Docker's MCP CLI plugin and gateway for running catalog, OCI, registry, or local-file MCP servers in containers and exposing them to Claude, Cursor, VS Code, and other MCP clients through a shared gateway profile.
Docker MCP Gateway can start and route multiple MCP servers, so each connected client inherits the permissions of every enabled server and tool., Container isolation reduces host exposure, but Docker Engine or Docker socket access is still highly privileged and should be limited to trusted users., The gateway supports tool allowlists, CPU limits, memory limits, network blocking, secret blocking, image signature verification, and interceptors; review defaults before production use., Catalog, profile, local-file, and registry references can change which servers run behind the gateway, especially when watch mode or shared profiles are enabled., Tool-call logging is enabled by default in the documented flags, so avoid routing secrets or sensitive payloads unless logging and retention are controlled.
Privacy notes
Docker MCP Gateway may process MCP server definitions, catalog entries, profile exports, local server files, secrets, OAuth tokens, tool names, tool arguments, tool outputs, logs, container metadata, and Docker Engine metadata., Secrets may come from Docker Desktop secrets or `.env` fallback files; keep those stores out of version control and restrict filesystem permissions., Tool outputs can include local files, API responses, credentials, account data, or infrastructure details depending on the enabled downstream MCP servers., Exported profiles and catalogs can reveal internal server names, image references, allowed tools, configuration values, and service endpoints.
Author
docker
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
5 safety and 4 privacy notes across 5 risk areas. Review closely: credentials & tokens, permissions & scopes, network access.
5 areas
SafetyPermissions & scopesDocker MCP Gateway can start and route multiple MCP servers, so each connected client inherits the permissions of every enabled server and tool.
SafetyGeneralContainer isolation reduces host exposure, but Docker Engine or Docker socket access is still highly privileged and should be limited to trusted users.
SafetyCredentials & tokensThe gateway supports tool allowlists, CPU limits, memory limits, network blocking, secret blocking, image signature verification, and interceptors; review defaults before production use.
SafetyLocal filesCatalog, profile, local-file, and registry references can change which servers run behind the gateway, especially when watch mode or shared profiles are enabled.
SafetyCredentials & tokensTool-call logging is enabled by default in the documented flags, so avoid routing secrets or sensitive payloads unless logging and retention are controlled.
PrivacyCredentials & tokensDocker MCP Gateway may process MCP server definitions, catalog entries, profile exports, local server files, secrets, OAuth tokens, tool names, tool arguments, tool outputs, logs, container metadata, and Docker Engine metadata.
PrivacyCredentials & tokensSecrets may come from Docker Desktop secrets or `.env` fallback files; keep those stores out of version control and restrict filesystem permissions.
PrivacyCredentials & tokensTool outputs can include local files, API responses, credentials, account data, or infrastructure details depending on the enabled downstream MCP servers.
PrivacyNetwork accessExported profiles and catalogs can reveal internal server names, image references, allowed tools, configuration values, and service endpoints.
Safety notes
Docker MCP Gateway can start and route multiple MCP servers, so each connected client inherits the permissions of every enabled server and tool.
Container isolation reduces host exposure, but Docker Engine or Docker socket access is still highly privileged and should be limited to trusted users.
The gateway supports tool allowlists, CPU limits, memory limits, network blocking, secret blocking, image signature verification, and interceptors; review defaults before production use.
Catalog, profile, local-file, and registry references can change which servers run behind the gateway, especially when watch mode or shared profiles are enabled.
Tool-call logging is enabled by default in the documented flags, so avoid routing secrets or sensitive payloads unless logging and retention are controlled.
Privacy notes
Docker MCP Gateway may process MCP server definitions, catalog entries, profile exports, local server files, secrets, OAuth tokens, tool names, tool arguments, tool outputs, logs, container metadata, and Docker Engine metadata.
Secrets may come from Docker Desktop secrets or `.env` fallback files; keep those stores out of version control and restrict filesystem permissions.
