Gemini Faf MCP
未认领Persistent Project Context for Google Gemini — IANA-registered .faf format · MCP server + Cloud Run REST API
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'gemini-faf-mcp' -- 'uvx' 'gemini-faf-mcp'04 / 在客户端中确认
打开客户端的 MCP 设置,确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描,显示代码能触及的范围(外部服务、环境变量、shell 命令、代理配置目录)以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
13 个工具中显示 13 个
文档中列出的工具 (13)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
faf_about
FAF format info — IANA registration, version, ecosystem
faf_agents
Export a BETTER-shaped AGENTS.md for OpenAI Codex, Cursor, and other AI tools (non-destructive)
faf_auto
Auto-detect stack from manifest files and author/update .faf
faf_context
Get Gemini-optimized context (project + stack + score)
faf_discover
Find .faf files in the project tree
faf_gemini
Export GEMINI.md in Gemini CLI's hierarchical convention (non-destructive)
faf_init
Create a starter .faf file with project name, goal, and language
faf_migrate
Bring a .faf up to the current format version (3.0); dryrun to preview
faf_model
Get a 100% Trophy-scored example .faf for any of 15 project types
faf_read
Parse a .faf file into structured data
faf_score
Quick Mk4 score — score, tier, populated/active/total slot counts
faf_stringify
Convert parsed FAF data back to clean YAML
faf_validate
Full Mk4 validation — score, tier, slot counts, errors, warnings