What can you do with this server?

The xamp server provides direct SQL access to XAMPP MariaDB/MySQL databases via five tools: * list_databases: Lists all accessible databases on the server (no arguments needed). * list_tables: Lists all tables within a specified database. * describe_table: Shows a table's structure, including column names, data types, and keys. * read_query: Executes read-only SQL statements (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH) against a specified database. * write_query: Executes data-modifying SQL statements (INSERT, UPDATE, DELETE, and DDL operations) against a specified database — requires the MCP_XAMP_ALLOW_WRITE=true environment variable to be set.

Which integrations are available for this server?

Provides tools to list databases, list tables, describe tables, and run read/write queries against MariaDB databases (via XAMPP or custom credentials). Enables querying MySQL databases with tools for listing databases, tables, describe table, read query, and write query (when enabled). Allows interaction with XAMPP's MariaDB/MySQL databases, providing tools for listing databases, tables, describing tables, and executing read/write queries.

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@xamp List all databases on my XAMPP server." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

xamp

by yeyorg

Overview Schema Source Related Servers Score Discussions Admin

Python

Local

MCP-XAMP

MCP server that gives Claude Code and OpenCode direct access to your XAMPP MariaDB/MySQL databases. Five tools: list databases, list tables, describe table, read query, write query.

Quick Start

Clone the repo
Configure your AI agent (Claude Code or OpenCode)
Start querying — list_databases, read_query, etc.

No global install needed — runs directly with uv run.

Related MCP server: MariaDB MCP Server

Requirements

Python 3.13+
XAMPP with MariaDB/MySQL running on localhost:3306
uv

Installation

git clone https://github.com/<user>/mcp-xamp.git
cd mcp-xamp
uv sync

Verify it works:

uv run mcp-xamp

Optional: install globally

If you prefer mcp-xamp available as a command anywhere:

uv tool install --python 3.13 .

Then use "command": "mcp-xamp" instead of uv run --directory ... in the configs below.

Claude Code Setup

Option A: global install (recomendado)

Instala mcp-xamp como comando global y registralo en Claude Code:

uv tool install --python 3.13 .

Luego agregá el server MCP. Elegí el scope que prefieras:

# Scope project (crea .mcp.json en el directorio actual)
claude mcp add xamp \
  -e MCP_XAMP_HOST=localhost \
  -e MCP_XAMP_PORT=3306 \
  -e MCP_XAMP_USER=root \
  -e MCP_XAMP_PASSWORD= \
  -e MCP_XAMP_ALLOW_WRITE=true \
  -- mcp-xamp

# Scope user (disponible en todos tus proyectos)
claude mcp add --scope user xamp \
  -e MCP_XAMP_HOST=localhost \
  -e MCP_XAMP_PORT=3306 \
  -e MCP_XAMP_USER=root \
  -e MCP_XAMP_PASSWORD= \
  -e MCP_XAMP_ALLOW_WRITE=true \
  -- mcp-xamp

Ajusta los valores de las variables según tu instalacion de XAMPP.

Option B: sin instalar (usando uv run)

Si preferis no instalar globalmente, apunta al directorio del repo:

claude mcp add xamp \
  -e MCP_XAMP_HOST=localhost \
  -e MCP_XAMP_PORT=3306 \
  -e MCP_XAMP_USER=root \
  -e MCP_XAMP_PASSWORD= \
  -e MCP_XAMP_ALLOW_WRITE=true \
  -- uv run --directory /ruta/a/mcp-xamp mcp-xamp

Reemplaza /ruta/a/mcp-xamp con la ruta real donde clonaste el repo.

Config manual (archivo .mcp.json)

Si preferis editar el archivo a mano, tambien funciona:

{
  "mcpServers": {
    "xamp": {
      "command": "mcp-xamp",
      "args": [],
      "env": {
        "MCP_XAMP_HOST": "localhost",
        "MCP_XAMP_PORT": "3306",
        "MCP_XAMP_USER": "root",
        "MCP_XAMP_PASSWORD": "",
        "MCP_XAMP_ALLOW_WRITE": "true"
      }
    }
  }
}

Si no instalaste globalmente, usa "command": "uv" con los args correspondientes (ver el .mcp.json de este repo como referencia).

