Allows executing Composer commands within the DDEV web service container for dependency management.
Enables querying, schema inspection, and database management for MariaDB instances within DDEV environments.
Enables querying, schema inspection, and database management for MySQL instances within DDEV environments.
Supports sharing local DDEV projects with external users via ngrok tunnels.
Enables querying, schema inspection, and database management for PostgreSQL instances within DDEV environments.
Allows for the execution of commands within Redis service containers in the DDEV environment.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@DDEV MCP Server list my ddev projects and check their status"
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.
This project provides a Model Context Protocol (MCP) server that enables Large Language Models (LLMs) and AI assistants to interact with DDEV local development environments.
Features include:
🗄️ Query databases directly - Execute SQL queries, inspect schemas, and analyze data in your DDEV MySQL/PostgreSQL databases
🚀 Manage DDEV projects - Start, stop, restart projects and check their status
🔧 Execute development commands - Run Composer, access logs, control Xdebug, and execute shell commands in containers
🛡️ Maintain security - Whitelist-based protection ensures only safe operations are allowed by default
Use Cases:
Database Development: "Show me all users with pending orders" → LLM queries your local database directly
Debugging: "Check the error logs for the last hour" → LLM retrieves and analyzes DDEV service logs
Project Management: "Start my e-commerce project and check if the database is ready" → LLM manages your DDEV environment
Schema Analysis: "What's the relationship between users and orders tables?" → LLM inspects your actual database structure
Development Workflow: "Run the latest migrations and show me the updated schema" → LLM executes commands and verifies results
Related MCP server: Docker MCP Server
ddev_db_backup - Create database snapshots
ddev_db_describe_table - Get table structure/schema (PostgreSQL \d or MySQL DESCRIBE)
ddev_db_list_backups - List available database backups
ddev_db_list_databases - List all databases (PostgreSQL \l or MySQL SHOW DATABASES)
ddev_db_list_tables - List all tables in the database (auto-detects database type)
ddev_db_query - Execute SQL queries with detailed error reporting (supports PostgreSQL, MySQL, MariaDB)
ddev_db_restore - Restore from database snapshots
ddev_list_projects - List all DDEV projects with status
ddev_project_status - Get current status and configuration of a DDEV project
ddev_start_project - Start a DDEV project
ddev_stop_project - Stop a DDEV project
ddev_restart_project - Restart a DDEV project
ddev_exec_command - Execute commands in DDEV web service
ddev_exec_service - Execute commands in specific DDEV services (web, db, redis, etc.)
ddev_ssh - SSH access and connection information
ddev_logs - Get service logs
ddev_composer_command - Run Composer commands
ddev_xdebug - Control Xdebug (on/off/toggle/status)
ddev_share - Share project via ngrok tunnel
ddev_mailpit - Access Mailpit for email testing
ddev_export_db - Export database dumps
ddev_import_db - Import database dumps
🔒 Security Features:
Whitelist Security Model: Only explicitly allowed read-only operations are permitted (default deny)
Comprehensive Protection: Blocks hundreds of potentially dangerous operations by default
Write Protection: All data modification blocked by default unless --allow-write is used
Catastrophic Operation Blocking: DROP DATABASE, SHUTDOWN, file operations always blocked
Configuration Protection: Blocks SET, FLUSH, GRANT, and other config changes
ddev://current - Current project context and server configuration
ddev://config - Current project DDEV configuration
🔒 Whitelist Security Model (Default Deny) The MCP server uses a comprehensive whitelist approach where only explicitly allowed read-only operations are permitted. Any query not matching the whitelist is automatically blocked.
SELECT - Data queries and joins
SHOW - Database/table inspection (TABLES, DATABASES, COLUMNS, etc.)
DESCRIBE / DESC - Table structure
EXPLAIN - Query execution plans
WITH ... SELECT - Common Table Expressions (read-only)
PostgreSQL meta-commands (\dt, \d, \l, etc.)
System catalog queries (INFORMATION_SCHEMA, pg_catalog)
DROP DATABASE / DROP SCHEMA - Catastrophic deletions
SHUTDOWN, KILL - System control
File system access (LOAD_FILE, INTO OUTFILE)
Shell commands (\!, COPY ... FROM PROGRAM)
Other system-level operations
To enable write operations, use the --allow-write flag:
# Enable write operations
ddev-mcp --allow-write
# Enable write operations with single project mode
ddev-mcp --allow-write --single-project my-project⚠️ Warning: Only enable write operations when necessary and ensure you trust the LLM application accessing the server.
