Skip to main content
Glama
Sign In
enesjakozh
SSH MCP Server

SSH MCP Server

by KinoThe-Kafkaesque
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

SSH MCP 서버

대장간 배지

SSH 기능을 제공하는 모델 컨텍스트 프로토콜(MCP) 서버 구현입니다. 이 서버는 MCP 프로토콜을 통한 안전한 원격 액세스 및 실행을 지원합니다.

특징

  • MCP 프로토콜을 사용한 SSH 서버 구현

  • 데이터 지속성을 위한 SQLite 데이터베이스 통합

  • 유형 안전성과 더 나은 개발 경험을 위한 TypeScript 구현

Related MCP server: Remote Command MCP Server

필수 조건

  • Node.js(v16 이상 권장)

  • npm 또는 yarn 패키지 관리자

  • 개발을 위한 TypeScript 지식

설치

Smithery를 통해 설치

Smithery를 통해 Claude Desktop용 SSH 서버를 자동으로 설치하려면:

지엑스피1

수동 설치

  1. 저장소를 복제합니다.

git clone <repository-url>
cd ssh-server

  1. 종속성 설치:

npm install

  1. 프로젝트를 빌드하세요:

npm run build

용법

구성

서버는 SQLite 데이터베이스( ssh.db )를 사용하여 SSH 자격 증명을 저장합니다. 데이터베이스 파일은 서버 시작 시 자동으로 생성됩니다.

도구

서버는 다음과 같은 도구를 제공합니다.

ssh_exec

SSH를 통해 명령을 실행합니다.

입력 매개변수:

  • host : 연결할 호스트입니다. (필수)

  • command : 실행할 명령입니다. (필수)

  • username : SSH 연결에 사용할 사용자 이름입니다. (필수)

  • privateKeyPath : 개인 키 파일의 경로입니다. (필수)

사용 예:

{
    "tool_name": "ssh_exec",
    "arguments": {
        "host": "example.com",
        "command": "ls -l",
        "username": "user",
        "privateKeyPath": "/path/to/private/key"
    }
}

참고: privateKeyPath 는 개인 키 파일에 대한 유효한 경로여야 합니다.

자격 증명 추가

새로운 SSH 자격 증명을 추가합니다.

입력 매개변수:

  • name : 자격 증명의 이름입니다. (필수)

  • host : 연결할 호스트입니다. (필수)

  • username : SSH 연결에 사용할 사용자 이름입니다. (필수)

  • privateKeyPath : 개인 키 파일의 경로입니다. (필수)

사용 예:

{
    "tool_name": "add_credential",
    "arguments": {
        "name": "my_credential",
        "host": "example.com",
        "username": "user",
        "privateKeyPath": "/path/to/private/key"
    }
}

참고: privateKeyPath 는 개인 키 파일에 대한 유효한 경로여야 합니다.

자격 증명 목록

저장된 모든 SSH 자격 증명을 나열합니다.

입력 매개변수:

  • 없음

사용 예:

{
    "tool_name": "list_credentials",
    "arguments": {}
}

자격 증명 제거

저장된 SSH 자격 증명을 제거합니다.

입력 매개변수:

  • name : 제거할 자격 증명의 이름입니다. (필수)

사용 예:

{
    "tool_name": "remove_credential",
    "arguments": {
        "name": "my_credential"
    }
}

서버 시작

npm start

서버는 구성된 포트에서 실행되기 시작합니다(기본 설정은 소스 코드에서 수정할 수 있습니다).

