Skip to main content
Glama
xuejike

Database Query MCP Server

by xuejike
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

@xuejike/develop-tool

一个面向 AI Agent 的开发工具，支持只读数据库查询、多平台日志查询和 Jenkins CI/CD 操作，同时支持 MCP（Model Context Protocol）协议接入和 CLI 命令行直接使用。

适用于让 AI Agent（如 Cursor、Kiro、Claude Desktop 等）安全地查询数据库、检索日志（Loki / Elasticsearch）、管理 Jenkins 构建，或在终端中快速执行操作。

核心特性

  • 只读安全 — 自动拦截 INSERT/UPDATE/DELETE/DROP 等写操作

  • 多数据库支持 — MySQL、PostgreSQL、MSSQL、Oracle

  • 日志查询 — 支持 Loki（LogQL）和 Elasticsearch（Query DSL）日志平台

  • Jenkins 集成 — 查看 Job 列表、触发构建、查看日志、查看 Job 信息

  • 别名配置 — 预存连接信息，一个别名代替一堆参数

  • 两层配置 — 用户级（全局）+ 项目级，项目级优先

  • 密码加密 — AES-256-GCM 加密存储，配置文件泄露也不暴露密码/Token

  • 双模式运行 — MCP stdio 服务（给 Agent 用）或 CLI 命令行（给人用）

  • 元数据查询 — AI 可自主查询标签/索引信息以构建精确查询条件

  • 嵌套文件夹 — Jenkins Job 支持多级文件夹路径

Related MCP server: DB CLI MCP Server

安装

npm install -g @xuejike/develop-tool

或用 npx 免安装运行：

npx @xuejike/develop-tool

AI Agent 安装配置

复制以下文本发送给 AI，即可让 AI 帮你完成安装配置：

请阅读 https://raw.githubusercontent.com/xuejike/coding-db-mcp/refs/heads/master/AI_INSTALL.md 按照其中的指引帮我完成 @xuejike/develop-tool CLI 工具的安装和连接配置。

快速开始

数据库查询

# 添加数据库连接
develop-tool config add mydb \
  --type mysql \
  --host localhost \
  --port 3306 \
  --user root \
  --password yourpass \
  --database myapp \
  --global

# 执行查询
develop-tool query --alias mydb -q "SELECT * FROM users LIMIT 5"

Jenkins 操作

# 添加 Jenkins 连接
develop-tool config add my-jenkins \
  --type jenkins \
  --base-url http://jenkins.example.com:8080 \
  --user admin \
  --token your-api-token \
  --global

# 查看 Job 列表
develop-tool jenkins list --alias my-jenkins

# 查看嵌套文件夹下的 Job
develop-tool jenkins list folder/subfolder --alias my-jenkins

# 查看 Job 详情（参数定义等）
develop-tool jenkins info folder/subfolder/my-job --alias my-jenkins

# 触发构建
develop-tool jenkins build folder/subfolder/my-job --alias my-jenkins --param branch=origin/main

# 查看构建日志
develop-tool jenkins log folder/subfolder/my-job --alias my-jenkins --build-number 10

日志查询

# 添加 Loki 日志平台配置
develop-tool config add prod-loki \
  --type loki \
  --base-url https://loki.example.com \
  --global

# 添加 Elasticsearch 配置（支持无认证模式）
develop-tool config add local-es \
  --type elasticsearch \
  --base-url http://localhost:9200 \
  --global

# 查询 Loki 日志
develop-tool log query --alias prod-loki -q '{namespace="prod"} |= "error"' --start 1h

# 直接参数模式查询
develop-tool log query --type loki --base-url https://loki.example.com -q '{app="payment"}' --start 30m --limit 50

# 查询 Elasticsearch 日志
develop-tool log query --alias local-es -q '{"match": {"level": "ERROR"}}' --index app-logs-* --start 24h

