New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Run any server from the Docker MCP Catalog in its own

Docker MCP gateway

by docker · MIT license · ★ 1,579 on GitHub · updated Sep 16

Docker MCP gateway cover

Docker's own CLI plugin: run any server from the Docker MCP Catalog in its own container, behind one connection, with secrets kept out of env vars.

# Docker MCP Plugin and Docker MCP Gateway

![build](https://github.com/docker/mcp-gateway/actions/workflows/ci.yml/badge.svg)

The [MCP Toolkit](https://docs.docker.com/ai/mcp-catalog-and-toolkit/toolkit/), in Docker Desktop, allows
developers to configure and consume MCP servers from the [Docker MCP Catalog](https://hub.docker.com/mcp).

Underneath, the Toolkit is powered by a docker CLI plugin: `docker-mcp`. This repository is the code of this CLI plugin. It can work in Docker Desktop or independently.

The main feature of this CLI is the **Docker MCP Gateway** which allows easy and secure running and deployment of MCP servers. See [Features](#Features) for a list of all the features.

## What is MCP?

The [Model Context Protocol (MCP)](https://spec.modelcontextprotocol.io/) is an open protocol that standardizes how AI applications connect to external data sources and tools. It provides a secure, controlled way for language models to access and interact with various services, databases, and APIs.

## Overview

Developers face criticial barriers when integrating Model Context Protocol (MCP) tools into production workflows:

Overview

The MCP Toolkit, in Docker Desktop, allows developers to configure and consume MCP servers from the Docker MCP Catalog.

What you get

  • 🐳 Container-based Servers: Run MCP servers as Docker containers with proper iso
  • 🔧 Server Management: List, inspect, and call MCP tools, resources and prompts f
  • 🔐 Secrets Management: Secure handling of API keys and credentials via Docker De
  • 🌐 OAuth Integration: Built-in OAuth flows for service authentication.
  • 📋 Server Catalog: Manage and configure multiple MCP catalogs.
  • 🔍 Dynamic Discovery: Automatic tool, prompt, and resource discovery from runnin
Manual install (npx, ZIP)
Claude Codemkdir -p ~/.claude/agents && curl -sL https://raw.githubusercontent.com/docker/mcp-gateway/a34df45d4ec0e941a9853ad768c4f6cd818966b3/README.md \ -o ~/.claude/agents/README.md
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\agents" | Out-Null; Invoke-WebRequest "https://raw.githubusercontent.com/docker/mcp-gateway/a34df45d4ec0e941a9853ad768c4f6cd818966b3/README.md" -OutFile "$HOME\.claude\agents\README.md"

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • README.md11.5 KB
Read the files here
docker/a34df451 file
Shared references3SKILL.md reads these from elsewhere in the repo. Not in the ZIP.Get them on GitHub ↗
README.md
Show the full text344 lines

Docker MCP Plugin and Docker MCP Gateway

build

The MCP Toolkit, in Docker Desktop, allows developers to configure and consume MCP servers from the Docker MCP Catalog.

Underneath, the Toolkit is powered by a docker CLI plugin: docker-mcp. This repository is the code of this CLI plugin. It can work in Docker Desktop or independently.

The main feature of this CLI is the Docker MCP Gateway which allows easy and secure running and deployment of MCP servers. See Features for a list of all the features.

What is MCP?

The Model Context Protocol (MCP) is an open protocol that standardizes how AI applications connect to external data sources and tools. It provides a secure, controlled way for language models to access and interact with various services, databases, and APIs.

Overview

Developers face criticial barriers when integrating Model Context Protocol (MCP) tools into production workflows:

  • Managing MCP server lifecycle Each local MCP sever in the catalog runs in an isolated Docker container. npx and uvx servers are granted minimal host privileges.
  • Providing a unified interface AI models access MCP servers through a single Gateway.
  • Handling authentication and security Keep secrets out of environment variables using Docker Desktop's secrets management.
  • Supports dynamic tool discovery and configuration. Each MCP client (eg VS Code, Cursor, Claude Desktop, etc.) connects to the same Gateway configuration, ensuring consistency across different clients.
  • Enables OAuth flows for MCPs that require OAuth access token service connections.