Verify

Dentro de Claude Code, corre /mcp para confirmar que xamp aparece como conectado. Despues proba:

List all databases on my XAMPP server.

OpenCode Setup

Config location

OpenCode reads MCP config from opencode.json or opencode.jsonc. The file can be in:

Location	Scope
`<project-root>/opencode.json`	Project-specific
`<project-root>/.opencode/opencode.json`	Project-specific (alt)
`~/.config/opencode/opencode.json`	Global (all projects)

Add the MCP server

Add this block to your opencode.json or opencode.jsonc:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "xamp": {
      "type": "local",
      "command": ["uv", "run", "--directory", "/path/to/mcp-xamp", "mcp-xamp"],
      "enabled": true,
      "environment": {
        "MCP_XAMP_ALLOW_WRITE": "true"
      }
    }
  }
}

Replace /path/to/mcp-xamp with your actual clone path.

If you used uv tool install, simplify to:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "xamp": {
      "type": "local",
      "command": ["mcp-xamp"],
      "enabled": true,
      "environment": {
        "MCP_XAMP_ALLOW_WRITE": "true"
      }
    }
  }
}

Verify

Restart OpenCode, then try:

Show me all databases on the xamp server. use xamp tools

Environment Variables

All configuration goes through environment variables. Sensible defaults for a standard XAMPP installation.

Variable	Default	Description
`MCP_XAMP_HOST`	`127.0.0.1`	MariaDB/MySQL host
`MCP_XAMP_PORT`	`3306`	MariaDB/MySQL port
`MCP_XAMP_USER`	`root`	Database user
`MCP_XAMP_PASSWORD`	(empty)	Database password
`MCP_XAMP_ALLOW_WRITE`	`false`	Set to `true` to enable INSERT/UPDATE/DELETE/DDL

Credentials are read from environment variables only. They never appear in tool arguments, log output, or error messages.

Tools

Tool	Description	Requires
`list_databases`	Show all accessible databases	—
`list_tables`	Show tables in a database	`database`
`describe_table`	Show columns, types, and keys	`database`, `table`
`read_query`	Execute SELECT / SHOW / DESCRIBE / EXPLAIN	`database`, `query`
`write_query`	Execute INSERT / UPDATE / DELETE / DDL	`database`, `query`, `MCP_XAMP_ALLOW_WRITE=true`

Security

Read-only by default. Write operations require MCP_XAMP_ALLOW_WRITE=true.
Credentials never logged. Host, port, user, and password are stripped from error messages.
Credentials only from env vars. No tool parameters, no config files, no CLI args.
Connection-per-query. Each tool invocation opens and closes its own connection — no shared state, no stale connections.

XAMPP default is root with no password. Create a dedicated user for production use:

CREATE USER 'mcp_agent'@'127.0.0.1' IDENTIFIED BY 'secure_password';
GRANT SELECT ON *.* TO 'mcp_agent'@'127.0.0.1';

Development

# Install dev dependencies
uv sync --group dev

# Run tests
uv run pytest -v --cov=src/mcp_xamp

# Lint
uv run ruff check src/ tests/

# Format
uv run ruff format src/ tests/

License

MIT — see LICENSE.

Available Tools

5 tools

describe_tableA

Describe la estructura de una tabla (columnas, tipos, claves).

ParametersJSON Schema

Name	Required	Description	Default
`database`	Yes	Nombre de la base de datos.
`table`	Yes	Nombre de la tabla.

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description carries full burden. It only states what the tool does (describe structure) but does not disclose read-only nature, permission requirements, or any other behavioral traits. For a simple metadata read, this is adequate but minimal.

