Skip to main content
Glama
enesjakozh
auchenberg

Claude Code MCP

by auchenberg
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

클로드 코드 MCP

Claude Code MCP는 Claude Code 를 모델 컨텍스트 프로토콜(MCP) 서버로 구현한 것입니다. 이 프로젝트를 통해 표준화된 MCP 인터페이스를 통해 Claude Code의 강력한 소프트웨어 엔지니어링 기능을 활용할 수 있습니다.

⚠️ 면책 조항 ⚠️

Claude Code MCP는 Claude Code 코드베이스를 분석하고 MCP 서버를 생성하라는 요청을 받은 DevinAI가 자동 생성한 프로젝트입니다.

이건 제가 누구에게도 권하지 않는 개념 증명이에요.

클로드 코드란 무엇인가?

Claude Code는 Claude를 기반으로 하는 Anthropic의 소프트웨어 엔지니어링 작업용 CLI 도구입니다. 개발자에게 다음과 같은 기능을 제공하는 도구와 기능을 제공합니다.

  • 코드 생성 및 편집

  • 코드 검토 및 분석

  • 디버깅 및 문제 해결

  • 파일 시스템 작업

  • 쉘 명령 실행

  • 프로젝트 탐색 및 이해

원래 구현은 Claude의 API와 상호 작용하기 위한 프롬프트와 도구를 정의하는 JavaScript 모듈로 제공됩니다.

Related MCP server: MCP Tool

MCP란 무엇인가요?

모델 컨텍스트 프로토콜(MCP)은 다양한 모델과 제공업체 간에 일관된 상호작용 패턴을 지원하는 AI 모델을 위한 표준화된 인터페이스입니다. MCP는 다음을 정의합니다.

  • 도구 : 모델이 작업을 수행하기 위해 호출할 수 있는 함수

  • 리소스 : 모델이 액세스할 수 있는 외부 데이터

  • 프롬프트 : 미리 정의된 대화 템플릿

Claude Code를 MCP 서버로 구현하면 모든 MCP 호환 클라이언트에서 해당 기능을 사용할 수 있으므로 상호 운용성과 유연성이 더욱 향상됩니다.

특징

  • MCP 서버로서 Claude Code 기능의 전체 구현

  • 파일 작업, 셸 명령 및 코드 분석을 위한 도구를 제공합니다.

  • 파일 시스템 및 환경 정보에 액세스하기 위한 리소스를 공개합니다.

  • 일반 CLI 상호 작용 및 코드 검토에 대한 프롬프트가 포함되어 있습니다.

  • 모든 MCP 클라이언트와 호환 가능

  • 완전한 유형 안전성을 갖춘 TypeScript 구현

설치

지엑스피1

용법

독립형 서버로 실행

# Start the server
npm start

MCP 클라이언트와 함께 사용

Claude Code MCP는 모든 MCP 클라이언트와 함께 사용할 수 있습니다. MCP TypeScript SDK를 사용하여 연결하는 방법의 예는 다음과 같습니다.

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

const transport = new StdioClientTransport({
  command: "node",
  args: ["dist/index.js"]
});

const client = new Client(
  {
    name: "example-client",
    version: "1.0.0"
  },
  {
    capabilities: {
      prompts: {},
      resources: {},
      tools: {}
    }
  }
);

await client.connect(transport);

// Use Claude Code through MCP
const result = await client.callTool({
  name: "bash",
  arguments: {
    command: "ls -la"
  }
});

console.log(result);

사용 가능한 도구

Claude Code MCP는 다음과 같은 도구를 제공합니다.

  • bash : 보안 제한 및 시간 초과 옵션을 사용하여 셸 명령 실행

  • readFile : 줄 오프셋 및 제한에 대한 옵션을 사용하여 파일 시스템에서 파일을 읽습니다.

  • listFiles : 자세한 메타데이터와 함께 파일 및 디렉토리를 나열합니다.

  • searchGlob : glob 패턴과 일치하는 파일을 검색합니다.

  • grep : 정규식 패턴을 지원하는 파일에서 텍스트 검색

  • think : 복잡한 문제를 생각해내기 위한 무작동 도구

  • codeReview : 버그, 보안 문제 및 모범 사례에 대한 코드 분석 및 검토

  • editFile : 지정된 내용으로 파일을 생성하거나 편집합니다.