Features

  • 🐳 Container-based Servers: Run MCP servers as Docker containers with proper isolation.
  • 🔧 Server Management: List, inspect, and call MCP tools, resources and prompts from multiple servers.
  • 🔐 Secrets Management: Secure handling of API keys and credentials via Docker Desktop.
  • 🌐 OAuth Integration: Built-in OAuth flows for service authentication.
  • 📋 Server Catalog: Manage and configure multiple MCP catalogs.
  • 🔍 Dynamic Discovery: Automatic tool, prompt, and resource discovery from running servers.
  • 📊 Monitoring: Built-in logging and call tracing capabilities.

Installation

Prerequisites
  • Docker Desktop 4.59+ (with MCP Toolkit feature enabled)
- Go 1.24+ (for development)
Install as Docker CLI Plugin

The MCP cli will already be installed on recent versions of Docker Desktop but you can build and install the latest version by following these steps:

# Clone the repository
git clone https://github.com/docker/mcp-gateway.git
cd mcp-gateway
mkdir -p "$HOME/.docker/cli-plugins/"

# Build and install the plugin
make docker-mcp

After installation, the plugin will be available as:

docker mcp --help

Usage

[!NOTE] Running without Docker Desktop Feature Flags

If you encounter "Docker Desktop is not running" errors when the Docker daemon is active, you can bypass Desktop feature checks by setting:

export DOCKER_MCP_IN_CONTAINER=1

This is useful when running in WSL2, containerized environments, or Docker CE where Desktop backend sockets are unavailable.

[!NOTE] Enabling Profiles outside Docker Desktop

Profiles are enabled automatically in Docker Desktop. If you are using the CLI independently (e.g. Docker CE, WSL2, or a containerized environment), enable the profiles feature first:

docker mcp feature enable profiles
Profile Management

Servers are organized into profiles. A profile groups related MCP servers together and can be connected to clients, exported, and shared via OCI registries.

Servers in a profile can reference multiple sources:

  • Catalog references: catalog://mcp/docker-mcp-catalog/github
  • OCI image references: docker://my-server:latest
  • MCP Registry references: https://registry.modelcontextprotocol.io/v0/servers/<id>
  • Local file references: file://./server.yaml
# Make sure to `docker mcp catalog pull mcp/docker-mcp-catalog` first.

# Create a new profile
docker mcp profile create --name dev-tools \
  --server catalog://mcp/docker-mcp-catalog/github

# Create a profile and connect it to a client
docker mcp profile create --name dev-tools \
  --server catalog://mcp/docker-mcp-catalog/github \
  --connect cursor

# List all profiles
docker mcp profile list

# Show profile details
docker mcp profile show <profile-id>

# Remove a profile
docker mcp profile remove <profile-id>

# Export/import profiles
docker mcp profile export <profile-id> output.yaml
docker mcp profile import input.yaml

# Push/pull profiles to OCI registries
docker mcp profile push <profile-id> <oci-reference>
docker mcp profile pull <oci-reference>
Manage servers in a profile
# List servers across all profiles
docker mcp profile server ls

# Filter servers by name or profile
docker mcp profile server ls --filter name=github
docker mcp profile server ls --filter profile=dev-tools

# Add servers to a profile
docker mcp profile server add dev-tools \
  --server catalog://mcp/docker-mcp-catalog/notion

# Remove servers from a profile
docker mcp profile server remove dev-tools github slack
Configure servers in a profile
# Set configuration values (<server-name>.<config-key>=<value>)
docker mcp profile config <profile-id> --set github.timeout=30

# Get configuration values (<server-name>.<config-key>)
docker mcp profile config <profile-id> --get github.timeout

# Get all configuration
docker mcp profile config <profile-id> --get-all

# Delete configuration values (<server-name>.<config-key>)
docker mcp profile config <profile-id> --del github.timeout
Manage tool allowlists in a profile
# Enable specific tools (dot notation: <server>.<tool>)
docker mcp profile tools <profile-id> --enable github.create_issue --enable github.list_repos

# Disable specific tools
docker mcp profile tools <profile-id> --disable github.search_code

# Enable/disable all tools for a server
docker mcp profile tools <profile-id> --enable-all github
docker mcp profile tools <profile-id> --disable-all github
Catalog Management

Manage the OCI-based catalogs available to the MCP gateway. The default catalog is the image mcp/docker-mcp-catalog.

