No install? Use cloud.anythingmcp.com directly.
Sign in, install the Statsig in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Drive Statsig (feature flags + experiments + analytics) from any AI agent: evaluate gates/dynamic configs/experiments, log events, manage console-side gates and experiments. 10 tools, server-secret-key auth.
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Statsig、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Statsig + Gemini
Drive Statsig (feature flags + experiments + analytics) from any AI agent: evaluate gates/dynamic configs/experiments, log events, manage console-side gates and experiments. 10 tools, server-secret-key auth.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
STATSIG_SERVER_SECRET_KEY
步骤 1 — 获取凭证
statsig.com).
Two distinct APIs:
- Server SDK API (
api.statsig.com/v1/...) — runtime evaluation + event logging. RequiresSTATSIG_SERVER_SECRET_KEY(starts withsecret-). - Console API (
statsigapi.net/console/v1/...) — admin operations like creating gates. RequiresSTATSIG_CONSOLE_API_KEY(starts withconsole-). The adapter uses the Server SDK base by default; tools that hit the Console API set explicit absolute URLs in their endpointMapping.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Statsig应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
statsig_check_gate | Evaluate a feature gate (boolean flag) for a user |
statsig_get_config | Evaluate a Dynamic Config for a user |
statsig_get_experiment | Evaluate an experiment for a user |
statsig_initialize | Bulk evaluate ALL gates/configs/experiments for a user in one call |
statsig_log_event | Log a custom event for analytics + experiment exposure tracking |
statsig_list_gates | Console: list feature gates defined in the project |
statsig_get_gate_config | Console: fetch a gate's definition (rules, targeting) |
statsig_create_gate | Console: create a new feature gate |
statsig_list_experiments | Console: list experiments |
statsig_get_experiment_results | Console: fetch experiment metric results (pulse readout) |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对您有帮助吗?