prayog-repo-fleet
Exposes code graphs across multi-program repositories via MCP, enabling humans and agents to query the fleet with evidence.
README
prayog-repo-fleet
Org: drivestream-lab (create the GitHub repo under this org when publishing)
Shared, up-to-date code graphs across multi-program repositories — exposed via MCP so humans and agents (Cursor, etc.) can ask fleet questions with evidence.
MIT licensed. Local-first; same shape for later cloud deploy.
What this is
| Piece | Role |
|---|---|
config/fleet.yaml |
Declare programs and repos (add/remove here) |
| Python syncer | Clone/pull develop only when commit SHA changes → index |
| codebase-memory-mcp (CBM) | Persistent code graph + MCP tools + graph UI :9749 |
| HTTP MCP gateway | Streamable HTTP at :9751/mcp (Cursor / remote clients) |
| Cursor MCP example | Wire IDE chat to the fleet graph via URL |
Agent skills such as query-fleet live in prayog-skills (Launchpad distributes them). This repo is the data/MCP plane, not the skill pack.
Quick start
cp config/fleet.local.example.yaml config/fleet.yaml # if needed
cp .env.example .env
make up # build + start
make ps # status
make projects # list indexed graphs
make logs # follow logs
make ui # http://localhost:9749
make down # stop
Or raw Compose:
docker compose -f docker-compose.yml -f docker-compose.local.yml up --build -d
Host paths come from .env (copy .env.example). Defaults assume sibling checkouts:
| Env var | Default (relative to this repo) | |
|---|---|---|
| Graph | CBM_HOST_DIR |
../central-graphs |
| Drivestream sources | DRIVESTREAM_ROOT |
../../drivestream |
| Prayog sources | PRAYOG_LAB_ROOT |
.. |
Full steps and Cursor IDE verification (without skills): docs/LOCAL.md.
Cursor MCP (verify now)
- Keep
prayog-repo-fleet-cbmrunning (make up). - Put this in
~/.cursor/mcp.json(or project.cursor/mcp.json):
{
"mcpServers": {
"prayog-fleet-cbm": {
"url": "http://localhost:9751/mcp"
}
}
}
- Restart Cursor / reload MCP; confirm
prayog-fleet-cbmconnects. - In chat: “Using MCP prayog-fleet-cbm, call list_projects and list every project.”
Remote (same stack on another host — private network; add auth later):
{
"mcpServers": {
"prayog-fleet-cbm": {
"url": "http://<fleet-host>:9751/mcp"
}
}
}
Layout
/data/repos/<program>/<repo>/ # on-disk clones or bind-mounts
CBM project id: <program>__<repo> # e.g. drivestream__order-service
Docs
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。