Run the Vault MCP server from source code

Beta feature

Beta functionality is stable but possibly incomplete and subject to change. We strongly discourage using beta features in production deployments of Vault.

We recommend building and running the MCP server from source code when you want access to the latest features and the ability to customize the server.

Assumptions

You have Go development environment.
You have a compatible operating system and architecture.

Step 1: Get the source code

Use go to install from Github. Use the latest tag to pull the latest stable release. To install the latest development release, use the main tag:
```
$ go install github.com/hashicorp/vault-mcp-server/cmd/vault-mcp-server@<tag>
```
Confirm the path to the downloaded vault-mcp-server binary. The binary location depends on your Go installation and GOPATH configuration.
```
$ which vault-mcp-server
```

Add the following MCP configuration to your AI client. Replace /path/to/vault-mcp-server with the actual path to the downloaded binary:

{
  "mcp": {
    "servers": {
      "vault": {
        "command": "/path/to/vault-mcp-server",
        "args": ["stdio"],
        "env": {
          "VAULT_ADDR": "<<vault_address_here>>",
          "VAULT_NAMESPACE": "<<vault_namespace_here>>",
          "VAULT_TOKEN": "<<vault_token_here>>"
        }
      }
    }
  }
}

Step 2: Start the server

You can use the vault-mcp-server CLI and specify the transport protocol you want to use to start the server.

Option 1: Start the server in `stdio` mode

Run the following command on the local instance to start the server in stdio mode:

$ vault-mcp-server stdio [--log-file /path/to/log]

Option 1: Start the server in `streamable-http` mode

Run the following command on the local instance to start the server in streamable-http mode:

$ vault-mcp-server streamable-http \
    [--transport-port 8080]        \
    [--transport-host 127.0.0.1]   \
    [--mcp-endpoint /mcp]          \
    [--log-file /path/to/log]

Use environment variables

Instead of setting values manually, consider using the supported environment variables.

Next steps

Begin prompting your AI model about Vault operations. Refer to Prompt an AI model for guidance on effective prompting techniques.
Ask for help with specific Vault operations and workflows.
Explore advanced configuration options for your specific deployment needs.