How to Connect AWS Knowledge Remote MCP to Cline
Add Amazon Web Services's remote MCP server to Cline in about a minute.
Step-by-step
- Open Cline MCP settingsCline sidebar โ MCP Servers โ Configure MCP Servers โ this opens
cline_mcp_settings.json. - Paste the configAdd the
mcpServersentry shown above (Streamable HTTPurl+ optionalheaders). - AuthorizeNo authentication needed โ AWS Knowledge is public.
- VerifyVerify in the browser: paste
https://knowledge-mcp.global.api.awsinto remotemcp.net/inspector and run initialize + tools/list.
Troubleshooting OAuth / 401
- A
401 Unauthorizedon first connect is normal โ the endpoint is OAuth-protected; let Cline finish the browser consent flow. - If the consent window never opens, remove and re-add the server, then retry.
- Check the exact challenge at our OAuth debugger.
- Run the live endpoint through the online inspector to see the raw JSON-RPC exchange.
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"
}
}
}Tools exposed by AWS Knowledge (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 |
Connect AWS Knowledge to another client
Other servers for Cline
GitHub's official remote MCP server hosted at api.githubcopilot.com. Gives AI agents first-party access to repositories, issues, pull requests and code search.
Notion's official hosted MCP server. Agents can search your workspace, read and create pages, and query databases over Streamable HTTP or SSE.
Linear's official remote MCP server. Agents can search, create and update issues and query your team's workflow over Streamable HTTP or SSE.
Figma's official remote MCP server. Agents can pull design context, variables, Code Connect mappings and screenshots from your Figma files.
Stripe's official remote MCP server at mcp.stripe.com. Agents can query customers, payment intents and subscriptions and invoke Stripe API operations with OAuth.
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.