# List catalogs
docker mcp catalog ls

# Show a catalog
docker mcp catalog show <oci-reference>

# Create a catalog from server references
docker mcp catalog create myorg/catalog:latest --title "My Catalog" \
  --server catalog://mcp/docker-mcp-catalog/github \
  --server file://./my-server.yaml

# Create a catalog from an existing profile
docker mcp catalog create myorg/catalog:latest --from-profile dev-tools

# Create a catalog from the community registry
docker mcp catalog create myorg/catalog:latest \
  --from-community-registry registry.modelcontextprotocol.io

# Push/pull catalogs to OCI registries
docker mcp catalog push <oci-reference>
docker mcp catalog pull <oci-reference>

# Manage servers within a catalog
docker mcp catalog server ls <oci-reference>
docker mcp catalog server add <oci-reference> --server docker://my-server:latest
docker mcp catalog server remove <oci-reference> github
docker mcp catalog server inspect <oci-reference> <server-name>

# Remove a catalog
docker mcp catalog remove <oci-reference>

# Tag a catalog
docker mcp catalog tag <source>:<tag> <target>:<tag>

More about importing from the OSS MCP Community Registry.

MCP Gateway Operations

Start up an MCP Gateway. This can be used for one client, or to service multiple clients if using either sse or streaming transports.

# Run the MCP gateway (stdio, using the default profile)
docker mcp gateway run

# Run with a specific profile
docker mcp gateway run --profile dev-tools

# Run the MCP gateway (streaming)
docker mcp gateway run --port 8080 --transport streaming

If no --profile flag is provided, the gateway uses the default profile.

Client Connection

Connect AI clients to the MCP gateway.

# List client configurations
docker mcp client ls

# Connect a client to a profile
docker mcp client connect <client-name> --profile <profile-id>

# Disconnect from a client
docker mcp client disconnect <client-name>
Secrets and OAuth

Configure MCP servers that require either secrets or OAuth.

# Manage secrets
docker mcp secret --help

# Handle OAuth flows
docker mcp oauth --help

# export any desktop secrets needed by either server1 or server2
#   (temporary requirement to export secrets for docker cloud runs - this command
#    will no longer be required once Docker Cloud can access secret stores)
docker mcp secret export server1 server2
Tool Management
# Count available tools
docker mcp tools count

# List all available MCP tools
docker mcp tools ls

# List all available MCP tools in JSON format
docker mcp tools ls --format=json

# Inspect a specific tool
docker mcp tools inspect <tool-name>

# Call a tool with arguments
docker mcp tools call <tool-name> [arguments...]

# Enable/disable tools for a server in a profile
docker mcp profile tools <profile-id> --enable <server>.<tool>
docker mcp profile tools <profile-id> --disable <server>.<tool>

Configuration

Configuration is stored in a local database. Profiles, catalogs, and server configuration are managed through the docker mcp profile and docker mcp catalog commands. Feature flags are stored in ~/.docker/config.json.

Environment Variables

The MCP CLI respects the following environment variables for client configuration:

  • CLAUDE_CONFIG_DIR: Override the default Claude Code configuration directory (~/.claude). When set, Claude Code will use $CLAUDE_CONFIG_DIR/.claude.json instead of ~/.claude.json for its MCP server configuration. This is useful for:
    • Maintaining separate Claude Code installations for work and personal use
    • Testing configuration changes in isolation
    • Managing multiple Claude Code profiles

Example usage:

# Set custom Claude Code configuration directory
export CLAUDE_CONFIG_DIR=/path/to/custom/config

# Connect MCP Gateway to Claude Code
docker mcp client connect claude-code --profile dev-tools --global

# Claude Code will now use /path/to/custom/config/.claude.json

Architecture

The Docker MCP CLI implements a gateway pattern:

AI Client → MCP Gateway → MCP Servers (Docker Containers)
  • AI Client: Language model or AI application
  • MCP Gateway: This CLI tool managing protocol translation and routing
  • MCP Servers: Individual MCP servers running in Docker containers

See docs/message-flow.md for detailed message flow diagrams.