도구 세부 정보

세게 때리다

{
  command: string;  // The shell command to execute
  timeout?: number; // Optional timeout in milliseconds (max 600000)
}

bash 도구에는 curl , wget 등과 같이 잠재적으로 위험한 명령의 실행을 방지하는 보안 제한이 포함되어 있습니다.

파일 읽기

{
  file_path: string; // The absolute path to the file to read
  offset?: number;   // The line number to start reading from
  limit?: number;    // The number of lines to read
}

검색글로브

{
  pattern: string;  // The glob pattern to match files against
  path?: string;    // The directory to search in (defaults to current working directory)
}

그렙

{
  pattern: string;   // The regular expression pattern to search for
  path?: string;     // The directory to search in (defaults to current working directory)
  include?: string;  // File pattern to include in the search (e.g. "*.js", "*.{ts,tsx}")
}

사용 가능한 리소스

  • 파일 : 파일 내용 접근 ( file://{path} )

    • 적절한 오류 처리를 통해 파일 내용에 직접 액세스할 수 있습니다.

    • 지정된 파일의 전체 텍스트 내용을 반환합니다.

  • 디렉토리 : 디렉토리 내용 나열 ( dir://{path} )

    • 파일 정보 객체의 JSON 배열을 반환합니다.

    • 각 객체에는 이름, 경로, 디렉토리, 크기 및 수정 날짜가 포함됩니다.

  • 환경 : 시스템 환경 정보 가져오기( env://info )

    • 시스템 환경에 대한 정보를 반환합니다.

    • Node.js 버전, npm 버전, OS 정보 및 환경 변수가 포함됩니다.

사용 가능한 프롬프트

  • generalCLI : Claude Code를 위한 일반 CLI 프롬프트

    • Claude가 CLI 도구 역할을 할 수 있도록 포괄적인 시스템 프롬프트를 제공합니다.

    • 톤, 스타일, 적극성 및 규칙 준수에 대한 지침이 포함되어 있습니다.

    • 환경 세부 정보를 자동으로 포함합니다

  • codeReview : 코드 검토를 위한 프롬프트

    • 코드 검토 작업을 위한 전문화된 프롬프트

    • 버그, 보안 취약점, 성능 문제 및 모범 사례에 대한 코드를 분석합니다.

  • prReview : 풀 리퀘스트 검토를 위한 프롬프트

    • PR 검토 업무를 위한 전문화된 프롬프트

    • PR 변화를 분석하고 포괄적인 피드백을 제공합니다.

  • initCodebase : 코드베이스 문서로 새 CLAUDE.md 파일을 초기화합니다.

    • 빌드/린트/테스트 명령 및 코드 스타일 가이드라인에 대한 문서를 작성합니다.

    • Claude Code로 새 프로젝트를 설정하는 데 유용합니다.

개발

# Run in development mode with auto-reload
npm run dev

건축학

Claude Code MCP는 모듈형 아키텍처로 구축되었습니다.

claude-code-mcp/
├── src/
│   ├── server/
│   │   ├── claude-code-server.ts  # Main server setup
│   │   ├── tools.ts               # Tool implementations
│   │   ├── prompts.ts             # Prompt definitions
│   │   └── resources.ts           # Resource implementations
│   ├── utils/
│   │   ├── bash.ts                # Shell command utilities
│   │   └── file.ts                # File system utilities
│   └── index.ts                   # Entry point
├── package.json
├── tsconfig.json
└── README.md

구현은 다음과 같은 주요 원칙을 따릅니다.

  1. 모듈성 : 각 구성 요소(도구, 프롬프트, 리소스)는 별도의 모듈로 구현됩니다.

  2. 유형 안전성 : 모든 구성 요소에 대한 전체 TypeScript 유형 정의

  3. 오류 처리 : 모든 작업에 대한 포괄적인 오류 처리

  4. 보안 : 잠재적으로 위험한 작업에 대한 보안 제한

구현 세부 사항

MCP 서버 설정

메인 서버는 claude-code-server.ts 에 설정되어 있습니다:

export async function setupClaudeCodeServer(server: McpServer): Promise<void> {
  // Set up Claude Code tools
  setupTools(server);
  
  // Set up Claude Code prompts
  setupPrompts(server);
  
  // Set up Claude Code resources
  setupResources(server);
}

도구 구현

도구는 MCP SDK의 도구 등록 방법을 사용하여 구현됩니다.