# 查询元数据 - 获取所有标签
develop-tool log metadata --alias prod-loki --metadata-type labels

# 查询标签的所有值
develop-tool log metadata --alias prod-loki --metadata-type label_values --label app

# 查询 ES 索引列表
develop-tool log metadata --alias local-es --metadata-type indices

# 查询 ES 字段映射
develop-tool log metadata --alias local-es --metadata-type mappings --index app-logs-*

管理连接

# 查看所有配置
develop-tool config list

# 查看连接详情
develop-tool config show mydb

# 删除连接
develop-tool config remove mydb --global

使用场景

AI Agent 通过 MCP 协议使用

将工具配置为 Agent 的 MCP 服务：

{
  "mcpServers": {
    "develop-tool": {
      "command": "npx",
      "args": ["@xuejike/develop-tool"]
    }
  }
}

Agent 可使用以下 MCP 工具：

  • query_mysql / query_postgresql / query_mssql / query_oracle — 数据库查询

  • query_loki — Loki 日志查询（LogQL）

  • query_elasticsearch — Elasticsearch 日志查询（Query DSL）

  • query_log_metadata — 日志平台元数据查询（标签、索引、字段映射等）

  • jenkins_list_jobs — 查看 Jenkins Job 列表

  • jenkins_build_job — 触发 Jenkins 构建

  • jenkins_get_build_log — 查看构建日志

  • jenkins_get_job_info — 查看 Job 详情（参数定义）

Agent 调用示例：

{
  "alias": "my-jenkins",
  "jobName": "devops/TKE_CSI_UAT/my-service"
}

终端快速操作

预配置好连接后，日常操作不用再记各种参数：

# 数据库查询
develop-tool query --alias prod -q "SELECT * FROM users WHERE id = 100"

# Jenkins 触发构建
develop-tool jenkins build my-job --alias ci --param env=prod

CLI 命令参考

develop-tool [命令] [选项]

命令:
  start                    启动 MCP 服务（默认）
  query                    执行 SQL 查询
  log query                执行日志查询（Loki / Elasticsearch）
  log metadata             查询日志平台元数据
  config add <alias>       添加连接配置
  config remove <alias>    删除连接配置
  config list              列出所有连接
  config show <alias>      查看连接详情
  jenkins list [folder]    查看 Jenkins Job 列表
  jenkins build <job>      触发 Jenkins 构建
  jenkins log <job>        查看构建日志
  jenkins info <job>       查看 Job 详情
  test                     测试数据库连接
  help                     显示帮助
  version                  显示版本

log 选项:
  --alias <alias>          使用预配置的日志平台连接别名
  --base-url <url>         日志平台地址
  --user <user>            认证用户名（可选）
  --password <pwd>         认证密码/Token（可选）
  -q, --query <expr>       查询表达式（LogQL / ES Query DSL）
  --start <time>           起始时间（ISO 8601 或 "1h"/"30m"/"7d"）
  --end <time>             结束时间（默认 "now"）
  --limit <n>              返回行数限制（默认 100，最大 1000）
  --direction <dir>        排序方向: forward | backward（仅 Loki）
  --index <pattern>        ES 索引模式
  --type <type>            日志平台类型 (loki/elasticsearch)
  --metadata-type <type>   元数据类型 (labels/label_values/series/indices/mappings/field_caps)
  --label <name>           标签名（配合 label_values）
  --match <selector>       流选择器（配合 series）
  --org-id <id>            Loki 租户 ID

jenkins 选项:
  --alias <alias>          使用预配置的 Jenkins 连接别名
  --base-url <url>         Jenkins 服务器地址
  --user <user>            Jenkins 用户名
  --token <token>          Jenkins API Token
  --build-number <num>     构建号（log 子命令，默认 lastBuild）
  --param <key=value>      构建参数（build 子命令，可多次指定）

query 选项:
  --alias <alias>          使用预配置的数据库别名
  -q, --query <sql>        SQL 语句
  -t, --type <type>        数据库类型
  -H, --host <host>        主机
  -P, --port <port>        端口
  -u, --user <user>        用户名
  -p, --password <pwd>     密码
  -d, --database <db>      数据库名

config add 选项:
  --type <type>            连接类型 (mysql/postgresql/oracle/mssql/jenkins/loki/elasticsearch)
  --host <host>            主机地址（数据库）
  --port <port>            端口（数据库）
  --base-url <url>         服务器地址（Jenkins/日志平台）
  --user <user>            用户名
  --password <pwd>         密码/Token
  --token <token>          API Token（Jenkins）
  --password-stdin         从 stdin 读取密码
  --database <db>          数据库名
  --org-id <id>            Loki 租户 ID
  --index <pattern>        默认索引模式（Elasticsearch）
  --global                 保存到用户级配置（默认项目级）

