Is the AWS Knowledge MCP Server official?
Yes. It is built and hosted by AWS and documented in the awslabs MCP project.
@AWS Knowledge MCP Server
Basic information
Transport
streamable-http
Authentication
Check provider docs
Category
Developer Tools
Author
AWS Knowledge MCP Server
The AWS Knowledge MCP Server is a fully managed remote server from AWS. It gives agents up-to-date AWS documentation, API references, regional availability for services and CloudFormation resources, and AWS agent skills. It needs no authentication and is subject to rate limits.
https://knowledge-mcp.global.api.aws/claude mcp add aws-knowledge --transport http https://knowledge-mcp.global.api.aws/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}.
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).
Retrieve a list of all AWS regions.
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.
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`.
The AWS Knowledge MCP Server is a fully managed remote MCP server from AWS that gives AI agents current AWS documentation, API references, regional availability data and AWS agent skills. It requires no authentication and no AWS account.
AWS publishes it as part of the open-source AWS MCP servers project (awslabs), and it is in general availability. Because AWS changes constantly, a model's training data quickly goes stale; this server lets an assistant search and read the live documentation, check whether a service, API or CloudFormation resource exists in a given Region, and load step-by-step AWS skills before it answers or writes infrastructure code.
The endpoint uses Streamable HTTP and needs no credentials. Usage is subject to rate limits and the AWS Site Terms.
https://knowledge-mcp.global.api.aws
claude mcp add --transport http aws-knowledge https://knowledge-mcp.global.api.aws
Open Settings → Connectors → Add custom connector, name it "AWS Knowledge" and paste the URL. There is no sign-in step.
In ~/.cursor/mcp.json:
{
"mcpServers": {
"aws-knowledge-mcp-server": {
"url": "https://knowledge-mcp.global.api.aws"
}
}
}
In .vscode/mcp.json:
{
"servers": {
"aws-knowledge-mcp-server": {
"type": "http",
"url": "https://knowledge-mcp.global.api.aws"
}
}
}
AWS documents a stdio-to-HTTP proxy using fastmcp:
{
"mcpServers": {
"aws-knowledge-mcp-server": {
"command": "uvx",
"args": ["fastmcp", "run", "https://knowledge-mcp.global.api.aws"]
}
}
}
Documentation. aws___search_documentation searches AWS docs by topic, such as reference_documentation, current_awareness (new or announced features), troubleshooting, amplify_docs and CDK content. Each result's context is real page text. aws___read_documentation fetches a full doc page as Markdown; its description tells the model to use it only when search chunks lack the needed detail, such as complete lists.
Regions. aws___list_regions returns all AWS Regions. aws___get_regional_availability reports whether products, service APIs or CloudFormation resources are available, not available or planned in up to 10 Regions; filter values must exactly match AWS catalog names.
Skills. aws___retrieve_skill returns an AWS skill's SKILL.md or one of its files. The skill name must be copied from a search result rather than guessed.
Yes. It is built and hosted by AWS and documented in the awslabs MCP project.
No. The server needs no authentication, and AWS states you can start without an AWS account.
AWS does not list a price for the server. Usage is subject to rate limits and the AWS Site Terms.
No. It works with public AWS knowledge: documentation, regional availability and skills. It has no access to your account.
Yes. Add the URL as a remote HTTP server. For stdio-only clients, use the fastmcp proxy.
Search results come back as verbatim page chunks from AWS's own index, plus structured tools for Regions and availability that a general web search does not provide.
The AWS Knowledge MCP Server remote MCP server is a hosted Model Context Protocol endpoint at https://knowledge-mcp.global.api.aws/, so AI assistants can connect to it without installing or running anything locally.
Add the endpoint https://knowledge-mcp.global.api.aws/ to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.
Authentication requirements for AWS Knowledge MCP Server have not been confirmed in this listing. Check the provider’s documentation before connecting.
AWS Knowledge MCP Server exposes a streamable-http endpoint, the transport used by remote MCP servers and supported by all major MCP clients.
CVE prioritization using exploitation signals, plus agent heartbeat monitoring and state capsules. Some tools use API-key or x402 access.
Pay-per-use data and tools for AI agents: crypto token safety and rug checks, web search with cited answers, page-to-Markdown, up-to-date library docs, package safety, company research and UK/EU open data. 160 tools, 20
App Store keyword research, rank tracking, competitor analysis and authorized performance data.
AdaptlyPost: Schedule and publish social posts to Instagram, TikTok, YouTube, X, Facebook, LinkedIn, Pinterest, Threads, and Bluesky from any MCP client.
Marketing campaign and audience insights from Adobe
Comments