AI 에이전트가 인증 앱과 상호 작용할 수 있도록 지원하는 안전한 MCP(모델 컨텍스트 프로토콜) 서버입니다. 2FA 코드와 비밀번호에 원활하게 접근할 수 있도록 하여 AI 에이전트가 보안을 유지하면서 자동 로그인 프로세스를 지원할 수 있도록 합니다. 이 도구는 AI 비서와 보안 인증 간의 간극을 메워 다양한 플랫폼과 웹사이트에서 자격 증명을 더욱 쉽게 관리할 수 있도록 합니다.
AI 에이전트의 통합 채팅 인터페이스(예: Cursor의 에이전트 모드)를 엽니다.
AI 에이전트에게 원하는 웹사이트와 계정에 대한 2FA 코드나 비밀번호를 검색해 달라고 요청하세요.
AI 에이전트는 이러한 자격 증명을 안전하게 가져온 다음 이를 활용하여 로그인 프로세스를 자동화할 수 있습니다.
이 MCP 서버는 Authenticator 앱 · 2FA 와 함께 사용하도록 특별히 설계되었습니다.
Related MCP server: ssh-mcp-server
많은 AI 클라이언트는 구성 파일을 사용하여 MCP 서버를 관리합니다.
authenticator-mcp 도구는 구성 파일에 다음을 추가하여 구성할 수 있습니다.
참고: 이 서버를 사용하려면 인증 앱 액세스 토큰을 생성해야 합니다. 인증 앱 액세스 토큰 생성 방법은 여기에서 확인할 수 있습니다.
지엑스피1
{
"mcpServers": {
"Authenticator App MCP": {
"command": "cmd",
"args": ["/c", "npx", "-y", "authenticator-mcp", "--access-token=YOUR-KEY"]
}
}
}또는 env 필드에 AUTHENTICATOR_ACCESS_TOKEN 설정할 수 있습니다.
Authenticator App · 2FA 데스크톱 버전을 실행하세요.
Settings 으로 이동하여 MCP Server 섹션을 찾으세요.
MCP 서버를 ON 활성화한 다음 액세스 토큰을 생성합니다.
액세스 토큰은 한 번만 표시됩니다. 즉시 복사하여 MCP 클라이언트 구성에 추가하세요.
Retrieve the current 2FA code for a username when logging into a website.
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes | The username or email of the account you need to login, e.g. "john.doe@example.com" | |
| website | Yes | The domain name of the website you need to login, e.g. "github.com" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves a 2FA code, implying a read operation, but lacks details on security implications, rate limits, authentication requirements, or response format. This is a significant gap for a tool handling sensitive data.
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?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is appropriately sized and front-loaded, making it easy to understand quickly.
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?
For a tool handling sensitive 2FA codes with no annotations and no output schema, the description is incomplete. It lacks critical details like security constraints, error handling, or return value format, leaving gaps in understanding how to use it effectively in context.
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?
Schema description coverage is 100%, so the schema fully documents both parameters (username and website). The description adds minimal value beyond the schema, as it only implies the parameters are used for login context without providing additional syntax or format details.
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?
The description clearly states the action ('Retrieve') and resource ('current 2FA code for a username'), specifying the context ('when logging into a website'). It distinguishes from sibling tools like get_account_list (lists accounts) and get_password (retrieves passwords), though it doesn't explicitly name them for comparison.
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?
The description mentions 'when logging into a website,' which provides some context, but it doesn't offer explicit guidance on when to use this tool versus alternatives like get_password for non-2FA logins or prerequisites. No exclusions or detailed scenarios are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the accounts can be used when logging into a website.
| Name | Required | Description | Default |
|---|---|---|---|
| website | Yes | The domain name of the website you need to login, e.g. "github.com" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves accounts, implying a read-only operation, but doesn't clarify aspects like authentication requirements, rate limits, data sensitivity, or what 'accounts' entails (e.g., usernames, emails). This leaves key behavioral traits unspecified for a tool handling login-related data.
