widescreen-research
Orchestrates distributed research drones on Google Cloud Run, enabling scalable and bidirectional research task management.
README
widescreen-research
Bidirectional MCP server orchestrating an army of research drones on Cloud Run in GCP.
Repo status
- Primary implementation: Go (coordinator and drone)
- Examples: Node (under examples/node)
Clone
git clone https://github.com/glassBead-tc/widescreen-research.git
cd widescreen-research
Quickstart (Go)
go 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/drone
Open http://localhost:8080 and GET /health.
Docker (Go)
docker build -t widescreen/coordinator:dev .
docker run --rm -p 8080:8080 widescreen/coordinator:dev
Deploy to Cloud Run (Go)
Preferred: 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:latest
Node examples (optional)
The Node projects live under ./examples/node/ and are provided as examples only.
- Requires Node 18+ LTS
- See each example's README for usage
Architecture and design
See project_spec.md for the canonical architecture, roles, and protocols.
Directory layout
cmd/coordinator: Go coordinator service (binary)cmd/drone: Go drone worker (binary)pkg/...: Reusable Go packagesexamples/node/...: Node example MCP servers and templates
Operations
- Endpoints: GET / (info), GET /health (readiness)
- Logging: structured logs; control via LOG_LEVEL
- Recommended: enable OpenTelemetry to Cloud Monitoring (future work)
Contributing
See CONTRIBUTING.md (coming soon). Please run go fmt/go vet and tests locally before submitting PRs.
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.
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.
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.
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.