这是一个用于从Sentry.io检索和分析问题的Model Context Protocol服务器。该服务器提供了工具来检查来自您的Sentry账户的错误报告、堆栈跟踪和其他调试信息。
get_sentry_issue
issue_id_or_url (字符串):要分析的Sentry问题ID或URLget_list_issues
project_slug (字符串):要分析的Sentry项目slugorganization_slug (字符串):要分析的Sentry组织slugsentry-issue
issue_id_or_url (字符串):Sentry问题ID或URL要通过Smithery自动安装mcp-sentry到Claude Desktop:
npx -y @smithery/cli install @qianniuspace/mcp-sentry --client claude
当使用uv时不需要特定的安装步骤。我们将使用uvx直接运行mcp-sentry。
或者你可以通过pip安装mcp-sentry:
pip install mcp-sentry
或者使用uv
uv pip install -e .
安装后,可以使用以下命令作为脚本运行它:
python -m mcp_sentry
在你的claude_desktop_config.json中添加以下内容:
"mcpServers": {
"sentry": {
"command": "uvx",
"args": ["mcp-sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
}
</details>
<details>
<summary>使用docker</summary>
"m_服务器": {
"sentry": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
}
</details>
<details>
<summary>使用pip安装</summary>
"mcpServers": {
"sentry": {
"command": "python",
"args": ["-m", "mcp_sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
}
</details>
在你的Zed设置.json中添加以下内容:
<details> <summary>使用uvx</summary>例如Curson
"context_servers": [
"mcp-sentry": {
"command": {
"path": "uvx",
"args": ["mcp-sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
}
],
</details>
<details>
<summary>使用pip安装</summary>
"context_servers": {
"mcp-sentry": {
"command": "python",
"args": ["-m", "mcp_sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
},
</details>
<details>
<summary>使用具有自定义路径的pip安装</summary>
"context_servers": {
"sentry": {
"command": "python",
"args": [
"-m",
"mcp_sentry",
"--auth-token",
"YOUR_SENTRY_TOKEN",
"--project-slug",
"YOUR_PROJECT_SLUG",
"--organization-slug",
"YOUR_ORGANIZATION_SLUG"
],
"env": {
"PYTHONPATH": "path/to/mcp-sentry/src"
}
}
},
</details>
你可以使用MCP检查器来调试服务器。对于uvx安装:
npx @modelcontextprotocol/inspector uvx mcp-sentry --auth-token YOUR_SENTRY_TOKEN --project-slug YOUR_PROJECT_SLUG --organization-slug YOUR_ORGANIZATION_SLUG
或者如果你已经在一个特定目录中安装了包或正在开发它:
cd path/to/servers/src/sentry
npx @modelcontextprotocol/inspector uv run mcp-sentry --auth-token YOUR_SENTRY_TOKEN --project-slug YOUR_PROJECT_SLUG --organization-slug YOUR_ORGANIZATION_SLUG
或者在终端中
npx @modelcontextprotocol/inspector uv --directory /Volumes/ExtremeSSD/MCP/mcp-sentry/src run mcp_sentry --auth-token YOUR_SENTRY_TOKEN
--project-slug YOUR_PROJECT_SLUG --organization-s_服务器-slug YOUR_ORGANIZATION_SLUG

此MCP服务器根据MIT许可证发布。这意味着您可以自由地使用、修改和分发软件,但需遵守MIT许可证中的条款和条件。更多详情,请参见项目存储库中的LICENSE文件。