server.tool(
  "toolName",
  "Tool description",
  {
    // Zod schema for tool arguments
    param1: z.string().describe("Parameter description"),
    param2: z.number().optional().describe("Optional parameter description")
  },
  async ({ param1, param2 }) => {
    // Tool implementation
    return {
      content: [{ type: "text", text: "Result" }]
    };
  }
);

리소스 구현

리소스는 MCP SDK의 리소스 등록 방법을 사용하여 구현됩니다.

server.resource(
  "resourceName",
  new ResourceTemplate("resource://{variable}", { list: undefined }),
  async (uri, variables) => {
    // Resource implementation
    return {
      contents: [{
        uri: uri.href,
        text: "Resource content"
      }]
    };
  }
);

특허

MIT

감사의 말

기여하다

기여를 환영합니다! 풀 리퀘스트를 제출해 주세요.

부인 성명

이 프로젝트는 Anthropic과 공식적으로 제휴 관계가 없습니다. Claude Code는 Anthropic의 제품이며, 이 프로젝트는 MCP 서버로서 Claude Code를 독립적으로 구현한 것입니다.

Available Tools

8 tools
bashC

Execute a shell command

ParametersJSON Schema
NameRequiredDescriptionDefault
commandYesThe shell command to execute
timeoutNoOptional timeout in milliseconds (max 600000)

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. 'Execute a shell command' implies a potentially powerful and risky operation, but the description doesn't mention security implications, permission requirements, side effects, or what happens on timeout. This is a significant gap for a tool that can perform arbitrary system operations.

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 extremely concise at just three words, with zero wasted language. It's front-loaded with the essential purpose and doesn't include any unnecessary elaboration, making it efficient for quick understanding.

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 tool that executes arbitrary shell commands with no annotations and no output schema, the description is inadequate. It doesn't address the significant behavioral complexity, security implications, or what the tool returns. Given the power and risk of this operation, more context is needed for safe and effective use.

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?

The schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description doesn't add any additional meaning beyond what's in the schema - it doesn't explain command syntax, shell environment, or timeout behavior. 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 'Execute a shell command' clearly states the verb ('execute') and resource ('shell command'), making the purpose immediately understandable. However, it doesn't distinguish this tool from potential sibling tools that might also execute commands or interact with the shell environment, keeping it from 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 'editFile' or 'listFiles'. There's no mention of prerequisites, safety considerations, or typical use cases, leaving the agent with minimal context for appropriate tool selection.

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

codeReviewC

Review code for bugs, security issues, and best practices

ParametersJSON Schema
NameRequiredDescriptionDefault
codeYesThe code to review

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 states the tool reviews code but doesn't describe how it operates (e.g., static analysis, AI-based review), what permissions or resources it requires, or the format of results. This leaves significant gaps in understanding the tool's behavior.

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

Conciseness4/5

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 waste. It's appropriately sized for a simple tool, though it could be slightly more structured (e.g., by listing review aspects in bullet points) for better clarity.

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 (code review can involve nuanced analysis), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what the review outputs (e.g., a list of issues, a summary), how comprehensive it is, or any limitations, making it inadequate for full contextual understanding.

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?

The input schema has 100% description coverage, with the 'code' parameter fully documented in the schema. The description adds no additional meaning beyond the schema, such as code language support or review depth, so it meets the baseline score of 3 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 tool's purpose with specific verbs ('review code') and resources ('bugs, security issues, and best practices'), making it easy to understand what the tool does. However, it doesn't differentiate from potential sibling tools like 'think' or 'bash' that might also analyze code, preventing 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. It doesn't mention prerequisites, context for code review, or compare it to sibling tools like 'think' for analysis or 'bash' for execution, leaving the agent with minimal usage direction.

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

editFileC

Create or edit a file

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesThe absolute path to the file to edit
contentYesThe new content for the file

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations, the description carries full burden but only states the operation without behavioral details. It doesn't disclose whether this overwrites existing files, requires specific permissions, handles errors, or has side effects like creating directories. The vague 'create or edit' leaves critical behavior ambiguous.

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 extremely concise with just three words, front-loaded and zero waste. Every word earns its place by conveying the core action and resource efficiently.

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 mutation tool with no annotations and no output schema, the description is incomplete. It lacks details on behavior, error handling, or output format, leaving significant gaps for an agent to use it correctly in context with siblings.

