Skip to main content

Run MCP servers

This guide explains how to run Model Context Protocol (MCP) servers using ToolHive. It covers how to run servers from the ToolHive registry, customize server settings, and run custom servers using Docker images or protocol schemes.

Run a server from the registry​

To run an MCP server from the ToolHive registry, use the thv run command with the name of the server you want to run. The server name is the same as its name in the registry.

thv run <server-name>

For example:

thv run fetch
What's happening?

When you run an MCP server from the registry, ToolHive:

  1. Pulls the image and launches a container using the configuration from the registry.
  2. Launches an HTTP proxy on a random port to forward client requests to the container.
  3. Labels the container so it can be tracked by ToolHive: 
    toolhive: true
    toolhive-name: <server-name>

See Running custom MCP servers to run a server that is not in the registry.

Customize server settings​

You might need to customize the behavior of an MCP server, such as changing the port, mounting a local directory, or passing secrets. ToolHive provides several options to customize the server's configuration when you run it.

For a complete list of options, run thv run --help or see the thv run command reference.

Run a server with a custom name​

By default, the container name matches the MCP server's name in the registry or is automatically generated from the image name when you run a custom server. To give your server instance a custom name, use the --name option:

thv run --name my-custom-name <server-name>

For example:

thv run --name my-fetch fetch

Run a server with secrets​

Many MCP servers require secrets or other configuration variables to function correctly. ToolHive lets you pass these secrets as environment variables when starting the server.

To pass a secret to an MCP server, use the --secret option:

thv run --secret <secret-name>,target=<env-var-name> <server-name>

The target parameter specifies the name of the environment variable in the MCP server's container. This is useful for passing secrets like API tokens or other sensitive information.

For example:

thv run --secret github,target=GITHUB_PERSONAL_ACCESS_TOKEN github

See Secrets management to learn how to manage secrets in ToolHive.

Mount a local directory​

To let an MCP server access files on your host machine, you can mount a local directory into the container:

thv run --volume <host-path>:<container-path>[:ro] <server-name>

The optional :ro suffix makes the volume read-only in the container. This is useful for sharing files without letting the MCP server modify them.

ToolHive automatically adds mounted paths to the MCP server's permissions profile.

For example, to mount a local directory to the Filesystem MCP server:

thv run --volume ~/code/toolhive:/projects/toolhive filesystem

The filesystem server can now access the contents of ~/code/toolhive as /projects/toolhive in the container (the filesystem MCP server expects directories to be mounted at /projects by default).

Pass additional arguments​

Some MCP servers require additional arguments to run correctly. You can pass these arguments after the server name in the thv run command:

thv run <server-name> -- <additional-args>

For example, to run the fetch server with custom arguments:

thv run fetch -- --arg1 value1 --arg2 value2

Check the MCP server's documentation for the required arguments.

Run a server on a specific port​

ToolHive creates a reverse proxy on a random port that forwards requests to the container. To specify the port for an MCP server:

thv run --port <port-number> <server-name>

Run a custom MCP server​

To run an MCP server that isn't in the registry, you can use a Docker image or a protocol scheme to dynamically build the server.

ToolHive supports the following transport methods:

  • Standard I/O (stdio), default:
    ToolHive redirects SSE traffic from the client to the container's standard input and output. This acts as a secure proxy, ensuring that the container doesn't have direct access to the network or the host machine.

  • HTTP with SSE (server-sent events) (sse):
    ToolHive creates a reverse proxy that forwards requests to the container. This means the container itself doesn't directly expose any ports.

  • Streamable HTTP - coming soon!
    The March 2025 revision of the MCP specification replaced the HTTP+SSE transport with Streamable HTTP. Follow the GitHub issue to be notified when this feature is available in ToolHive.

Run a server from a Docker image​

To run an MCP server from a Docker image, specify the image name and tag in the thv run command. You can also specify a custom name for the server instance, the transport method, and any additional arguments required by the MCP server.

thv run [--name <friendly-name>] [--transport <stdio/sse>] <image-name:tag> -- <server-args>

For example, to run an MCP server from a Docker image named my-mcp-server-image that uses the SSE transport method and takes additional arguments:

thv run --name my-mcp-server --transport sse my-mcp-server-image:latest -- --arg1 value1 --arg2 value2

Check your MCP server's documentation for the required arguments.

