AWS Cognito MCP Server
AWS Cognito MCP 서버
인증 및 사용자 관리를 위해 AWS Cognito에 연결하는 모델 컨텍스트 프로토콜(MCP) 서버 구현입니다. 이 서버는 가입, 로그인, 비밀번호 관리 등 사용자 인증 흐름을 위한 도구 세트를 제공합니다.
필수 조건
Cognito 사용자 풀이 구성된 AWS 계정
Node.js 18 이상
Related MCP server: Remote MCP Server with GitHub OAuth
설치
지엑스피1
AWS Cognito 구성
AWS 콘솔에 로그인하고 Amazon Cognito로 이동합니다.
사용자 풀을 생성하거나 기존 사용자 풀을 사용하세요
사용자 풀 ID와 앱 클라이언트 ID를 기록하세요.
다음 값을 환경 변수 또는 .env 파일로 설정합니다(Claude 코드를 사용할 때만 .env 파일이 필요하고, Claude 데스크톱에서는 필요하지 않습니다).
AWS_COGNITO_USER_POOL_ID=your-user-pool-id
AWS_COGNITO_USER_POOL_CLIENT_ID=your-app-client-id사용 가능한 도구
도구 이름 | 설명 | 매개변수 |
| 새로운 사용자 등록 |
|
| 확인 코드로 계정을 확인하세요 |
|
| 사용자 인증 |
|
| 현재 사용자 로그아웃 | 없음 |
| 현재 로그인한 사용자 가져오기 | 없음 |
| 비밀번호 재설정 코드 요청 |
|
| 인증코드로 비밀번호 재설정 |
|
| 로그인한 사용자의 비밀번호 변경 |
|
| 인증 토큰을 새로 고칩니다. | 없음 |
| 사용자 프로필 속성 업데이트 |
|
| 현재 로그인한 사용자 삭제 | 없음 |
| 계정 확인 코드 재전송 |
|
| MFA에 대한 TOTP 확인 |
|
검사기는 브라우저에서 디버깅 도구에 액세스할 수 있는 URL을 제공합니다.
Claude Desktop과 함께 사용
npx 작동하려면 시작하기 전에 데스크톱에 Node.js가 설치되어 있는지 확인하세요.
이동: 설정 > 개발자 > 구성 편집
claude_desktop_config.json에 다음을 추가하세요.
{
"mcpServers": {
"aws-cognito-mcp-server": {
"command": "/path/to/mcp-server-aws-cognito/build/index.js",
"env": {
"AWS_COGNITO_USER_POOL_ID": "your-user-pool-id",
"AWS_COGNITO_USER_POOL_CLIENT_ID": "your-app-client-id"
}
}
}
}Claude Code와 함께 사용
Claude Code는 Claude용 명령줄 인터페이스입니다. Claude Code와 함께 이 MCP 서버를 사용하려면 다음 단계를 따르세요.
Claude Code 문서의 지침에 따라 Claude Code를 설치하세요.
Claude Code에 MCP 서버를 추가합니다.
claude mcp add "aws-cognito-mcp" npx tsx index.ts추가되었는지 확인하세요:
claude mcp listMCP 서버로 Claude를 실행하세요.
claude개발
자동 재빌드를 사용한 개발의 경우:
npm run watch디버깅
MCP 서버는 stdio를 통해 통신하므로 디버깅이 어려울 수 있습니다. MCP Inspector를 사용하면 더 나은 가시성을 확보할 수 있습니다.
npm run inspector이제 Claude와 함께 AWS Cognito 인증 도구를 사용할 수 있습니다!
Available Tools
13 toolschange_passwordD
| Name | Required | Description | Default |
|---|---|---|---|
| oldPassword | Yes | ||
| newPassword | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
confirm_code_from_email_for_signUpD
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes | ||
| confirmationCode | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
delete_userD
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getCurrentUserD
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
refresh_sessionD
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
resend_confirmation_codeD
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
reset_password_send_codeD
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
reset_password_veryify_codeD
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes | ||
| code | Yes | ||
| newPassword | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
sign_inD
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes | ||
| password | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
sign_outD
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
sign_upD
| Name | Required | Description | Default |
|---|---|---|---|
| password | Yes | ||
| Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
update_user_attributesD
| Name | Required | Description | Default |
|---|---|---|---|
| attributes | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
verify_software_tokenD
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes | ||
| totpCode | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
Most tools have distinct purposes targeting specific Cognito operations like sign_in, sign_up, change_password, and delete_user. However, reset_password_send_code and reset_password_veryify_code could potentially be confused with resend_confirmation_code or confirm_code_from_email_for_signUp due to overlapping 'code' terminology, though their contexts differ.
The naming is mostly snake_case with clear verb_noun patterns (e.g., sign_in, delete_user), but there are inconsistencies: getCurrentUser uses camelCase instead of snake_case, and verify_software_token is less descriptive compared to others. This mixed style reduces predictability.
With 13 tools, this is well-scoped for an AWS Cognito server, covering essential user management and authentication workflows. Each tool appears to serve a specific function without obvious bloat, making the count appropriate for the domain.
The tool set provides good coverage of core Cognito operations, including user lifecycle (sign-up, sign-in, update, delete), password management, and session handling. Minor gaps might include admin functions or multi-factor authentication setup, but basic workflows are well-supported.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Model Context Protocol server for Studex tools, notifications, and profile integrations
A Model Context Protocol (MCP) server for Selise Blocks Cloud integration
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A Model Context Protocol server for Wix AI tools
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that requires user authentication via Auth0 before enabling secure API access on behalf of the authenticated user.
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that supports remote connections and authenticates users via GitHub OAuth, allowing them to access tools based on their GitHub identity.
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables management of Keycloak users and realms through a standardized interface, providing tools for user creation, deletion, role assignment, and group management.94813MIT
- FlicenseCqualityDmaintenanceA Model Context Protocol server demonstrating user management capabilities with tools for creating, retrieving, and generating random user data.2
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gitCarrot/mcp-server-aws-cognito'
If you have feedback or need assistance with the MCP directory API, please join our Discord server