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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.