What's happening?

When you run an MCP server from a Docker image, ToolHive:

  1. Pulls the image (my-mcp-server-image:latest) and launches a container with the options and arguments you specified.
  2. Launches an HTTP proxy on a random port (optionally, add --port <port-number> to specify the port).
  3. Labels the container so it can be tracked by ToolHive: 
    toolhive: true
    toolhive-name: my-mcp-server
  4. Sets up the specified transport method (--transport stdio or --transport sse).

See thv run --help for more options.

Run a server using protocol schemes​

ToolHive also supports running MCP servers directly from package managers. This means you can launch MCP servers without building or publishing a Docker image, and without installing language-specific build tools on your machine.

Currently, three protocol schemes are supported:

  • uvx://: For Python-based MCP servers using the uv package manager
  • npx://: For Node.js-based MCP servers using npm
  • go://: For Go-based MCP servers
thv run <protocol>://<package-name>@<version>

You'll likely need to specify additional arguments like the transport method, volumes, and environment variables. Check your MCP server's documentation and see thv run --help for more options.

What's happening?

When you use a protocol scheme, ToolHive:

  1. Detects the protocol scheme and extracts the package reference
  2. Generates a Dockerfile based on the appropriate template
  3. Builds a Docker image with the package installed
  4. Runs the MCP server using the new image (see Run a server from a Docker image for details)

Examples​

The uvx:// protocol is used for Python-based MCP servers. The package name must be a valid package in the PyPI registry. The @<version> suffix is optional and defaults to the latest version if omitted.

thv run --name aws-docs uvx://awslabs.aws-documentation-mcp-server@latest

Add a custom CA certificate​

In corporate environments with TLS inspection or custom certificate authorities, you may need to configure a CA certificate for ToolHive to use when building containers from protocol schemes like uvx://, npx://, and go://.

ToolHive provides both global configuration and per-command options for CA certificates.

Configure a global CA certificate​

To set a CA certificate that ToolHive will use for all container builds:

thv config set-ca-cert /path/to/corporate-ca.crt

To view the currently configured CA certificate:

thv config get-ca-cert

To remove the CA certificate configuration:

thv config unset-ca-cert

Override CA certificate per command​

You can override the global CA certificate configuration for a specific run using the --ca-cert flag:

thv run --ca-cert /path/to/other-ca.crt uvx://some-package

This is useful when you need to use different CA certificates for different servers or when testing with a specific certificate.

Priority order​

ToolHive uses the following priority order for CA certificates:

  1. Command-line flag (--ca-cert)
  2. Global configuration (thv config set-ca-cert)
  3. No custom CA certificate (default behavior)

For example:

# Set a global CA certificate
thv config set-ca-cert /path/to/corporate-ca.crt

# This uses the configured CA certificate
thv run uvx://some-package

# This overrides the configured CA certificate
thv run --ca-cert /path/to/special-ca.crt uvx://other-package

Next steps​

See Monitor and manage MCP servers to monitor and control your servers.

Troubleshooting​

Server fails to start​

If a server fails to start:

  1. Check if Docker/Podman is running
  2. Verify you have internet access to pull images
  3. Check if the port is already in use
  4. Look at the error message for specific issues

Server starts but isn't accessible​

If a server starts but isn't accessible:

  1. Check the server logs:

    thv logs <server-name>

  2. Verify the port isn't blocked by a firewall

  3. Make sure clients are properly configured (see Client configuration)

Server crashes or exits unexpectedly​

If a server crashes or exits unexpectedly:

  1. List all MCP servers including stopped ones:

    thv list --all

  2. Check the logs for error messages:

    thv logs <server-name>

  3. Try running with a different permission profile:

    thv run --permission-profile network <server-name>

  4. Check if the server requires any secrets or environment variables