配置文件

层级

路径

说明

用户级

~/.develop-tool/config.json

全局共享，适合放各环境连接

项目级

.develop-tool.json（项目根目录）

仅当前项目，优先级高于用户级

建议把 .develop-tool.json 加入 .gitignore。

支持的连接类型：

  • 数据库：mysql、postgresql、oracle、mssql

  • Jenkins：jenkins

  • 日志平台：loki、elasticsearch

密码和 Token 自动加密存储（AES-256-GCM），密钥通过本机用户信息派生。

Jenkins 嵌套文件夹

Jenkins 的 Job 可以放在多级文件夹中，使用 / 分隔路径：

# Job 路径格式: folder1/folder2/jobName
develop-tool jenkins build devops/UAT/my-service --alias ci
develop-tool jenkins log devops/UAT/my-service --alias ci
develop-tool jenkins info devops/UAT/my-service --alias ci
develop-tool jenkins list devops/UAT --alias ci

工具会自动将路径转换为 Jenkins API 格式 (/job/folder1/job/folder2/job/jobName)。

安全说明

  1. 数据库只允许 SELECT/SHOW/DESCRIBE/EXPLAIN 等只读操作

  2. 日志查询仅执行只读操作（Loki GET / ES _search），不修改任何远端数据

  3. 密码和 Token 使用 AES-256-GCM 加密存储，配置文件权限 0600

  4. 日志平台支持无认证模式（内网部署无需 user/pwd）

  5. 支持 --password-stdin 避免密码出现在 shell 历史

  6. Jenkins 操作自动处理 CSRF crumb token

  7. 建议数据库账号仅授予只读权限

License

ISC

Available Tools

4 tools
query_mssqlA
Read-only

执行MSSQL数据库查询（只读模式）

ParametersJSON Schema
NameRequiredDescriptionDefault
hostYes数据库主机地址
portYes数据库端口
userYes数据库用户名
pwdYes数据库密码
dbYes数据库名称
querySqlYes要执行的SQL查询语句（仅支持SELECT等只读操作）

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, and idempotentHint=false. The description adds the read-only mode context ('只读模式'), which reinforces but doesn't significantly expand beyond annotations. It doesn't disclose additional behavioral traits like rate limits, authentication needs beyond parameters, or error handling.

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 in Chinese that directly states the tool's purpose and key constraint ('只读模式'). It's front-loaded with no unnecessary 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.

Completeness3/5

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

Given the tool's complexity (database querying with 6 required parameters), annotations cover safety aspects (read-only, non-destructive), but there's no output schema. The description is minimal and doesn't explain return values, error cases, or connection behavior. It's adequate but lacks depth for a tool with significant operational context.

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%, with all parameters well-documented in the input schema. The description doesn't add meaningful parameter semantics beyond what's already in the schema, such as format examples or constraints. Baseline 3 is appropriate since the schema carries the full burden.

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 ('执行MSSQL数据库查询') and resource ('MSSQL数据库'), specifying it's for read-only operations. It distinguishes from siblings by mentioning MSSQL specifically, though it doesn't explicitly contrast with other database query tools like query_mysql or query_oracle.

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

Usage Guidelines3/5

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

The description implies usage for MSSQL database queries in read-only mode, but doesn't provide explicit guidance on when to use this tool versus alternatives like query_mysql or query_oracle. No exclusions or prerequisites are mentioned beyond the read-only constraint.

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

query_mysqlA
Read-only

执行MySQL数据库查询（只读模式）

ParametersJSON Schema
NameRequiredDescriptionDefault
hostYes数据库主机地址
portYes数据库端口
userYes数据库用户名
pwdYes数据库密码
dbYes数据库名称
querySqlYes要执行的SQL查询语句（仅支持SELECT等只读操作）

TDQS

A3.5/5.0
Behavior3/5

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

The description adds value beyond annotations by specifying '只读模式' (read-only mode), which aligns with the readOnlyHint=true annotation. However, it doesn't provide additional behavioral context such as connection handling, timeout behavior, result format, or error conditions. With annotations covering safety (readOnlyHint=true, destructiveHint=false), the description meets the lower bar but doesn't enrich understanding significantly.