Contributing

The build instructions are available in the contribution guide.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

1# Docker MCP Plugin and Docker MCP Gateway
2 
3![build](https://github.com/docker/mcp-gateway/actions/workflows/ci.yml/badge.svg)
4 
5The [MCP Toolkit](https://docs.docker.com/ai/mcp-catalog-and-toolkit/toolkit/), in Docker Desktop, allows
6developers to configure and consume MCP servers from the [Docker MCP Catalog](https://hub.docker.com/mcp).
7 
8Underneath, the Toolkit is powered by a docker CLI plugin: `docker-mcp`. This repository is the code of this CLI plugin. It can work in Docker Desktop or independently.
9 
10The main feature of this CLI is the **Docker MCP Gateway** which allows easy and secure running and deployment of MCP servers. See [Features](#Features) for a list of all the features.
11 
12## What is MCP?
13 
14The [Model Context Protocol (MCP)](https://spec.modelcontextprotocol.io/) is an open protocol that standardizes how AI applications connect to external data sources and tools. It provides a secure, controlled way for language models to access and interact with various services, databases, and APIs.
15 
16## Overview
17 
18Developers face criticial barriers when integrating Model Context Protocol (MCP) tools into production workflows:
19 
20- **Managing MCP server lifecycle** Each local MCP sever in the catalog runs in an isolated Docker container. npx and uvx servers are granted minimal host privileges.
21- **Providing a unified interface** AI models access MCP servers through a single Gateway.
22- **Handling authentication and security** Keep secrets out of environment variables using Docker Desktop's secrets management.
23- **Supports dynamic tool discovery** and configuration. Each MCP client (eg VS Code, Cursor, Claude Desktop, etc.) connects to the same Gateway configuration, ensuring consistency across different clients.
24- **Enables OAuth flows** for MCPs that require OAuth access token service connections.
25 
26## Features
27 
28- 🐳 **Container-based Servers**: Run MCP servers as Docker containers with proper isolation.
29- 🔧 **Server Management**: List, inspect, and call MCP tools, resources and prompts from multiple servers.
30- 🔐 **Secrets Management**: Secure handling of API keys and credentials via Docker Desktop.
31- 🌐 **OAuth Integration**: Built-in OAuth flows for service authentication.
32- 📋 **Server Catalog**: Manage and configure multiple MCP catalogs.
33- 🔍 **Dynamic Discovery**: Automatic tool, prompt, and resource discovery from running servers.
34- 📊 **Monitoring**: Built-in logging and call tracing capabilities.
35 
36## Installation
37 
38### Prerequisites
39 
40- Docker Desktop `4.59+` (with MCP Toolkit feature enabled)
41 
42<div align="left">
43 <img src="./img/enable_toolkit.png" width="400"/>
44</div>
45- Go 1.24+ (for development)
46 
47### Install as Docker CLI Plugin
48 
49The MCP cli will already be installed on recent versions of Docker Desktop but you can build and install the latest version by following these steps:
50 
51```bash
52# Clone the repository
53git clone https://github.com/docker/mcp-gateway.git
54cd mcp-gateway
55mkdir -p "$HOME/.docker/cli-plugins/"
56 
57# Build and install the plugin
58make docker-mcp
59```
60 
61After installation, the plugin will be available as:
62 
63```bash
64docker mcp --help
65```
66 
67## Usage
68 
69> [!NOTE]
70> **Running without Docker Desktop Feature Flags**
71>
72> If you encounter "Docker Desktop is not running" errors when the Docker daemon is active, you can bypass Desktop feature checks by setting:
73> ```bash
74> export DOCKER_MCP_IN_CONTAINER=1
75> ```
76> This is useful when running in WSL2, containerized environments, or Docker CE where Desktop backend sockets are unavailable.
77 
78> [!NOTE]
79> **Enabling Profiles outside Docker Desktop**
80>
81> Profiles are enabled automatically in Docker Desktop. If you are using the CLI independently (e.g. Docker CE, WSL2, or a containerized environment), enable the profiles feature first:
82> ```bash
83> docker mcp feature enable profiles
84> ```
85 
86### Profile Management
87 
88Servers are organized into **profiles**. A profile groups related MCP servers together and can be connected to clients, exported, and shared via OCI registries.