프로젝트 구조

  • src/ - 소스 코드 디렉토리

  • build/ - 컴파일된 JavaScript 출력

  • node_modules/ - 프로젝트 종속성

종속성

  • @modelcontextprotocol/sdk : MCP 프로토콜 구현

  • sqlite3 : SQLite 데이터베이스 드라이버

  • typescript : TypeScript 지원을 위한 개발 종속성

개발

프로젝트를 변경하려면:

  1. src/ 디렉토리에서 변경하세요

  2. 프로젝트를 다시 빌드합니다.

npm run build

  1. 변경 사항을 테스트하려면 서버를 시작하세요.

npm start

특허

아이에스씨

기여하다

  1. 저장소를 포크하세요

  2. 기능 브랜치를 생성하세요

  3. 변경 사항을 커밋하세요

  4. 지점으로 밀어 넣기

  5. 새로운 풀 리퀘스트 만들기

Available Tools

5 tools
add_credentialC

Add a new SSH credential with private key file path

NameRequiredDescriptionDefault
hostYes
nameYes
privateKeyPathYes
usernameYes

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It states it adds a credential but doesn't cover critical aspects: whether this requires admin permissions, if it overwrites existing credentials, error handling (e.g., invalid file paths), or what happens on success (e.g., confirmation message). It mentions 'private key file path' but not how it's stored or used. This leaves significant gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with no wasted words. It's front-loaded with the core action and resource, making it easy to scan. Every part of the sentence contributes directly to the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (a mutation tool for SSH credentials), lack of annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't explain return values, error cases, or behavioral nuances. For a tool that likely involves security-sensitive operations, more context is needed to ensure safe and correct usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only mentions 'private key file path', which maps to one of the four parameters (privateKeyPath). It doesn't explain the other parameters (host, name, username), their purposes, formats, or constraints. The description adds minimal value beyond the schema, failing to address the coverage gap adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Add') and resource ('SSH credential'), specifying it's for a new credential with a private key file path. It distinguishes from siblings like list_credentials (read) and remove_credential (delete), though it doesn't explicitly mention rsync_copy or ssh_exec. The purpose is specific but could be more detailed about what 'add' entails.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing private key file), exclusions, or comparisons to siblings like ssh_exec (which might use credentials). The description implies usage for adding SSH credentials but lacks contextual advice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_credentialsB

List all stored SSH credentials

NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It states what the tool does but doesn't describe how it behaves: no information about return format (e.g., list structure, credential details), pagination, error conditions, or authentication requirements. This is a significant gap for a tool that accesses 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste. It's front-loaded with the core action and resource, making it easy to parse. Every word earns its place without redundancy or unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of listing credentials (sensitive data access) with no annotations and no output schema, the description is incomplete. It doesn't explain what information is returned (e.g., credential IDs, types, metadata), security implications, or how to handle the results, leaving critical gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the schema already fully documents the input. The description appropriately doesn't add parameter details, and the baseline for 0 parameters is 4. It could be 5 if it explicitly stated 'no parameters required' but this is minor.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('all stored SSH credentials'), making the purpose immediately understandable. However, it doesn't differentiate from potential sibling tools like 'get_credentials' or 'search_credentials' if they existed, which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'add_credential' or 'remove_credential'. It doesn't mention prerequisites, context, or exclusions, leaving the agent to infer usage from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

remove_credentialC

Remove a stored SSH credential

NameRequiredDescriptionDefault
nameYes

TDQS

C2.8/5.0
Behavior2/5

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 performs a removal operation, implying mutation, but doesn't address critical aspects like whether this is destructive, irreversible, requires specific permissions, or what happens on success/failure. This is a significant gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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, with zero waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (a mutation operation with no annotations, 0% schema coverage, and no output schema), the description is incomplete. It lacks details on behavior, parameters, return values, and error handling, making it inadequate 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.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the single parameter 'name' is undocumented in the schema. The description adds no semantic information about this parameter, such as what 'name' refers to (e.g., credential identifier), its format, or examples. It fails to compensate for the schema's lack of documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Remove') and resource ('stored SSH credential'), making the purpose immediately understandable. It doesn't explicitly distinguish from siblings like 'add_credential' or 'list_credentials', but the verb 'Remove' inherently differentiates it from those operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'add_credential' or 'list_credentials'. The description lacks context about prerequisites (e.g., needing an existing credential to remove) or exclusions, leaving usage entirely implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

rsync_copyC

Copy files/directories between local and remote server via rsync

NameRequiredDescriptionDefault
credentialNameYesName of the stored credential to use
directionYesDirection of copy (toRemote or fromRemote)
localPathYesPath on the local machine
remotePathYesPath on the remote server