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?
The description is a single, straightforward sentence that efficiently conveys the core purpose without unnecessary words. It's appropriately sized for a simple tool, though it could be slightly more structured by front-loading key details more explicitly. There's minimal waste, earning a high score for conciseness.
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?
Given the tool's low complexity (1 parameter, no output schema, no annotations), the description is adequate but incomplete. It covers the basic purpose but lacks details on behavioral aspects like security or usage guidelines. Without annotations or output schema, the description should do more to compensate, but it provides a minimal viable explanation, scoring at the threshold of adequacy.
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?
The input schema has 100% description coverage, with the 'website' parameter fully documented as 'The domain name of the website you need to login, e.g. "github.com".' The description adds no additional parameter semantics beyond this, so it meets the baseline of 3 where the schema does the heavy lifting without compensating for gaps.
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?
The description clearly states the tool's purpose: 'Retrieve the accounts can be used when logging into a website.' It specifies the action ('retrieve') and resource ('accounts'), and the context ('when logging into a website') is clear. However, it doesn't explicitly differentiate from sibling tools like get_2fa_code or get_password, which prevents a score of 5.
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?
The description provides minimal guidance by mentioning 'when logging into a website,' which implies usage context but lacks explicit when-to-use rules or alternatives. There's no mention of when to use this tool versus get_2fa_code or get_password, or any prerequisites or exclusions, leaving significant gaps in usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the password for a username when logging into a website.
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes | The username or email of the account you need to login, e.g. "john.doe@example.com" | |
| website | Yes | The domain name of the website you need to login, e.g. "github.com" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves a password, implying a read operation, but doesn't cover critical aspects such as authentication requirements, security implications (e.g., if it's stored securely), rate limits, or what happens on failure (e.g., if the password isn't found). This leaves significant gaps for a tool handling sensitive data.
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?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and wastes no space, making it easy to parse quickly while conveying the essential action.
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?
Given the complexity of handling passwords (sensitive data) and the lack of annotations and output schema, the description is incomplete. It doesn't address security behaviors, error handling, or return values, which are crucial for such a tool. The description alone is insufficient for safe and effective use by an AI agent.
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?
The input schema has 100% description coverage, with clear documentation for both parameters ('username' and 'website'), including examples. The description adds no additional parameter semantics beyond what the schema provides, such as format details or constraints. Given the high schema coverage, a baseline score of 3 is appropriate as the schema does the heavy lifting.
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?
The description clearly states the tool's purpose with a specific verb ('Retrieve') and resource ('password for a username'), making it understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_2fa_code' or 'get_account_list', which would require mentioning it's specifically for password retrieval rather than other authentication data or account listings.
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?
The description provides a basic context ('when logging into a website'), but it lacks explicit guidance on when to use this tool versus alternatives like 'get_2fa_code' for two-factor codes or 'get_account_list' for listing accounts. There's no mention of prerequisites, exclusions, or specific scenarios, leaving usage unclear relative to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_2fa_codeget_account_listget_passwordScored across 3 tools
Each tool has a clearly distinct purpose: get_2fa_code retrieves time-based codes, get_account_list lists available accounts, and get_password retrieves passwords. There is no overlap in functionality, making tool selection unambiguous for an agent.
All tool names follow a consistent verb_noun pattern with 'get_' prefix (get_2fa_code, get_account_list, get_password). The naming is uniform and predictable, using snake_case throughout without any deviations.
With only 3 tools, the server feels thin for an authenticator app domain that might benefit from operations like adding/removing accounts or updating credentials. While the tools cover core retrieval needs, the count is borderline minimal for comprehensive functionality.
The toolset is severely incomplete for an authenticator app, lacking any write operations such as adding accounts, updating passwords, or managing 2FA settings. Agents can only retrieve data, leading to dead ends for common workflows like account setup or credential changes.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
MCP server teaching AI agents to implement TideCloak: auth, E2EE, IGA, security analysis
