这是 Brev 的 MCP 服务器实现。
MCP 服务器使用 Brev CLI 的 API 访问令牌和当前设置的 org。
如果尚未下载 CLI 并登录，请按照Brev 文档进行操作。
如果你想切换你的 Brev 组织，请运行brev set <org-name>
CLI 访问令牌每小时过期一次。如果遇到任何 403 错误，只需运行brev ls即可刷新访问令牌。
Related MCP server: GCP Infrastructure MCP Server
git clone git@github.com:brevdev/brev-mcp.git
遵循uv 安装指南
在 MacOS 上： ~/Library/Application\ Support/Claude/claude_desktop_config.json在 Windows 上： %APPDATA%/Claude/claude_desktop_config.json
将以下内容添加到您的claude_desktop_config.json中：
"mcpServers": {
"brev_mcp": {
"command": "uv",
"args": [
"--directory",
"<path-to-repo>",
"run",
"brev-mcp"
]
}
}准备分发包：
同步依赖项并更新锁文件：
uv sync构建软件包分发版：
uv build这将在dist/目录中创建源和轮子分布。
发布到 PyPI：
uv publish注意：您需要通过环境变量或命令标志设置 PyPI 凭据：
令牌： --token或UV_PUBLISH_TOKEN
或用户名/密码： --username / UV_PUBLISH_USERNAME和--password / UV_PUBLISH_PASSWORD
由于 MCP 服务器通过 stdio 运行，调试起来可能比较困难。为了获得最佳调试体验，我们强烈建议使用MCP Inspector 。
您可以使用以下命令通过npm启动 MCP Inspector：
npx @modelcontextprotocol/inspector uv --directory /Users/tmontfort/Brev/repos/brev_mcp run brev-mcp启动后，检查器将显示一个 URL，您可以在浏览器中访问该 URL 以开始调试。
Create a workspace from an instance type and cloud provider
| Name | Required | Description | Default |
|---|---|---|---|
| cloud_provider | Yes | The cloud provider for the workspace | |
| instance_type | No | The instance type of the workspace | |
| name | No | The name of the workspace |
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 this is a creation tool, implying a write/mutation operation, but doesn't mention permission requirements, whether the operation is idempotent, what happens on failure, or any rate limits. This leaves significant behavioral gaps for a tool that creates resources.
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 unnecessary words. It's appropriately sized and front-loaded with the essential information, making it easy to parse quickly.
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 resource creation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what a 'workspace' represents in this context, what happens after creation, whether there are dependencies or constraints, or what the return value might be. The combination of mutation behavior and lack of structured metadata creates significant contextual gaps.
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 schema description coverage is 100%, with all parameters well-documented in the schema itself. The description mentions 'instance type and cloud provider' as inputs, which aligns with two of the three parameters, but doesn't add meaningful semantic context beyond what the schema already provides. The baseline of 3 is appropriate given the comprehensive schema documentation.
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 ('Create') and resource ('workspace') with specific inputs ('from an instance type and cloud provider'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from the sibling tool 'get_instance_types', which appears to be a read-only counterpart rather than a direct alternative for creation.
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 or any prerequisites for its use. While it mentions 'instance type and cloud provider' as inputs, it doesn't clarify if this is the only way to create a workspace or if there are other methods available.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get available instances types for a cloud provider
| Name | Required | Description | Default |
|---|---|---|---|
| cloud_provider | Yes | The cloud provider to get instance types for |
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 mentions 'Get available instance types' but doesn't specify if this is a read-only operation, requires authentication, has rate limits, or what the output format might be. This leaves significant gaps in understanding the tool's behavior.
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, clear sentence that efficiently conveys the tool's purpose without any unnecessary words. It is front-loaded and appropriately sized, making it easy to parse quickly.
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 (one parameter with full schema coverage) and lack of output schema, the description is minimally adequate. However, it doesn't compensate for the absence of annotations or output details, leaving the agent with incomplete context about the tool's full behavior and results.
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 schema description coverage is 100%, with the parameter 'cloud_provider' well-documented in the schema, including an enum list. The description adds no additional meaning beyond what the schema provides, such as explaining the significance of the provider choice, so it meets the baseline for high schema coverage.
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 ('Get') and resource ('available instance types for a cloud provider'), making the purpose immediately understandable. However, it doesn't differentiate from the sibling tool 'create_workspace', which is unrelated, so it doesn't fully earn the highest score for sibling distinction.
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 or any prerequisites. It simply states what it does without context about timing, constraints, or comparisons to other tools, leaving the agent with minimal usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0create_workspaceget_instance_typesScored across 2 tools
The two tools have completely distinct purposes: one creates a workspace and the other retrieves instance types. There is no overlap in functionality, making it impossible for an agent to confuse them.
Both tools follow a consistent verb_noun naming pattern (create_workspace, get_instance_types). The verbs are clear and descriptive, and the style is uniform throughout.
With only two tools, the server feels thin for managing workspaces. It lacks essential operations like listing, updating, or deleting workspaces, which limits its utility for typical lifecycle management.
The toolset is severely incomplete for workspace management. It includes creation and instance type lookup but omits critical operations such as listing existing workspaces, updating configurations, or deleting workspaces, leaving significant gaps in coverage.
Run AI models, create deployments, and manage predictions via cloud API
Discover, run, inspect, build, test, and privately reuse AI workflows.
GPU cloud platform — create, manage, and monitor instances, snapshots, SSH keys, and billing.
Deploy apps on your cloud. Create environments, configure infrastructure, and monitor jobs.