The MCP server automatically detects the database type from your DDEV configuration and uses the appropriate commands:
Commands: psql, \dt, \d table_name, \l
Detected from: database.type: postgres in .ddev/config.yaml
Commands: mysql, SHOW TABLES, DESCRIBE table_name, SHOW DATABASES
Detected from: database.type: mysql or database.type: mariadb in .ddev/config.yaml
Reads .ddev/config.yaml to determine database type
Falls back to MySQL if no configuration found
Database type is shown in command output for clarity
Download the NPM package from the latest release and install locally:
# Download the .tgz file from releases, then:
npm install -g ./ddev-mcp-0.8.0.tgz
# Verify installation
ddev-mcp --help# NPM publishing is currently disabled
# Use Option 1 (GitHub Releases) instead
npm install -g ddev-mcp # This will not work currently
# Or install directly from the downloaded package
tar -xzf ddev-mcp-1.0.0.tgz
cd package
npm install -g .# Clone the repository
git clone https://github.com/AkibaAT/ddev-mcp.git
cd ddev-mcp
# Install dependencies and build
npm install
npm run build
# Install globally (optional)
npm install -g .# Clone and install
git clone https://github.com/AkibaAT/ddev-mcp.git
cd ddev-mcp
chmod +x install.sh
./install.shThis will:
✅ Check system requirements (Node.js 20+, DDEV)
📦 Install the server globally via npm
📋 Provide MCP client configuration
{
"mcpServers": {
"ddev": {
"command": "ddev-mcp"
}
}
}{
"mcpServers": {
"ddev": {
"command": "node",
"args": ["/absolute/path/to/ddev-mcp/dist/index.js"]
}
}
}⚠️ Important: When you configure single project mode, the MCP server becomes limited to that single project only. All tools will automatically target the configured project, project selection parameters (project_name) will be hidden from the interface, and the ddev_list_projects command will be disabled for security reasons (to prevent information disclosure about other projects on the system).
{
"mcpServers": {
"ddev": {
"command": "ddev-mcp",
"args": ["--single-project", "project-id"]
}
}
}Use Case: Perfect when working on a single project and you want a clean, dedicated interface without repetitive project parameters.
{
"mcpServers": {
"ddev-write": {
"command": "ddev-mcp",
"args": ["--allow-write", "--single-project", "development-site"]
}
}
}{
"mcpServers": {
"ddev": {
"command": "ddev-mcp"
}
}
}Use Case: When working with multiple DDEV projects, you can specify project_name or project_path for each command.
All tools will show project selection parameters.
{
"mcpServers": {
"ddev-production": {
"command": "ddev-mcp",
"args": ["--single-project", "main-site"]
},
"ddev-development": {
"command": "ddev-mcp",
"args": ["--allow-write", "--single-project", "dev-site"]
}
}
}Use Case: Separate MCP servers for different projects with different security levels (e.g., read-only for production, write-enabled for development).
Mode | Configuration | Project Parameters |
| Use Case |
Single Project |
| Hidden (automatic) | Disabled (security) | Dedicated development on one project |
Multi-Project | No default args | Visible (required) | Available | Working across multiple projects |
Multiple Servers | Multiple servers with different single projects | Hidden per server | Disabled per server | Different projects with different access levels |
Configuration file locations depend on your MCP client. Common examples:
Generic MCP Client: ~/.config/mcp/config.json
Application-specific: Check your MCP client documentation for the correct path
🎯 Intelligent Project Context
When you configure single project mode, the MCP server provides rich contextual information to LLMs through the
ddev://current resource.
The ddev://current resource provides real-time:
Project Details: Name, status, database type, URL
Server Configuration: Security mode, default settings
Dynamic Status: Current project state (updated when accessed)
Example Response:
{
"project": {
"name": "project-id",
"status": "running",
"dbType": "postgres",
"url": "https://project-id.ddev.site",
"description": "DDEV project 'project-id' (running) using postgres database"
},
"serverConfig": {
"securityMode": "read-only",
"allowWriteOperations": false
}
}The MCP server supports different project targeting modes depending on your configuration:
// Clean interface - no project parameters needed or visible
{
"name": "ddev_db_query",
"arguments": {
"query": "SELECT COUNT(*) FROM games;"
}
}All commands automatically target the configured single project.
// Use Project Name
{
"name": "ddev_db_query",
"arguments": {
"project_name": "project-id",
"query": "SELECT COUNT(*) FROM users;"
}
}// Start a specific project
{
"name": "ddev_start_project",
"arguments": {
"project_name": "my-site"
}
}Project parameters are visible and required for targeting specific projects.