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 fully documents both parameters ('file_path' and 'content'). The description adds no additional meaning beyond implying these parameters are used for the operation, meeting 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 tool's purpose with specific verbs ('create or edit') and resource ('a file'), making it immediately understandable. However, it doesn't differentiate from sibling tools like 'readFile' or 'listFiles' beyond the basic operation type.

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 about when to use this tool versus alternatives. The description doesn't mention prerequisites (e.g., file permissions), when editing is preferred over creating, or how it relates to siblings like 'readFile' for viewing or 'bash' for file operations.

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

grepC

Search for text in files

ParametersJSON Schema
NameRequiredDescriptionDefault
patternYesThe regular expression pattern to search for in file contents
pathNoThe directory to search in. Defaults to the current working directory.
includeNoFile pattern to include in the search (e.g. "*.js", "*.{ts,tsx}")

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. 'Search for text in files' implies a read-only operation, but it doesn't specify whether this is safe, if it requires permissions, how it handles errors, or what the output format looks like. For a tool with three parameters and no annotations, this is a significant gap in behavioral context.

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—'Search for text in files' is front-loaded and perfectly concise. Every word earns its place by directly conveying the core functionality without 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 tool's complexity (3 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain what the tool returns (e.g., matches, line numbers, file names), how results are formatted, or any behavioral nuances like case sensitivity or recursion. For a search tool, this leaves critical gaps for an AI agent to use it effectively.

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?

The description adds no parameter-specific information beyond what's already in the schema, which has 100% coverage with clear descriptions for 'pattern', 'path', and 'include'. According to the rules, when schema description coverage is high (>80%), the baseline is 3 even with no param info in the description, which applies here.

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 'Search for text in files' clearly states the verb (search) and resource (text in files), making the purpose immediately understandable. However, it doesn't distinguish this tool from sibling tools like 'searchGlob' or 'listFiles' that might also involve searching or file operations, so it doesn't reach the highest level of sibling differentiation.

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 'searchGlob' or 'listFiles'. There's no mention of prerequisites, context, or exclusions, leaving the agent to infer usage based solely on the tool name and basic purpose.

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

listFilesC

Lists files and directories in a given path

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYesThe absolute path to the directory to list

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 states the basic action but doesn't describe key behaviors like whether it returns recursive listings, handles symbolic links, includes hidden files, or what happens if the path is invalid. This leaves significant gaps for an agent to understand how the tool behaves beyond the simple listing.

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, clear sentence that directly states the tool's function without any unnecessary words. It's front-loaded with the core action and resource, making it highly efficient and easy to parse.

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 lack of annotations and output schema, the description is incomplete for a tool that performs file system operations. It doesn't address important contextual aspects like error handling, output format, or behavioral details (e.g., recursion, hidden files), which are crucial for an agent to use this tool effectively in real scenarios.

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?

The input schema has 100% description coverage, with the 'path' parameter clearly documented as 'The absolute path to the directory to list'. The description adds no additional semantic information beyond what the schema provides, so it meets the baseline for adequate but unenhanced parameter 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 ('Lists') and the target ('files and directories in a given path'), making the purpose immediately understandable. However, it doesn't distinguish this tool from potential siblings like 'searchGlob' or 'grep' that might also involve file operations, so it doesn't achieve full differentiation.

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 'searchGlob' or 'grep'. It lacks any context about prerequisites, such as whether the path must exist or be accessible, or when other tools might be more appropriate for similar tasks.

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

readFileC

Read a file from the local filesystem

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesThe absolute path to the file to read
offsetNoThe line number to start reading from
limitNoThe number of lines to read

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 states the basic action but lacks details on error handling (e.g., for missing files), performance considerations, or output format (e.g., text vs. binary). This leaves significant gaps in understanding how the tool behaves in practice.

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, direct sentence with no wasted words, making it highly efficient and easy to parse. It front-loads the core purpose without unnecessary elaboration, which is ideal for quick understanding.

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 (file I/O with parameters) and lack of annotations and output schema, the description is insufficient. It doesn't cover critical aspects like return values, error cases, or security implications, leaving the agent poorly equipped to use the tool effectively in real scenarios.

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?

The schema description coverage is 100%, with clear descriptions for all parameters (file_path, offset, limit). The description doesn't add any semantic details beyond what the schema provides, such as explaining how offset and limit interact or file encoding issues. 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 ('Read') and resource ('a file from the local filesystem'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'grep' or 'searchGlob' that also involve file reading operations, 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 'grep' for searching or 'listFiles' for directory contents. There's no mention of prerequisites, such as file existence or permissions, which leaves the agent without context for appropriate tool selection.

