이 프로젝트는 MariaDB 데이터베이스를 탐색하고 상호작용하기 위한 Model Context Protocol (MCP) 서버입니다. 이 서버는 Cline과 같은 AI 어시스턴트가 MariaDB 데이터베이스에 접근하여 정보를 조회할 수 있도록 도구를 제공합니다.
이 MCP 서버는 다음과 같은 도구를 제공합니다:
list_databases: 접근 가능한 모든 데이터베이스의 목록을 반환합니다.
list_tables: 지정된 데이터베이스 내의 모든 테이블 목록을 반환합니다.
입력: database (문자열, 필수) - 테이블 목록을 조회할 데이터베이스 이름.
get_table_schema: 지정된 테이블의 스키마(컬럼 정의)를 반환합니다.
입력:
database (문자열, 필수) - 테이블이 속한 데이터베이스 이름.
table (문자열, 필수) - 스키마를 조회할 테이블 이름.
query_table: 지정된 테이블에서 데이터를 조회합니다. 기본적으로 처음 100개의 행을 반환합니다.
입력:
database (문자열, 필수) - 테이블이 속한 데이터베이스 이름.
table (문자열, 필수) - 데이터를 조회할 테이블 이름.
limit (숫자, 선택) - 반환할 최대 행 수 (기본값: 100).
Related MCP server: MCP MariaDB Server
이 서버를 사용하려면 GitHub 저장소를 클론하고, MCP 클라이언트(예: VS Code 확장 프로그램)의 설정 파일에 서버 정보를 등록해야 합니다. 이 저장소에는 미리 빌드된 실행 파일(build/index.js)이 포함되어 있어 별도의 빌드 과정이 필요하지 않습니다.
저장소 클론: 원하는 위치에 이 저장소를 클론합니다.
git clone https://github.com/moosin76/mcp_server_mariadb_reader.gitMCP 설정 파일 수정:
설정 예시:
{
"mcpServers": {
"mcp_server_mariadb_reader": {
"command": "node",
"args": ["<클론된 저장소 경로>/build/index.js"], // 클론된 저장소 내 build/index.js 파일 경로
"env": {
"MARIADB_HOST": "YOUR_DB_HOST", // MariaDB 호스트 주소
"MARIADB_PORT": "YOUR_DB_PORT", // MariaDB 포트 번호 (예: "3306")
"MARIADB_USER": "YOUR_DB_USER", // MariaDB 사용자 이름
"MARIADB_PASSWORD": "YOUR_DB_PASSWORD", // MariaDB 비밀번호
"MARIADB_DATABASE": "YOUR_DEFAULT_DB" // (선택) 기본 데이터베이스 이름
},
"disabled": false,
"autoApprove": []
}
// 다른 MCP 서버 설정...
}
}주의:
<클론된 저장소 경로> 부분을 실제 저장소를 클론한 로컬 경로로 변경해야 합니다. (예: C:/Users/YourUser/Documents/GitHub/mcp_server_mariadb_reader)
env 객체 내의 MariaDB 연결 정보를 실제 환경에 맞게 수정해야 합니다.
이 저장소에는 빌드된 파일이 포함되어 있으므로, 서버를 사용하기 위해 아래 단계를 수행할 필요는 없습니다. 소스 코드(src 디렉토리)를 직접 수정하고 변경 사항을 적용하려면 다음 단계를 따르세요.
의존성 설치 (최초 한 번 또는 package.json 변경 시):
npm install수정 후 빌드:
npm run build이 명령은 src 디렉토리의 TypeScript 코드를 build 디렉토리의 JavaScript 코드로 컴파일합니다.
(선택) 개발 중 변경 사항 감지 및 자동 빌드:
npm run watch이 프로젝트는 [라이선스 정보 입력] 라이선스 하에 배포됩니다.
특정 테이블의 스키마(컬럼 정의)를 가져옵니다.
| Name | Required | Description | Default |
|---|---|---|---|
| database | Yes | 데이터베이스의 이름입니다. | |
| table | Yes | 테이블의 이름입니다. |
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. While it implies a read operation ('가져옵니다' - retrieves), it lacks details on permissions, rate limits, error handling, or response format. For a tool with no annotations, this is a significant gap in transparency.
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 for an agent to parse 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?
Given the tool's low complexity (2 required parameters, no output schema) and high schema coverage, the description is minimally adequate. However, it lacks behavioral context (e.g., permissions, errors) and does not reference sibling tools, which could improve completeness for agent usage.
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%, with both parameters ('database' and 'table') clearly documented in the input schema. The description does not add any additional meaning beyond what the schema provides, such as format examples or constraints. Baseline 3 is appropriate when the schema handles parameter documentation effectively.
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: '특정 테이블의 스키마(컬럼 정의)를 가져옵니다' translates to 'Retrieves the schema (column definitions) of a specific table.' This specifies the verb ('가져옵니다' - retrieves) and resource ('스키마' - schema). However, it does not explicitly differentiate from sibling tools like 'list_tables' or 'query_table', which would require a 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 no guidance on when to use this tool versus alternatives. It does not mention sibling tools like 'list_databases', 'list_tables', or 'query_table', nor does it specify prerequisites or contexts for usage. This leaves the agent without explicit direction on tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
접근 가능한 모든 데이터베이스 목록을 보여줍니다.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool shows a list, implying a read-only operation, but does not disclose any behavioral traits such as permissions required, rate limits, pagination, or what 'accessible' entails. The description is minimal and lacks critical operational context.