When no single project restriction is configured, the server resolves projects in this order:
Explicit project_name - Uses the specified DDEV project name
Current directory - Fallback if no project name provided
Note: In single project mode, all commands automatically use the configured project.
# Global installation
npx @modelcontextprotocol/inspector ddev-mcp
# Local installation
npx @modelcontextprotocol/inspector node dist/index.js
# Development mode
npx @modelcontextprotocol/inspector node --loader ts-node/esm index.ts# Check if globally installed
which ddev-mcp
# Test DDEV integration
ddev list --json-outputNode.js 20+
DDEV installed and accessible via PATH
DDEV projects configured
npm run dev # Run with ts-node
npm run build # Build TypeScript
npm run start # Run built versionnpm run lint # Run ESLint
npm run lint:fix # Fix auto-fixable ESLint issues
npm run lint:check # Run ESLint with strict checking (CI)npm run test # Run tests
npm run test:watch # Run tests in watch mode
npm run test:ci # Run tests for CI (with coverage)Run a Composer command in the DDEV project
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | Composer command to run | |
| project_name | No | Name of the DDEV project |
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 but provides minimal information. It mentions running a command but doesn't disclose execution context (e.g., where it runs, permissions needed), potential side effects (e.g., package installation/modification), error handling, or output characteristics. For a command execution tool with zero annotation coverage, this leaves significant behavioral gaps.
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's appropriately sized for a simple command execution tool and front-loads the essential information. Every word earns its place with zero waste.
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 command execution tools and the absence of both annotations and output schema, the description is insufficiently complete. It doesn't explain what happens when the command runs (e.g., execution environment, output format, error conditions), nor does it address common use cases or limitations. For a tool that could have significant behavioral implications, 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 both parameters ('command' and 'project_name') with their types and descriptions. The description adds no additional parameter semantics beyond what the schema provides—it doesn't clarify command syntax examples, project_name defaults, or parameter interactions. The baseline 3 is appropriate when the 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 action ('Run') and target ('a Composer command in the DDEV project'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'ddev_exec_command' which might also run commands, leaving some ambiguity about when to use this specific Composer-focused tool versus general command execution.
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. There's no mention of when to choose this Composer-specific tool over 'ddev_exec_command' for general commands, or whether it should be used instead of direct Composer execution outside DDEV. No prerequisites, exclusions, or contextual boundaries are specified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a SQL query on the DDEV database
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | SQL query to execute | |
| database | No | Database name (optional) | |
| project_name | No | Name of the DDEV project |
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 but provides minimal information. It states the action ('Execute a SQL query') which implies both read and write operations are possible, but doesn't disclose any behavioral traits like permissions needed, whether queries can be destructive, transaction handling, error behavior, or result format. For a database query tool with zero annotation coverage, this is inadequate.
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 extremely concise with just one sentence that directly states the tool's purpose. There's zero wasted language or unnecessary elaboration. It's appropriately sized for what it communicates and is front-loaded with the essential information.
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?
For a database query tool with 3 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't address important contextual information like what types of SQL queries are supported, whether it's read-only or can modify data, what authentication is required, how results are returned, or error handling. The description provides only the most basic functional statement without the necessary context for safe and effective use.
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 three parameters (query, database, project_name) with their descriptions. The tool description doesn't add any meaningful parameter semantics beyond what's in the schema - it mentions 'SQL query' which is already covered by the schema's description of the 'query' parameter. Baseline 3 is appropriate when the 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 action ('Execute a SQL query') and target resource ('on the DDEV database'), providing a specific verb+resource combination. However, it doesn't distinguish this tool from potential database-related siblings (none are listed among the provided sibling tools, but the description doesn't address this).
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. There's no mention of when this tool is appropriate, what prerequisites might exist, or how it differs from other database interaction methods. The sibling tools are all DDEV-related but serve different purposes, yet the description doesn't help the agent understand this distinction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a command inside the DDEV web service
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | Command to execute in the web service | |
| project_name | No | Name of the DDEV project |
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 cover important aspects like whether this requires specific permissions, if it's destructive, what happens on failure, rate limits, or output format. For a command execution tool with zero annotation coverage, this leaves significant gaps.
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 any wasted words. It's appropriately sized and front-loaded with the essential information.
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?
For a command execution tool with no annotations and no output schema, the description is insufficient. It doesn't explain what kind of commands are appropriate, what environment they run in, what permissions are needed, or what the response looks like. Given the complexity of command execution and lack of structured data, more guidance 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 both parameters adequately. The description doesn't add any meaningful parameter semantics beyond what's in the schema - it mentions executing a command but doesn't clarify syntax, shell environment, or project context beyond what the parameter descriptions provide.