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 a single sentence that efficiently communicates the core purpose and constraint. It's front-loaded with no wasted words, making it easy for an AI agent to parse quickly. Every part of the sentence earns its place by specifying the action, target, and operational mode.

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

Completeness3/5

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

Given the tool's complexity (6 required parameters for database connection and query execution), the description is minimal. While annotations provide safety information (readOnlyHint=true, destructiveHint=false) and the schema fully documents parameters, there's no output schema and the description doesn't explain what the tool returns (e.g., result sets, error formats). For a database query tool, this leaves gaps in understanding the complete behavior.

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 doesn't add any parameter-specific information beyond what's already in the input schema, which has 100% description coverage. It mentions 'MySQL数据库查询' (MySQL database query) but doesn't explain individual parameters like host, port, or querySql. With high schema coverage, the baseline score of 3 is appropriate as the schema carries the full burden of 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 verb ('执行' - execute) and resource ('MySQL数据库查询' - MySQL database query), and specifies the operational mode ('只读模式' - read-only mode). It distinguishes from siblings by mentioning MySQL specifically, though it doesn't explicitly contrast with other database types like MSSQL, Oracle, or PostgreSQL.

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

Usage Guidelines3/5

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

The description implies usage context by specifying '只读模式' (read-only mode) and the input schema further clarifies that SQL queries should be '仅支持SELECT等只读操作' (only support SELECT and other read-only operations). However, it doesn't explicitly state when to use this tool versus the sibling database tools (query_mssql, query_oracle, query_postgresql), nor does it provide any exclusion criteria beyond the read-only constraint.

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

query_oracleA
Read-only

执行Oracle数据库查询（只读模式）

ParametersJSON Schema
NameRequiredDescriptionDefault
hostYes数据库主机地址
portYes数据库端口
userYes数据库用户名
pwdYes数据库密码
dbYes数据库名称
querySqlYes要执行的SQL查询语句（仅支持SELECT等只读操作）

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already provide readOnlyHint=true, destructiveHint=false, openWorldHint=false, and idempotentHint=false. The description adds valuable context by specifying '只读模式' (read-only mode) and implying Oracle-specific behavior. While it doesn't detail rate limits, authentication needs beyond parameters, or result formats, it usefully reinforces the read-only constraint beyond what annotations alone convey.

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 in Chinese: '执行Oracle数据库查询（只读模式）'. It's front-loaded with the core purpose and includes the critical 'read-only mode' qualification. There's zero wasted verbiage or redundant information.

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

Completeness4/5

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

For a database query tool with 6 parameters, 100% schema coverage, and annotations covering safety (readOnlyHint=true, destructiveHint=false), the description is reasonably complete. It specifies the database type (Oracle) and read-only mode. The main gap is lack of output schema, but the description doesn't need to explain return values. It could better differentiate from sibling tools but covers essential context.

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%, with all 6 parameters well-documented in the input schema (e.g., host, port, user, pwd, db, querySql). The description adds no additional parameter information beyond what's in the schema. With complete schema coverage, the baseline score of 3 is appropriate as the description doesn't need to compensate for gaps.

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 as '执行Oracle数据库查询（只读模式）' which translates to 'Execute Oracle database query (read-only mode)'. This specifies both the verb (execute query) and resource (Oracle database), and distinguishes it from non-database tools. However, it doesn't explicitly differentiate from sibling database query tools (query_mssql, query_mysql, query_postgresql) beyond specifying Oracle.

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

Usage Guidelines3/5

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

The description implies usage context through '只读模式' (read-only mode) and the input schema's querySql description specifies '仅支持SELECT等只读操作' (only supports SELECT and other read-only operations). However, there's no explicit guidance on when to use this tool versus the sibling database tools, nor any mention of prerequisites or alternative scenarios.