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 concise sentence that effectively communicates the tool's purpose with no redundancy.

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 simple schema retrieval tool with no output schema, the description is sufficient to understand its function. The hint about columns, types, and keys suggests the return structure. It could mention that it returns detailed metadata, but it is mostly complete.

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 coverage is 100% with descriptions for both 'database' and 'table'. The tool description does not add additional meaning beyond what the schema provides, so baseline 3 is appropriate.

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

Purpose5/5

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

The description clearly states that the tool describes table structure including columns, types, and keys. It is distinct from sibling tools like list_databases, list_tables, read_query, and write_query, which have different purposes.

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?

Usage is implied by the tool name and description: use when you need schema information. However, there is no explicit guidance on when to use versus alternatives or any prerequisites.

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

list_databasesA

Lista todas las bases de datos accesibles en el servidor MariaDB/MySQL.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A3.7/5.0

Behavior2/5

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

No annotations are provided, so the description must carry full behavioral burden. It only states that databases are 'accessible' but does not disclose potential side effects, authentication requirements, rate limits, or performance implications. The read-only nature is implied but not confirmed.

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 concise sentence, front-loaded with the key action and target. Every word adds value, with no unnecessary information.

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?

The tool has no output schema, so the description should ideally describe the return format. It only says 'lists databases' without indicating whether the output is an array of strings, objects, etc. Given the simplicity of the tool, this is a moderate gap.

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?

There are no parameters, so the description does not need to add meaning beyond the schema. The schema coverage is 100%, so baseline 4 is appropriate.

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

Purpose5/5

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

The description clearly states the tool lists all accessible databases on a MariaDB/MySQL server. The verb 'Lists' and resource 'databases' are specific. It distinguishes from siblings like list_tables (lists tables within a database) and describe_table (describes a table).

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 discovering available databases, but does not explicitly state when to use this tool versus alternatives like list_tables or read_query. No exclusions or prerequisites are mentioned.

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

list_tablesA

Lista todas las tablas en una base de datos.

ParametersJSON Schema

Name	Required	Description	Default
`database`	Yes	Nombre de la base de datos.

TDQS

A3.5/5.0

Behavior3/5

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

With no annotations, the description carries full burden. It implies a read-only, non-destructive operation but does not disclose any potential side effects, authentication requirements, or error conditions. The description is minimal but adequate for a simple list operation.

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, concise sentence that directly states the tool's purpose with no unnecessary words. It is front-loaded and efficient.

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 absence of an output schema and annotations, the description lacks information about return values or format. It is adequate for a simple listing tool but could be more complete by mentioning the output (e.g., list of table names).

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 coverage is 100% for the single parameter 'database', and the description does not add extra meaning beyond the schema description. Baseline score of 3 is appropriate.

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

Purpose5/5

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

The description clearly states the specific action (list all tables) and resource (tables in a database). It distinguishes from sibling tools like list_databases (lists databases) and describe_table (describes a specific table).

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. Sibling tools exist (describe_table, list_databases, read_query, write_query) but no criteria for selection are mentioned.

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

read_queryA

Ejecuta una consulta SQL de solo lectura (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH).

ParametersJSON Schema

Name	Required	Description	Default
`database`	Yes	Nombre de la base de datos.
`query`	Yes	Consulta SQL de solo lectura.

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description must carry behavioral transparency. It states the tool is read-only, but lacks details on authentication, rate limits, or error handling. This is sufficient but minimal.

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?

One concise sentence that front-loads the purpose and scope. No 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?

Given the low complexity (2 params, no output schema), the description covers the essential read-only constraint and allowed commands. It could mention return behavior, but is complete enough for an agent to use correctly.

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 coverage is 100%, so the schema already describes both parameters. The description does not add extra meaning beyond listing allowed SQL commands, which is partially related to the query parameter.

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

Purpose5/5

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

The description clearly states the tool executes read-only SQL queries (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH). It specifies the verb 'ejecuta' and resource 'consulta SQL de solo lectura', distinguishing it from write operations.