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 ('execute a command') and target ('inside the DDEV web service'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like ddev_composer_command or ddev_db_query, which also execute commands in related contexts.
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 when to choose ddev_exec_command over ddev_composer_command or ddev_db_query, nor does it specify prerequisites or appropriate contexts for execution.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all DDEV projects with their status and information
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a listing operation but doesn't describe whether it requires authentication, what format the output takes, whether it's paginated, if there are rate limits, or what happens with no projects. For a tool with zero annotation coverage, this leaves significant behavioral gaps.
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 states exactly what the tool does with zero wasted words. It's appropriately sized for a simple listing tool and front-loads the core functionality. Every word earns its place.
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 (no parameters, no annotations, no output schema), the description is minimally adequate. It states what the tool does but lacks important context about output format, authentication needs, or error conditions. For a listing tool with no structured metadata, the description should provide more behavioral context to be truly complete.
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 zero parameters, and schema description coverage is 100% (empty schema is fully described). The description appropriately doesn't discuss parameters since none exist. Baseline for zero parameters with full schema coverage is 4, as the description correctly focuses on the tool's purpose rather than nonexistent parameters.
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 verb ('List') and resource ('DDEV projects') with specific scope ('all'), and mentions what information is returned ('status and information'). It distinguishes from siblings like 'ddev_project_status' which likely checks a single project, but doesn't explicitly contrast with other listing/searching tools that might exist.
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 'ddev_project_status' or 'dsearch' tools. It doesn't mention prerequisites, timing considerations, or any explicit 'when-not-to-use' scenarios. The agent must infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the current status and configuration of a DDEV project
| Name | Required | Description | Default |
|---|---|---|---|
| project_name | No | Name of the DDEV project |
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 retrieves status and configuration, implying a read-only operation, but doesn't clarify aspects like whether it requires specific permissions, what format the output returns, if there are rate limits, or how it handles errors. This leaves significant gaps in understanding the tool's behavior beyond its basic purpose.
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, well-structured sentence that efficiently conveys the core purpose without unnecessary words. It's front-loaded with the key action ('Get') and resource, making it easy to parse. Every part of the sentence earns its place by specifying what is retrieved (status and configuration) and for what (a DDEV project).
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 moderate complexity (a status check with one parameter) and the absence of both annotations and an output schema, the description is incomplete. It doesn't explain what 'status and configuration' entails, the format of the return value, or any behavioral nuances. For a tool with no structured metadata, more descriptive detail is needed to fully guide an AI agent.
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 input schema has 100% description coverage, with the single parameter 'project_name' clearly documented. The description doesn't add any additional semantic context beyond what the schema provides, such as examples of project names or constraints. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, though no extra value is added.
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 with a specific verb ('Get') and resource ('current status and configuration of a DDEV project'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'ddev_list_projects' (which lists projects) or 'ddev_exec_command' (which executes commands), leaving some ambiguity about when to choose this specific status tool over alternatives.
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 its siblings. It doesn't mention alternatives like 'ddev_list_projects' for listing projects or 'ddev_exec_command' for executing commands, nor does it specify prerequisites or contextual cues for selecting this status-checking tool over others in the DDEV toolset.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose with no ambiguity: composer commands, database queries, command execution, project listing, and project status retrieval. The descriptions specify different targets (Composer, database, web service, projects) and actions (run, execute, list, get), making misselection unlikely.
All tool names follow a consistent 'ddev_' prefix with a descriptive verb_noun pattern (e.g., ddev_composer_command, ddev_db_query). This predictable naming scheme enhances readability and agent usability without any deviations or mixed conventions.
With 5 tools, the server is well-scoped for managing DDEV projects, covering key operations like project listing, status checks, and command execution. Each tool earns its place by addressing distinct aspects of DDEV management without being overly sparse or bloated.
The tool set provides solid coverage for core DDEV workflows, including project discovery, status monitoring, and execution of commands. A minor gap exists in lifecycle management (e.g., starting/stopping projects or creating new ones), but agents can likely work around this using existing tools like ddev_exec_command.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Develop, manage, and debug Railway projects, services, and deployments from within agents.
Deploy and manage your apps, databases, storage, and scheduled jobs from your AI agent
Plan Salesforce deploys, open pull requests and trigger pipelines from your AI client.
Your AI Agent's Infrastructure Layer. Connect Claude, Copilot, Codex, or ChatGPT to 200+ managed open source services. Start databases, pipelines, and applications through natural language.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AkibaAT/ddev-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