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, clear sentence that directly states the tool's purpose without unnecessary details. It is appropriately concise and front-loaded, though it could be slightly more informative to improve completeness without sacrificing brevity.
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 simplicity (0 parameters, no output schema, no annotations), the description is minimally adequate. However, it lacks details on behavioral aspects like what 'accessible' means or how the list is formatted, which would be helpful for an agent. The absence of an output schema means the description should ideally hint at the return format, but it does not.
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 tool has 0 parameters, and the input schema has 100% description coverage (though empty). The description does not need to add parameter semantics, so it meets the baseline for tools with no parameters. No additional parameter information is required or provided.
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: '접근 가능한 모든 데이터베이스 목록을 보여줍니다' (shows a list of all accessible databases). It specifies the verb '보여줍니다' (shows) and the resource '데이터베이스 목록' (database list), but does not explicitly differentiate it from sibling tools like 'list_tables' or 'get_table_schema'.
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 no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, context for usage, or comparisons with sibling tools such as 'list_tables' or 'query_table', leaving the agent to infer usage based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
특정 데이터베이스 내의 모든 테이블 목록을 보여줍니다.
| Name | Required | Description | Default |
|---|---|---|---|
| database | Yes | 데이터베이스의 이름입니다. |
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 shows table lists but doesn't describe return format (e.g., array of names, pagination), permissions required, rate limits, or error conditions. This leaves significant gaps for a tool that likely interacts with a database system.
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 in Korean that directly states the tool's function. There's no wasted wording, though it could be slightly more structured (e.g., by front-loading the core action more explicitly).
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 no annotations and no output schema, the description is incomplete for a database tool. It doesn't explain what the output looks like (e.g., list format, metadata included), error handling, or behavioral constraints. For a tool with one parameter but potentially complex database interactions, more context is needed.
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 already documents the single 'database' parameter thoroughly. The description adds no additional parameter semantics beyond implying the tool operates within a database context, which is already clear from the schema. Baseline 3 is appropriate when 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: '보여줍니다' (shows/displays) + '모든 테이블 목록' (all table list) + '특정 데이터베이스 내의' (within a specific database). It specifies the verb (show/list), resource (tables), and scope (within a database), though it doesn't explicitly differentiate from sibling tools like 'list_databases' or 'get_table_schema'.
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 no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'list_databases' (for listing databases instead of tables) or 'get_table_schema' (for detailed table info), nor does it specify 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.
특정 테이블에서 데이터를 조회합니다 (제한된 행 반환).
| Name | Required | Description | Default |
|---|---|---|---|
| database | Yes | 데이터베이스의 이름입니다. | |
| limit | No | 반환할 최대 행 수 (기본값 100). | |
| table | Yes | 테이블의 이름입니다. |
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 'limited rows returned', which hints at a constraint, but fails to cover critical aspects like read-only status, potential permissions needed, error handling, or response format. This is inadequate for a query tool with zero annotation coverage.
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 in Korean that directly states the tool's purpose and a key constraint ('limited rows returned'). It is front-loaded with no wasted words, making it highly concise and well-structured.
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 a database query tool with no annotations and no output schema, the description is insufficient. It lacks details on behavior, error cases, return values, and usage context, leaving significant gaps for an agent to operate effectively.
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 already documents all parameters ('database', 'table', 'limit') with clear descriptions. The description adds no additional meaning beyond what the schema provides, such as query syntax or examples, resulting in a baseline score of 3.
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 ('query_table' translates to 'retrieve data from a specific table') and the resource ('table'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_table_schema' (which might return metadata) or 'list_tables' (which lists tables rather than querying data), missing full sibling distinction.
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 no guidance on when to use this tool versus alternatives like 'get_table_schema' or 'list_tables'. It mentions 'limited rows returned', but this doesn't clarify usage context, exclusions, or prerequisites, leaving the agent without explicit direction.
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_table_schemalist_databaseslist_tablesquery_tableScored across 4 tools
Each tool has a clearly distinct purpose with no overlap: get_table_schema retrieves column definitions, list_databases shows available databases, list_tables enumerates tables within a database, and query_table fetches data from a table. The descriptions clearly differentiate their functions, making misselection unlikely.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., get_table_schema, list_databases, list_tables, query_table). The naming is predictable and readable throughout the set, with no deviations in style.
With 4 tools, the count is reasonable for a database reader server, but it feels slightly thin for covering all typical read operations. While core functions are present, additional tools like querying across tables or advanced filtering might enhance completeness without being excessive.
The tool set covers basic read operations (list databases, list tables, get schema, query data), but there are notable gaps for a database reader. Missing operations include querying with custom SQL, joining tables, or advanced filtering, which could limit agent capabilities in complex scenarios.
PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.
Astra DB tools for agents: schema, find, vector search, guarded writes, and interactive views.
Explore, query, and inspect SQLite databases with ease. List tables, preview results, and view det…
Query Postgres, MySQL, SQL Server, Oracle, BigQuery, ClickHouse and Redshift from your AI client.