TDQS

C2.9/5.0
Behavior2/5

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 mentions copying via rsync but doesn't cover critical aspects like whether it overwrites files, handles symlinks, requires specific permissions, has rate limits, or what happens on errors. This leaves significant gaps for a file operation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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 any fluff. It's front-loaded and every word contributes to understanding the core functionality.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of file copying with rsync, no annotations, and no output schema, the description is inadequate. It lacks details on behavior, error handling, and output format, which are essential for safe and effective use of this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no additional meaning beyond implying the need for paths and direction, which is already clear from the schema. This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Copy files/directories') and the mechanism ('via rsync'), specifying both the resource (files/directories) and the scope (between local and remote server). It doesn't explicitly differentiate from sibling tools like ssh_exec, but the focus on copying distinguishes it from credential management tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like ssh_exec for other operations, nor does it mention prerequisites such as needing stored credentials. It only states what the tool does, not when or why to choose it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

ssh_execC

Execute command over SSH using private key file path

NameRequiredDescriptionDefault
commandYes
hostYes
privateKeyPathYes
usernameYes

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the authentication mechanism but doesn't describe execution behavior (e.g., synchronous/asynchronous, timeout handling, error propagation, output capture, or security implications). For a potentially destructive remote execution tool, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that communicates the core functionality without unnecessary words. It's appropriately sized for a tool with this complexity level and gets straight to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a remote execution tool with 4 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what happens during execution, how output is returned, error handling, security considerations, or typical use patterns. The agent would need to guess about important behavioral aspects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage for all 4 parameters, the description doesn't add any semantic information beyond what's implied by parameter names. It mentions 'private key file path' which aligns with the privateKeyPath parameter name but doesn't explain format expectations, path resolution, or relationships between parameters like host and username.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Execute command') and resource ('over SSH using private key file path'), making the purpose immediately understandable. It doesn't distinguish from sibling tools like rsync_copy or credential management tools, but it's specific enough to understand what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like rsync_copy or when SSH execution is appropriate. It mentions the authentication method (private key file path) but doesn't explain prerequisites, error conditions, or typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 5 tool updatesv1.0.0
    • First observedadd_credential
    • First observedlist_credentials
    • First observedremove_credential
    • First observedrsync_copy
    • First observedssh_exec
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: credential management (add, list, remove) is separate from remote operations (rsync, ssh_exec). The descriptions clearly differentiate between managing stored credentials and performing remote actions, eliminating any potential for misselection.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with snake_case: add_credential, list_credentials, remove_credential, rsync_copy, ssh_exec. The naming is predictable and readable throughout, with no deviations or mixed conventions.

Tool Count5/5

With 5 tools, this server is well-scoped for SSH operations. Each tool earns its place by covering essential functions: credential management (3 tools) and remote execution/copy (2 tools). This count is appropriate for the domain without being too thin or heavy.

Completeness4/5

The tool surface covers core SSH workflows: credential lifecycle (add, list, remove) and remote operations (execute, copy). A minor gap exists in credential updates (e.g., update_credential), but agents can work around this by removing and re-adding. Overall, the set provides good coverage for the stated purpose.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP SSH Server

    shaike1
    A
    license
    Not graded
    quality
    F
    maintenance
    A secure SSH server implementation for Model Context Protocol that enables remote command execution and file operations, supporting both password and key-based authentication.
    58
    MIT

  • SSH MCP Server

    mfangtao
    A
    license
    B
    quality
    D
    maintenance
    A server that enables remote command execution over SSH through the Model Context Protocol (MCP), supporting both password and private key authentication.
    1
    7 npm
    2
    MIT

  • SSH MCP Server

    vilasone455
    F
    license
    A
    quality
    D
    maintenance
    A local Model Context Protocol server that allows LLMs to securely execute shell commands on remote Linux and Windows systems via SSH connections.
    6
    7 npm
    2
    -

Appeared in Searches