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

Usage Guidelines4/5

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

The description implies use for read-only queries and explicitly lists allowed SQL commands. It does not directly mention alternatives like write_query, but sibling context makes it clear.

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

write_queryA

Ejecuta una consulta SQL de escritura (INSERT, UPDATE, DELETE, DDL). Requiere MCP_XAMP_ALLOW_WRITE=true.

ParametersJSON Schema

Name	Required	Description	Default
`database`	Yes	Nombre de la base de datos.
`query`	Yes	Consulta SQL de escritura.

TDQS

A4.1/5.0

Behavior3/5

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

Discloses the authorization requirement (MCP_XAMP_ALLOW_WRITE=true), which is useful behavioral context. However, with no annotations, it omits details like error handling, idempotency, or destructiveness.

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?

Single sentence covering purpose and requirement, no fluff. Front-loads critical information.

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?

With no output schema and a destructive tool, the description could mention return value (e.g., affected rows) or security warnings. It provides minimal but sufficient context for basic use.

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?

Schema coverage is 100%, providing baseline 3. Description adds value by specifying query types (INSERT, UPDATE, DELETE, DDL), reinforcing the write nature beyond the schema description.

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

Purpose5/5

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

Clearly states it executes SQL write queries (INSERT, UPDATE, DELETE, DDL). Distinguishes from sibling read_query and metadata tools.

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

Usage Guidelines4/5

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

Implies usage for write operations by listing write command types and a required environment variable, but does not explicitly contrast with read_query or state when not to use.

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.

5 tool updatesv0.1.0Jun 23, 2026
- First observeddescribe_table
- First observedlist_databases
- First observedlist_tables
- First observedread_query
- First observedwrite_query

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Disambiguation4/5

Most tools have distinct purposes, but read_query can also describe a table, creating some overlap with describe_table. However, the specialized describe_table provides a simpler interface.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with snake_case: describe_table, list_databases, list_tables, read_query, write_query.

Tool Count5/5

Five tools is well-scoped for a database server, covering essential operations without unnecessary bloat.

Completeness5/5

The set covers listing databases and tables, describing table structure, and arbitrary read/write SQL queries, including DDL via write_query. This provides full CRUD and schema management capabilities.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Remote Desktop CommanderOAuth
app.desktopcommander
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Shell Access OS Automation
219
mcp
dev.augments
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Developer Tools Documentation Access
2128
Artificial Wit AIOAuth
com.artificialwit
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
ERP Systems CRM Knowledge & Memory
2
DataDoe MCPOAuth
com.datadoe
Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.
E-commerce & Retail CRM
214

Related MCP Servers

mysqldb-mcp-server
Databases Developer Tools
burakdirin
A
license
C
quality
D
maintenance
An MCP server that enables MySQL database integration with Claude. You can execute SQL queries and manage database connections.
Updated a year ago (2025-03-18 00:01 UTC)
2
9
MIT
MariaDB MCP Server
Databases Search
abel9851
A
license
Not graded
quality
D
maintenance
An MCP server implementation that enables Claude to execute read-only queries against MariaDB databases and explore database schemas through natural language.
Updated a year ago (2025-03-26 17:34 UTC)
20
MIT
Database Tools for Claude AI
Databases Search
elber-code
A
license
B
quality
D
maintenance
MCP server that allows Claude AI to interact directly with MySQL databases, enabling query execution and table information retrieval through natural language.
Updated a year ago (2025-04-17 22:41 UTC)
1
15
4
MIT
mysql-mcp-webui
Databases
yashagldit
A
license
Not graded
quality
C
maintenance
MySQL MCP Server enables Claude Desktop and Claude Code to execute SQL queries, explore databases, Webview to add or enable Databases, Connections, and interact with your MySQL data - all through a secure, permission-controlled interface.
Updated 4 months ago (2026-05-21 09:46 UTC)
61
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/yeyorg/mcp-xamp'

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