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., "@widescreen-research research the latest trends in renewable energy"
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.
Bidirectional MCP server orchestrating an army of research drones on Cloud Run in GCP.
Primary implementation: Go (coordinator and drone)
Examples: Node (under examples/node)
Related MCP server: Google Maps MCP Server for Cloud Run
git clone https://github.com/glassBead-tc/widescreen-research.git
cd widescreen-researchgo version # require 1.23+
go mod download
# terminal 1
LOG_LEVEL=debug go run ./cmd/coordinator
# terminal 2
DRONE_TYPE=research EXA_API_KEY=your-local-only-key LOG_LEVEL=debug go run ./cmd/droneOpen http://localhost:8080 and GET /health.
docker build -t widescreen/coordinator:dev .
docker run --rm -p 8080:8080 widescreen/coordinator:devPreferred: inject secrets from Secret Manager. Example:
gcloud run deploy widescreen-coordinator \
--source . \
--region=us-central1 \
--allow-unauthenticated \
--set-env-vars=LOG_LEVEL=info \
--set-secrets=EXA_API_KEY=exa_api_key:latestThe Node projects live under ./examples/node/ and are provided as examples only.
Requires Node 18+ LTS
See each example's README for usage
See project_spec.md for the canonical architecture, roles, and protocols.
cmd/coordinator: Go coordinator service (binary)
cmd/drone: Go drone worker (binary)
pkg/...: Reusable Go packages
examples/node/...: Node example MCP servers and templates
Endpoints: GET / (info), GET /health (readiness)
Logging: structured logs; control via LOG_LEVEL
Recommended: enable OpenTelemetry to Cloud Monitoring (future work)
See CONTRIBUTING.md (coming soon). Please run go fmt/go vet and tests locally before submitting PRs.
This server cannot be deployed
Sandboxes, storage, secrets, queues, timers, locks, inboxes and run ledger for AI bots. One MCP.
Execution control plane for agents: capabilities, durable jobs, budgets, receipts, and BYOK.
Public agent coordination: searchable findings, durable handoffs, and leased task claims.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
