prayog-repo-fleet
Provides access to up-to-date code graphs across multiple GitHub repositories, enabling agents to query and analyze codebases from a fleet of programs.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@prayog-repo-fleetshow me the code graph for drivestream__order-service"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 |
| Declare programs and repos (add/remove here) |
Python syncer | Clone/pull |
codebase-memory-mcp (CBM) | Persistent code graph + MCP tools + graph UI |
HTTP MCP gateway | Streamable HTTP at |
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.
Related MCP server: code-intel
Quick start
Prefer git-backed sync (clone/pull develop on SHA change):
cp config/fleet.example.yaml config/fleet.yaml # edit urls / YOUR_ORG
cp .env.example .env # set GITHUB_TOKEN for private repos
make up # build + start
make ps # status
make projects # list indexed graphs
make logs # follow logs
make ui # http://localhost:9749
make down # stopClones land under ./data/repos/<program>/<repo>/. Do not bind-mount host
checkouts over those paths if you want the syncer to fetch remote develop.
Bind-mount / skip_git pilot (no remote fetch): see docs/LOCAL.md.
Or raw Compose:
docker compose -f docker-compose.yml -f docker-compose.local.yml up --build -dEnv var | Default (relative to this repo) | |
Graph |
|
|
Private clones |
| (empty — required for private GitHub HTTPS) |
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-serviceDocs
License
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted code graph over MCP: exact callers, dependencies, and cross-repo blast radius for AI agents.
Repository knowledge graph MCP server for codebase understanding and debugging.
Ask a codebase what calls what: search, blast radius, paths between symbols, and diffs.
Guarded MCP server for agent-readable business truth, provenance, readiness, and discovery.
Related MCP Servers
- AlicenseBqualityDmaintenanceExposes CodeGraph capabilities for multiple local repositories to MCP-compatible AI coding assistants, enabling multi-repo code exploration and cross-repo symbol tracing.5MIT
- AlicenseNot gradedqualityAmaintenanceMCP server for persistent code exploration and diff-aware review, exposing explore and review tools to map call paths, blast radius, and generate explainable risk-scored reports.22 npm2MIT
- AlicenseNot gradedqualityBmaintenanceProvides a code graph querying and visualization MCP server, enabling users to search, trace, and describe code components, overlay diffs, and explore architecture through natural language.MIT
- FlicenseNot gradedqualityCmaintenanceEnables coding agents to query a local-first code intelligence graph of Python repositories—covering functions, classes, modules, and their relationships—via MCP, supporting subgraph retrieval, caller lookup, and impact analysis without re-reading the codebase.-