Tool outputs can include local files, API responses, credentials, account data, or infrastructure details depending on the enabled downstream MCP servers.
Exported profiles and catalogs can reveal internal server names, image references, allowed tools, configuration values, and service endpoints.
Prerequisites
Docker Desktop `4.59+` with the MCP Toolkit feature enabled, or the Docker MCP CLI plugin built and installed independently.
Docker Engine access for running containerized MCP servers and the gateway.
MCP server sources prepared from Docker MCP Catalog entries, OCI images, MCP Registry entries, or local YAML/JSON server files.
Profiles feature enabled when using `docker mcp profile` and profile-based gateway runs outside Docker Desktop.
Secrets, OAuth flows, allowed tools, network policy, filesystem mounts, CPU, memory, and image signature policy reviewed before sharing a gateway.
Schema details
Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
20 minutes
Difficulty
advanced
Full copyable content
docker mcp gateway run --profile dev-tools
About this resource
Content
Docker MCP Gateway is the open-source Docker CLI plugin and gateway behind
Docker Desktop's MCP Toolkit. It runs selected MCP servers in containers,
groups them through profiles, and exposes them to MCP clients through one
gateway command or network transport.
The repository documents gateway runs over stdio by default, plus SSE or
streaming transports when serving one or more clients over a TCP port. Servers
can come from Docker MCP Catalog references, OCI images, MCP Registry entries,
or local server definition files.
These sources were reviewed on 2026-06-06. Prefer the live repository,
README, gateway guide, security guide, profiles guide, generated command
reference, Docker image page, and license file for current gateway behavior,
feature flags, deployment options, and security controls.
Features
Run MCP servers inside Docker containers with CPU and memory limits.
Expose a unified MCP gateway over stdio, SSE, or streaming transports.
Organize MCP servers into reusable profiles for client-specific tool sets.
Pull servers from Docker MCP Catalog, OCI images, MCP Registry entries, or local server files.
Connect clients such as Claude Desktop, Cursor, and VS Code to the selected profile.
Enable or disable selected tools per gateway run or profile.
Manage catalogs, server definitions, profile import/export, and OCI-backed profile sharing.
Handle secrets through Docker Desktop secrets or explicit fallback secret files.
Support OAuth flows for MCP servers that require service authentication.
Use logging, call tracing, network blocking, secret blocking, image signature verification, and interceptors.
Installation
Recent Docker Desktop versions include the Docker MCP CLI plugin when the MCP
Toolkit feature is enabled. The repository also documents building and
installing the plugin manually:
git clone https://github.com/docker/mcp-gateway.git
cd mcp-gateway
mkdir -p "$HOME/.docker/cli-plugins/"
make docker-mcp
Run the default stdio gateway with:
docker mcp gateway run
Connect Claude Desktop or another stdio MCP client with:
For shared client access, run the gateway with a port and streaming transport,
or pass a profile, selected servers, selected tools, secret sources, and other
gateway flags from the documented command reference.
Use Cases
Give Claude a single managed entrypoint to a curated Docker MCP Toolkit profile.
Run MCP servers from Docker MCP Catalog in isolated containers instead of directly on the host.
Share a team profile through exported profile files or OCI references.
Test one server image with docker mcp gateway run --server before adding it to a catalog.
Restrict risky tools with explicit tool allowlists before connecting a client.
Use the gateway's SSE or streaming transport for multi-client access.
Keep API keys in Docker Desktop secrets or a controlled secret file instead of ad hoc environment variables.
Review tool-call logs and container limits when evaluating an MCP server for production.
Safety and Privacy
Docker MCP Gateway is a control point for other MCP servers. It can reduce risk
by running servers in containers, limiting CPU and memory, blocking secrets,
blocking network access, enforcing selected tools, and checking image
signatures. Those controls still depend on the chosen catalog entries, profiles,
server files, gateway flags, Docker permissions, and client approval settings.