89 
90Servers in a profile can reference multiple sources:
91- **Catalog references**: `catalog://mcp/docker-mcp-catalog/github`
92- **OCI image references**: `docker://my-server:latest`
93- **MCP Registry references**: `https://registry.modelcontextprotocol.io/v0/servers/<id>`
94- **Local file references**: `file://./server.yaml`
95 
96```bash
97# Make sure to `docker mcp catalog pull mcp/docker-mcp-catalog` first.
98 
99# Create a new profile
100docker mcp profile create --name dev-tools \
101 --server catalog://mcp/docker-mcp-catalog/github
102 
103# Create a profile and connect it to a client
104docker mcp profile create --name dev-tools \
105 --server catalog://mcp/docker-mcp-catalog/github \
106 --connect cursor
107 
108# List all profiles
109docker mcp profile list
110 
111# Show profile details
112docker mcp profile show <profile-id>
113 
114# Remove a profile
115docker mcp profile remove <profile-id>
116 
117# Export/import profiles
118docker mcp profile export <profile-id> output.yaml
119docker mcp profile import input.yaml
120 
121# Push/pull profiles to OCI registries
122docker mcp profile push <profile-id> <oci-reference>
123docker mcp profile pull <oci-reference>
124```
125 
126#### Manage servers in a profile
127 
128```bash
129# List servers across all profiles
130docker mcp profile server ls
131 
132# Filter servers by name or profile
133docker mcp profile server ls --filter name=github
134docker mcp profile server ls --filter profile=dev-tools
135 
136# Add servers to a profile
137docker mcp profile server add dev-tools \
138 --server catalog://mcp/docker-mcp-catalog/notion
139 
140# Remove servers from a profile
141docker mcp profile server remove dev-tools github slack
142```
143 
144#### Configure servers in a profile
145 
146```bash
147# Set configuration values (<server-name>.<config-key>=<value>)
148docker mcp profile config <profile-id> --set github.timeout=30
149 
150# Get configuration values (<server-name>.<config-key>)
151docker mcp profile config <profile-id> --get github.timeout
152 
153# Get all configuration
154docker mcp profile config <profile-id> --get-all
155 
156# Delete configuration values (<server-name>.<config-key>)
157docker mcp profile config <profile-id> --del github.timeout
158```
159 
160#### Manage tool allowlists in a profile
161 
162```bash
163# Enable specific tools (dot notation: <server>.<tool>)
164docker mcp profile tools <profile-id> --enable github.create_issue --enable github.list_repos
165 
166# Disable specific tools
167docker mcp profile tools <profile-id> --disable github.search_code
168 
169# Enable/disable all tools for a server
170docker mcp profile tools <profile-id> --enable-all github
171docker mcp profile tools <profile-id> --disable-all github
172```
173 
174### Catalog Management
175 
176Manage the OCI-based catalogs available to the MCP gateway. The [default catalog](https://hub.docker.com/mcp) is the image `mcp/docker-mcp-catalog`.
177 
178```bash
179# List catalogs
180docker mcp catalog ls
181 
182# Show a catalog
183docker mcp catalog show <oci-reference>
184 
185# Create a catalog from server references
186docker mcp catalog create myorg/catalog:latest --title "My Catalog" \
187 --server catalog://mcp/docker-mcp-catalog/github \
188 --server file://./my-server.yaml
189 
190# Create a catalog from an existing profile
191docker mcp catalog create myorg/catalog:latest --from-profile dev-tools
192 
193# Create a catalog from the community registry
194docker mcp catalog create myorg/catalog:latest \
195 --from-community-registry registry.modelcontextprotocol.io
196 
197# Push/pull catalogs to OCI registries
198docker mcp catalog push <oci-reference>
199docker mcp catalog pull <oci-reference>
200 
201# Manage servers within a catalog
202docker mcp catalog server ls <oci-reference>
203docker mcp catalog server add <oci-reference> --server docker://my-server:latest
204docker mcp catalog server remove <oci-reference> github
205docker mcp catalog server inspect <oci-reference> <server-name>
206 
207# Remove a catalog
208docker mcp catalog remove <oci-reference>
209 
210# Tag a catalog
211docker mcp catalog tag <source>:<tag> <target>:<tag>
212```
213 
214 
215More about [importing from the OSS MCP Community Registry](docs/catalog.md#importing-from-the-oss-mcp-community-registry).
216 
217### MCP Gateway Operations
218 
219Start up an MCP Gateway. This can be used for one client, or to service multiple clients if using either `sse` or `streaming` transports.
220 
221```bash
222# Run the MCP gateway (stdio, using the default profile)
223docker mcp gateway run
224 
225# Run with a specific profile
226docker mcp gateway run --profile dev-tools
227 
228# Run the MCP gateway (streaming)
229docker mcp gateway run --port 8080 --transport streaming
230```
231 
232If no `--profile` flag is provided, the gateway uses the `default` profile.
233 
234* more about [the MCP Gateway](docs/mcp-gateway.md)
235 
236### Client Connection
237 
238Connect AI clients to the MCP gateway.
239 
240```bash
241# List client configurations
242docker mcp client ls
243 
244# Connect a client to a profile
245docker mcp client connect <client-name> --profile <profile-id>
246 
247# Disconnect from a client
248docker mcp client disconnect <client-name>
249```
250 
251### Secrets and OAuth
252 
253Configure MCP servers that require either secrets or OAuth.
254 
255```bash
256# Manage secrets
257docker mcp secret --help
258 
259# Handle OAuth flows
260docker mcp oauth --help
261 
262# export any desktop secrets needed by either server1 or server2
263# (temporary requirement to export secrets for docker cloud runs - this command
264# will no longer be required once Docker Cloud can access secret stores)
265docker mcp secret export server1 server2
266```
267 
268### Tool Management
269 
270```bash
271# Count available tools
272docker mcp tools count
273 
274# List all available MCP tools
275docker mcp tools ls
276 
277# List all available MCP tools in JSON format
278docker mcp tools ls --format=json
279 
280# Inspect a specific tool
281docker mcp tools inspect <tool-name>
282 
283# Call a tool with arguments
284docker mcp tools call <tool-name> [arguments...]
285 
286# Enable/disable tools for a server in a profile
287docker mcp profile tools <profile-id> --enable <server>.<tool>
288docker mcp profile tools <profile-id> --disable <server>.<tool>
289```
290 
291## Configuration
292 
293Configuration is stored in a local database. Profiles, catalogs, and server configuration are managed through the `docker mcp profile` and `docker mcp catalog` commands. Feature flags are stored in `~/.docker/config.json`.
294 
295### Environment Variables
296 
297The MCP CLI respects the following environment variables for client configuration:
298 
299- **`CLAUDE_CONFIG_DIR`**: Override the default Claude Code configuration directory (`~/.claude`). When set, Claude Code will use `$CLAUDE_CONFIG_DIR/.claude.json` instead of `~/.claude.json` for its MCP server configuration. This is useful for:
300 - Maintaining separate Claude Code installations for work and personal use
301 - Testing configuration changes in isolation
302 - Managing multiple Claude Code profiles
303 
304Example usage:
305```bash
306# Set custom Claude Code configuration directory
307export CLAUDE_CONFIG_DIR=/path/to/custom/config
308 
309# Connect MCP Gateway to Claude Code
310docker mcp client connect claude-code --profile dev-tools --global
311 
312# Claude Code will now use /path/to/custom/config/.claude.json
313```
314 
315## Architecture
316 
317The Docker MCP CLI implements a gateway pattern:
318 
319```
320AI Client → MCP Gateway → MCP Servers (Docker Containers)
321```
322 
323- **AI Client**: Language model or AI application
324- **MCP Gateway**: This CLI tool managing protocol translation and routing
325- **MCP Servers**: Individual MCP servers running in Docker containers
326 
327See [docs/message-flow.md](docs/message-flow.md) for detailed message flow diagrams.
328 
329## Contributing
330 
331The build instructions are available in the [contribution guide](CONTRIBUTING.md).
332 
333## License
334 
335This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
336 
337## Support
338 
339- 💬 [Troubleshooting](/docs/troubleshooting.md)
340- 📖 [MCP Specification](https://modelcontextprotocol.io/specification/2025-11-25)
341- 🐳 [Docker Desktop Documentation](https://docs.docker.com/desktop/)
342- 🐛 [Report Issues](https://github.com/docker/mcp-gateway/issues)
343- 💬 [Discussions](https://github.com/docker/mcp-gateway/discussions)
344 
View all files on GitHub →

Details

Updated
Sep 16, 2026
License
MIT
Stars on the repo
★ 1,579
Checked
Source
docker/mcp-gateway ↗
Creator
docker · 1 listing
View creator

Similar MCP servers

See all →
SkillFrom a business idea, app ideaAzure app onboardmicrosoft/skills · by microsoftEnd-to-end orchestrator: from a business idea, app idea, or existing app to running Azure deployment with cost estimates and pre-deploy approval. Analyzes your app, auto-detects the right Azure services, scaffolds infrastructure code, and deploys — tailored to your app, not a template. Handles moving existing apps to Azure without rewriting or with minimal changes. WHEN: bring your app to Azure, plan my app, cost to run, is my code ready to deploy, deploy my app to the cloud, deploy all my services, what Azure services do I need, plan my Azure deployment, deploy my new app to Azure, one-click deploy, I have an app and want it on Azure, migrate my app to Azure, help me get started, build an app, no code yet, starter project. DO NOT USE FOR: use azd for deployment(use azure-deploy), optimizing existing costs (use cost-optimization), code readiness checks only (use azure-app-onboard-prereq).★ 3.1k GitHub starsSkillAssess whether source code is ready to deploy to AzureAzure App Onboard Prereq — Repository Evaluationmicrosoft/skills · by microsoftAssess whether source code is ready to deploy to Azure — the check BEFORE infrastructure work. Evaluates build health, app completeness, dependencies and local services, stack compatibility, and deployment feasibility. Answers questions about what your app needs before it can be deployed — frameworks, dependencies, and configuration. Checks whether dependencies are compatible and identifies deployment blockers and unsupported frameworks. WHEN: "evaluate my repo", "is my app ready to deploy", "what does my app need to deploy", "what do I need before deploying", "does my app need", "can I ship this to Azure", "scan my repo for issues", "is this app deployable", "check if my app is ready for Azure", "do I need a Dockerfile", "what's blocking my deployment", "are there any blockers", "are my dependencies compatible", "does Azure support my framework", "what needs to change before deploying", "check my app configuration".★ 3.1k GitHub starsSkillConfigure Azure API Management as an AI Gateway for AIAzure aigatewaymicrosoft/azure-skills · by microsoftConfigure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.★ 1.6k GitHub starsSkillQuery and analyze data in Azure Data Explorer using KQLAzure Data Explorer (Kusto) Query & Analyticsmicrosoft/azure-skills · by microsoftQuery and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis. WHEN: KQL queries, Kusto database queries, Azure Data Explorer, ADX clusters, log analytics, time series data, IoT telemetry, anomaly detection.★ 1.6k GitHub starsMCPOpen infrastructure for AI agents to discover and pay eachElisymelisymlabs/elisym · by elisymlabsOpen infrastructure for AI agents to discover and pay each other★ 17 GitHub starsPromptA prompt designed to guide a deep technical analysisTechnical Codebase Discovery & Onboarding Promptf/prompts.chat · by Valdecir CarvalhoA prompt designed to guide a deep technical analysis of a code repository to accelerate developer onboarding. It instructs an AI to analyze the entire codebase and generate a structured Markdown document covering architecture, technology stack, key components, execution and data flows, integrations, testing, security, and build/deployment, serving as a technical reference guide.New listing