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

query_postgresqlA
Read-only

执行PostgreSQL数据库查询（只读模式）

ParametersJSON Schema
NameRequiredDescriptionDefault
hostYes数据库主机地址
portYes数据库端口
userYes数据库用户名
pwdYes数据库密码
dbYes数据库名称
querySqlYes要执行的SQL查询语句（仅支持SELECT等只读操作）

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, etc., covering safety aspects. The description adds the read-only mode context ('只读模式') and specifies SQL query constraints ('仅支持SELECT等只读操作'), which provides useful behavioral context beyond annotations, though it doesn't detail rate limits, error handling, or output format.

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 in Chinese that directly states the tool's purpose and key constraint ('只读模式'). It's front-loaded with no unnecessary 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.

Completeness3/5

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

Given the tool's complexity (6 required parameters for database queries) and lack of output schema, the description is adequate but minimal. It covers the read-only nature and PostgreSQL focus, but doesn't explain return values, error cases, or connection handling, leaving gaps for an AI agent to infer.

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 all 6 parameters. The description doesn't add any parameter-specific semantics beyond what's in the schema, such as format details or examples. Baseline score of 3 is appropriate as the schema handles the heavy lifting.

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 ('执行PostgreSQL数据库查询') and resource ('PostgreSQL数据库'), specifying it's for read-only operations. It distinguishes from siblings by mentioning PostgreSQL specifically, though it doesn't explicitly contrast with other database types like MySQL or Oracle.

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

Usage Guidelines3/5

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

The description implies usage for PostgreSQL read-only queries but doesn't provide explicit guidance on when to use this tool versus the sibling tools (query_mssql, query_mysql, query_oracle). No alternative tools or exclusions are mentioned beyond the read-only constraint.

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. Dates show when Glama detected each change.

  1. 4 tool updates
    • First observedquery_mssql
    • First observedquery_mysql
    • First observedquery_oracle
    • First observedquery_postgresql
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose targeting a specific database system (MSSQL, MySQL, Oracle, PostgreSQL). There is no ambiguity or overlap since each tool is dedicated to a different database technology, making tool selection straightforward for agents based on the target system.

Naming Consistency5/5

All tool names follow a perfectly consistent verb_noun pattern: 'query_' followed by the database name (e.g., query_mssql, query_mysql). This uniform naming convention makes the tools predictable and easy to understand, with no deviations in style or structure.

Tool Count4/5

With 4 tools, the count is reasonable for a database query server covering multiple systems. It might be slightly thin if additional database types (e.g., SQLite) are expected, but it effectively covers major databases without being overwhelming, making it well-scoped for its purpose.

Completeness3/5

The server provides read-only query capabilities for multiple databases, which is a clear and focused domain. However, there are notable gaps: it lacks write operations (e.g., insert, update, delete) and administrative functions (e.g., schema management, connection testing), limiting agents to read-only workflows and potentially causing failures for broader database tasks.

Maintenance

ActivitySlowing
ResponsivenessSyncing

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

Related MCP Servers

  • Database Lookup Protocol (DLP)

    kalyangupta12
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides AI assistants with read-only access to inspect database schemas, preview data, and run safe queries across PostgreSQL, MySQL, MongoDB, and SQL Server. It enables AI tools to understand database structures and relationships automatically to generate more accurate code.
    12
    7
    MIT

  • DB CLI MCP Server

    firejeff01
    F
    license
    Not graded
    quality
    D
    maintenance
    Provides a unified, read-only interface for executing SQL queries across multiple database engines including SQL Server, MySQL, and PostgreSQL via CLI tools. It features automatic project configuration detection and strict query validation to ensure safe AI-driven data interactions.
    -

  • MCP Database Query Server

    Vicus-Brits
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to query and explore databases including SQLite, PostgreSQL, MySQL, and SQL Server through a secure, read-only workflow. It provides tools for listing connections, inspecting table schemas, and executing SELECT statements directly within VS Code.
    1
    -

  • PostgreSQL MCP Server

    sebcbi1
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables secure, read-only PostgreSQL database interaction through natural language, with automatic database discovery and connection management.
    2
    MIT

Appeared in Searches

Latest Blog Posts

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/xuejike/coding-db-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server