Treat Docker Engine access as privileged. A user or service that can run
containers, mount host paths, access the Docker socket, or load arbitrary server
definitions can affect the host. Review every server's volume mounts, allowed
hosts, secrets, OAuth scopes, and enabled tools before connecting Claude or
another agent client.
The gateway and its downstream servers can see tool arguments, tool outputs,
logs, traces, catalog metadata, profile exports, container image names, Docker
metadata, secrets, OAuth tokens, and local file paths. Keep exported profiles,
catalogs, .env files, and logs out of public repositories.
Duplicate Check
No docker/mcp-gateway source entry or Docker MCP Gateway entry was found in
content/mcp. The existing Docker MCP Server for Claude entry is distinct
content about Docker API management from Claude rather than Docker's MCP
Toolkit gateway and catalog runner.
Show that Docker MCP Gateway is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/docker-mcp-gateway)
How it compares
Docker MCP Gateway side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
Docker's MCP CLI plugin and gateway for running catalog, OCI, registry, or local-file MCP servers in containers and exposing them to Claude, Cursor, VS Code, and other MCP clients through a shared gateway profile.
Open-source AI gateway that can connect to downstream MCP servers and expose their aggregated tools through a single HTTP or SSE MCP endpoint for Claude Desktop, Cursor, and other MCP clients.
Dashboard, CLI, and gateway for centrally managing many MCP servers and exposing them as authenticated all-server, group, single-server, or smart routing endpoints.
✓Docker MCP Gateway can start and route multiple MCP servers, so each connected client inherits the permissions of every enabled server and tool.
Container isolation reduces host exposure, but Docker Engine or Docker socket access is still highly privileged and should be limited to trusted users.
The gateway supports tool allowlists, CPU limits, memory limits, network blocking, secret blocking, image signature verification, and interceptors; review defaults before production use.
Catalog, profile, local-file, and registry references can change which servers run behind the gateway, especially when watch mode or shared profiles are enabled.
Tool-call logging is enabled by default in the documented flags, so avoid routing secrets or sensitive payloads unless logging and retention are controlled.
✓Bifrost can expose all selected downstream MCP tools through one `/mcp` gateway endpoint, so treat the endpoint like an access layer for every connected tool.
The docs state that default LLM tool calls are suggestions until an explicit tool execution API call is made, but agent mode can enable configured automatic execution.
Gateway-mode auto-approval is controlled by the external MCP host, such as Claude Desktop, Cursor, Cline, or a custom client, not by Bifrost's `tools_to_auto_execute` setting.
Stdio connections spawn local commands inside the Bifrost runtime; Docker deployments need images that include the requested executables.
Use virtual keys, per-tool allowlists, auth headers, OAuth, per-user credentials, and network controls to limit which clients can reach high-impact tools.
✓MCPHub centralizes many downstream MCP servers, so one hub endpoint can expose broad read, write, file, shell, browser, database, or account capabilities depending on the registered servers.
The Docker command binds the dashboard and gateway to 127.0.0.1 by default; use a reverse proxy with TLS and explicit access controls before exposing MCPHub on a network interface.
MCP endpoints require authentication by default; do not disable bearer authentication outside trusted local testing.
Smart routing can discover and invoke tools by semantic similarity, so keep group visibility and bearer-key scopes narrow.
Hot-swappable configuration can add, remove, or change downstream MCP server access while the hub is running.
OAuth server mode, OAuth client mode, social login, and database mode introduce additional credential and session management responsibilities.
✓Archestra is a platform/control-plane entry, not a single-purpose local MCP helper; admins can expose many MCP servers, agents, tools, and credentials through one gateway.
The upstream quickstart mounts the host Docker socket so the platform can run MCP servers; treat that as highly privileged host access and avoid using it on sensitive machines without isolation.
Self-hosted MCP servers may run as Kubernetes workloads with injected environment variables, secrets, images, network policies, and restart controls.
Tool assignments, gateway visibility, credential resolution, custom headers, and load-tools-on-demand settings should be reviewed per team and environment.