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

searchGlobC

Search for files matching a pattern

ParametersJSON Schema
NameRequiredDescriptionDefault
patternYesThe glob pattern to match files against
pathNoThe directory to search in. Defaults to the current working directory.

TDQS

C2.9/5.0
Behavior2/5

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 searches for files but doesn't describe how it behaves—e.g., whether it returns full paths, file contents, or metadata; if it's recursive or case-sensitive; or any performance or permission considerations. This leaves significant gaps for an agent to understand the tool's behavior.

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 or redundancy. It is appropriately sized and front-loaded, making it easy for an agent to quickly grasp 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 a file search tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., a list of file paths or details), how errors are handled, or any behavioral nuances. This makes it inadequate for an agent to fully understand the tool's context and usage.

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?

The input schema has 100% description coverage, with clear documentation for both parameters ('pattern' and 'path'). The description adds no additional meaning beyond the schema, such as examples of glob patterns or path constraints. Since the schema does the heavy lifting, the baseline score of 3 is appropriate.

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 'Search for files matching a pattern' clearly states the verb ('search') and resource ('files'), specifying the action and target. However, it doesn't distinguish this tool from sibling tools like 'grep' or 'listFiles', which might offer similar file-searching capabilities, so it lacks sibling differentiation.

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. It doesn't mention when to prefer 'searchGlob' over 'grep' for pattern matching or 'listFiles' for file listing, nor does it specify any prerequisites or exclusions for usage.

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

thinkC

A tool for thinking through complex problems

ParametersJSON Schema
NameRequiredDescriptionDefault
thoughtYesYour thoughts

TDQS

C2.6/5.0
Behavior2/5

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

With no annotations, the description carries full burden but only states the tool is for 'thinking through complex problems,' without disclosing behavioral traits like whether it's read-only, has side effects, requires authentication, or produces output. This leaves significant gaps in understanding how the tool behaves.

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

Conciseness4/5

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 for a simple tool, though it could be more front-loaded with specific details to improve clarity.

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 conceptual nature, no annotations, and no output schema, the description is incomplete. It doesn't explain what 'thinking through' results in, how the tool aids problem-solving, or what the agent should expect, leaving too much ambiguity for effective use.

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?

The schema description coverage is 100%, with the single parameter 'thought' described as 'Your thoughts.' The description adds no additional meaning beyond this, so it meets the baseline of 3 where the schema handles the parameter documentation adequately.

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

Purpose3/5

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

The description 'A tool for thinking through complex problems' states a general purpose but lacks specificity about what 'thinking through' entails or what resource it operates on. It distinguishes from siblings like 'bash' or 'readFile' by being about cognitive processing rather than file operations, but remains vague about the actual function.

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 explicit guidance on when to use this tool versus alternatives is provided. The description implies usage for complex problems, but it doesn't specify contexts, prerequisites, or exclusions, leaving the agent to infer based on 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.

Tool Schema Changelog

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

  1. 8 tool updates
    • First observedbash
    • First observedcodeReview
    • First observededitFile
    • First observedgrep
    • First observedlistFiles
    • First observedreadFile
    • First observedsearchGlob
    • First observedthink
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

B3.2/5.0

Scored across 8 tools

Disambiguation4/5

Most tools have distinct purposes, such as bash for shell execution, codeReview for analysis, and file operations like editFile, readFile, and listFiles. However, grep and searchGlob could be slightly confusing as both involve searching, though grep targets text content while searchGlob focuses on file patterns, which is clarified in descriptions.

Naming Consistency3/5

The naming is mixed with camelCase (codeReview, editFile, readFile, listFiles, searchGlob) and lowercase (bash, grep, think), lacking a uniform pattern. While the camelCase tools follow a verbNoun style, the inconsistency in case usage reduces predictability across the set.

Tool Count5/5

With 8 tools, the count is well-scoped for a code and file management server, covering essential operations like execution, review, file handling, and search. Each tool serves a clear purpose without feeling excessive or insufficient for the domain.

Completeness4/5

The toolset provides strong coverage for code and file workflows, including creation, reading, editing, listing, searching, and review. A minor gap is the lack of a deleteFile tool, which agents might need to work around, but core operations are well-represented.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches