mcp.global.api.aws/ · Streamable HTTP. No authentication is required by the catalog listing.

Agent prompt for Claude Code or Codex

Add the AWS Knowledge MCP server to my MCP client configuration and verify that it works.

What it is: Searches and reads AWS documentation, API references, What's New posts, and regional service availability. No authentication is required.
Server URL: https://knowledge-mcp.global.api.aws/
Transport: Streamable HTTP (remote MCP server, no local install).
Authentication: none. The server accepts connections without credentials.
Tools (5, as last observed by mcptest): aws___get_regional_availability, aws___list_regions, aws___read_documentation, aws___retrieve_skill, aws___search_documentation.
Reference: https://mcptest.io/servers/aws-knowledge/

Steps:
1. Work out which MCP client I use (Claude Code, Codex, Cursor, VS Code or another) and add the server under the name "aws-knowledge" in that client's MCP configuration, user scope unless I ask otherwise.
   Claude Code: claude mcp add --transport http --scope user 'aws-knowledge' 'https://knowledge-mcp.global.api.aws/'
   Codex: codex mcp add 'aws-knowledge' --url 'https://knowledge-mcp.global.api.aws/'
   Other clients: use the setup for that client on the reference page.
2. Never write a credential value into a file that could be committed; reference an environment variable or the client's secret store, and ask me for any value you need.
3. Verify: connect to the server and call tools/list. Confirm the tools above are listed, and report any sign-in step I still have to complete.

Claude Code setup

Run in a terminal. This user-scoped entry is available across projects.

claude mcp add --transport http --scope user 'aws-knowledge' 'https://knowledge-mcp.global.api.aws/'

Codex CLI setup

Run in a terminal; Codex stores the entry in ~/.codex/config.toml.

codex mcp add 'aws-knowledge' --url 'https://knowledge-mcp.global.api.aws/'

Cursor setup

Add to .cursor/mcp.json for this project, or ~/.cursor/mcp.json for all projects.

{
  "mcpServers": {
    "aws-knowledge": {
      "url": "https://knowledge-mcp.global.api.aws/"
    }
  }
}

VS Code setup

Add to .vscode/mcp.json, or run “MCP: Open User Configuration” for a private user-level entry.

{
  "servers": {
    "aws-knowledge": {
      "type": "http",
      "url": "https://knowledge-mcp.global.api.aws/"
    }
  }
}

Claude setup

Add the endpoint above in Claude:

Customize > Connectors > Add custom connector
Team/Enterprise: Organization settings > Connectors > Add > Custom > Web

Claude Desktop setup

Add the endpoint above in Claude Desktop:

Remote: Customize > Connectors (same as claude.ai)
Local: Settings > Developer > Edit Config, or Settings > Extensions for .mcpb files
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), local servers only

ChatGPT setup

Add the endpoint above in ChatGPT:

ChatGPT web: Plugins > Add custom MCP server, then configure authentication and accept the risk warning

Windsurf setup

Add the endpoint above in Windsurf:

~/.config/devin/mcp_config.json (%APPDATA%\devin\mcp_config.json on Windows), serverUrl or url
Cascade panel > ... > MCPs > Open MCP config file

Gemini CLI setup

Add the endpoint above in Gemini CLI:

gemini mcp add --transport http <name> <url>
~/.gemini/settings.json (user) or .gemini/settings.json (project), mcpServers

MCP SDK setup

Add the endpoint above in MCP SDK:

Programmatic: new Client(...).connect(new StreamableHTTPClientTransport(url))

Client compatibility

Client	Status	Why
Claude Code	Supported	Claude Code supports Streamable HTTP servers and servers without authentication.
Codex	Partial	Codex's documentation does not state support for servers without authentication.
Cursor	Supported	Cursor supports Streamable HTTP servers and servers without authentication.
VS Code	Supported	VS Code supports Streamable HTTP servers and servers without authentication.
Claude	Supported	Claude supports Streamable HTTP servers and servers without authentication.
Claude Desktop	Supported	Claude Desktop supports Streamable HTTP servers and servers without authentication.
ChatGPT	Partial	Stateful routing needs operational care: ChatGPT can preserve MCP sessions, but the deployment must route a session consistently and retain its state.
Windsurf	Partial	Windsurf's documentation does not state support for servers without authentication.
Gemini CLI	Supported	Gemini CLI supports Streamable HTTP servers and servers without authentication.
MCP SDK	Supported	MCP SDK supports Streamable HTTP servers and servers without authentication.

Computed from this server's validated transport, protocol and authentication against documented client support. Checks the catalog has not observed are not counted.

Similar servers

Context7 — Context7 provides up-to-date, version-specific library documentation and code examples directly from the source. No authentication
DeepWiki — DeepWiki provides conversational, up-to-date documentation for public GitHub repositories. No authentication
MDN — Open remote MCP server for MDN web documentation, search, and browser compatibility data. No authentication
Cloudflare Docs — Searches Cloudflare's developer documentation for reference material on Workers, R2, D1, DNS, Zero Trust, and other Cloudflare products. No authentication is required. No authentication
Microsoft Learn — Searches and fetches Microsoft Learn documentation and official code samples for Azure, .NET, Microsoft 365, and other Microsoft products. No authentication is required. No authentication
Google Developer Knowledge — Searches, retrieves, and answers questions from Google developer documentation for Firebase, Google Cloud, Android, Maps, and other Google platforms. Requires a Google Cloud API key with the Developer Knowledge API enabled, sent in the X-Goog-Api-Key header. API key

Guides for this server

Watch this server for breaking changes

Share and embed

Maintain AWS Knowledge? Embed this badge in your README. It follows the latest catalog validation result and links to this server profile.

Markdown

[![Tested on mcptest.io](https://mcptest.io/badge/server/aws-knowledge.svg)](https://mcptest.io/servers/aws-knowledge/)

HTML

<a href="https://mcptest.io/servers/aws-knowledge/"><img src="https://mcptest.io/badge/server/aws-knowledge.svg" alt="Tested on mcptest.io"></a>

reStructuredText

.. image:: https://mcptest.io/badge/server/aws-knowledge.svg
   :alt: Tested on mcptest.io
   :target: https://mcptest.io/servers/aws-knowledge/

Latest validation evidence

Validation status: Online when last tested
Validation checked at: Oct 26, 2026 at 11:06 AM
Validation detail: Negotiated stateful MCP 2025-03-26 at https://knowledge-mcp.global.api.aws/; detected transport streamable-http; authentication none

Tool inventory

What the catalog validator observed on Oct 26, 2026 at https://knowledge-mcp.global.api.aws/ without credentials. The live server may have changed since; connect in the Playground for the current list.

Tools provided by AWS Knowledge 5

Some details were sanitized for public display.

aws___get_regional_availabilityNo outputSchema
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
Input filters?: array, next_token?: string, region?: string, regions?: array, resource_type: string
- filters?: arrayoptional
  Use exact AWS product or sub-feature name. - product: 'Amazon Bedrock' (service), or sub-features like 'Comprehend Auto Scaling', 'Latency-Based Routing', 'PrivateLink Support'. When the user names a specific sub-feature, filter on the sub-feature -- do NOT generalize to the parent service ('Amazon Comprehend'); that returns availability for the wrong scope. - api: 'SdkServiceId+Operation' (e.g. 'CloudFormation+CreateStack', 'IAM+GetSSHPublicKey') or 'SdkServiceId' (e.g. 'EC2'). Use a literal '+' between service and operation -- not space, colon, or hyphen. - cfn: 'AWS::EC2::Instance', 'AWS::L
- next_token?: stringoptional
  Pagination token. Single-region, no filters only.
- region?: stringoptional
  Unused; use `regions`.
- regions?: arrayoptional
  AWS region codes (max 10). Multi-region requires `filters`; single-region supports `next_token`.
- resource_type: stringrequired
  Required: 'product' | 'api' | 'cfn'.
aws___list_regionsNo outputSchema
Retrieve a list of all AWS regions.
Input No parameters
aws___read_documentationNo outputSchema
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 exac
Input requests?: array
- requests?: arrayoptional
  List of `{url, max_length?, start_index?}`. Batch 2-5.
aws___retrieve_skillNo outputSchema
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`.
Input file?: string, skill_name: string
- file?: stringoptional
  Optional file path within the skill, copied as cited (e.g. `references/architecture.md`). Don't add or strip a `references/` prefix. Omit for SKILL.md.
- skill_name: stringrequired
  Required. Exact `skill_name` from a search_documentation result, copied verbatim. Do not invent or modify.
aws___search_documentationNo outputSchema
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_d
Input limit?: integer, search_phrase: string, topics?: array
- limit?: integeroptional
  Maximum number of results to return (default 4).
- search_phrase: stringrequired
  Keywords; preserve exact error strings and all task terms verbatim.
- topics?: arrayoptional
  Up to 3 from: reference_documentation, current_awareness, troubleshooting, amplify_docs, cdk_docs, cdk_constructs, cloudformation, agent_skills, strands_docs, general. Default ["general"].