Deterministic tool guardrails can reduce some unsafe tool chains, but they depend on correct policies and do not make untrusted MCP servers safe by default.
Privacy notes
✓Docker MCP Gateway may process MCP server definitions, catalog entries, profile exports, local server files, secrets, OAuth tokens, tool names, tool arguments, tool outputs, logs, container metadata, and Docker Engine metadata.
Secrets may come from Docker Desktop secrets or `.env` fallback files; keep those stores out of version control and restrict filesystem permissions.
Tool outputs can include local files, API responses, credentials, account data, or infrastructure details depending on the enabled downstream MCP servers.
Exported profiles and catalogs can reveal internal server names, image references, allowed tools, configuration values, and service endpoints.
✓Bifrost may process provider prompts, model responses, MCP tool names, tool arguments, tool results, headers, virtual keys, OAuth tokens, per-user credentials, logs, traces, metrics, and downstream server metadata.
Per-user auth stores credentials against a signed-in user, virtual key, or session identity; review credential lifecycle, revocation, and orphaned-session behavior.
Logs, config stores, provider settings, MCP sessions, and gateway analytics can contain sensitive operational or user data.
Keep real provider keys, virtual keys, OAuth secrets, MCP endpoint URLs, and upstream service credentials in environment variables or secret stores, not committed config.
✓MCPHub may handle prompts, tool names, tool arguments, tool results, server configs, resource data, bearer keys, OAuth tokens, login sessions, user identities, logs, and CLI command history.
Mounted config files, data directories, database rows, vector indexes, generated passwords, and dashboard screenshots can reveal sensitive server names, environment variables, credentials, and tool schemas.
Downstream MCP servers may forward private workspace, browser, database, cloud, ticketing, or account data through MCPHub to connected clients and model providers.
Do not commit real `mcp_settings.json` files, bearer keys, OAuth secrets, social-login credentials, database URLs, generated admin passwords, or exported hub data.
✓MCP server definitions, tool schemas, gateway tokens, upstream credentials, OAuth tokens, API keys, custom headers, logs, traces, and tool results may be stored or processed by the platform.
Built-in observability, LLM proxy, chat, agents, and policy features can reveal prompts, tool arguments, tool outputs, token usage, user identities, team membership, and trace metadata.
Registry entries and installations can use personal, team-scoped, or shared credentials; choose the narrowest scope that matches the use case.
When external MCP clients call an Archestra gateway, downstream tool results can still be sent by the MCP client to the configured model provider.
Prerequisites
Docker Desktop `4.59+` with the MCP Toolkit feature enabled, or the Docker MCP CLI plugin built and installed independently.
Docker Engine access for running containerized MCP servers and the gateway.
MCP server sources prepared from Docker MCP Catalog entries, OCI images, MCP Registry entries, or local YAML/JSON server files.
Profiles feature enabled when using `docker mcp profile` and profile-based gateway runs outside Docker Desktop.
Node.js with `npx`, Docker, or another supported Bifrost Gateway deployment path.
Bifrost Gateway version `v1.4.0-prerelease1` or newer for MCP gateway mode.
Downstream MCP server commands or HTTP/SSE endpoint URLs prepared before registering clients.
Provider API keys, virtual keys, gateway auth settings, and governance policies reviewed before sharing the endpoint.
Docker available for the documented container deployment.
A reviewed `mcp_settings.json` file for the MCP servers the hub should launch or proxy.
A durable mounted data directory so credentials, generated passwords, sessions, and state survive restarts.
OpenSSL or another secure random generator available to create a unique administrator password.
Docker for local evaluation, or Kubernetes and Helm/Terraform-style deployment planning for production use.
Organization policy for which MCP servers, credentials, teams, environments, and external network destinations may be exposed.
LLM provider keys or local model configuration if using Archestra's built-in chat, agents, or LLM proxy features.
Admin review of the quickstart container command before mounting the Docker socket.