BDT Ops Desk MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
BDT Ops Desk
Founder ops assistant for BDT Talent Group — Amazon Developer Hackathon 2026 (Alexa+ track + AWS Builder mini-challenge).
Self-hosted MCP server over Streamable HTTP (protocol 2025-11-25 via @modelcontextprotocol/sdk) plus a simulated Alexa+ web chat for demos without Preview access.
Tools
Tool | Purpose |
| Fixture LinkedIn-style digest ( |
| Open PRs, stale issues, failing checks (live GitHub API or fixture) |
| Combined brief via Amazon Bedrock |
Related MCP server: SecondBrain MCP Server
Quick start
cd bdt-ops-desk
cp .env.example .env
npm install
npm test
npm run build
npm startDev (hot reload):
npm run devOpen the simulated Alexa+ UI: http://127.0.0.1:3000/
MCP endpoint: POST http://127.0.0.1:3000/mcp
Optional env
See .env.example:
MCP_AUTH_TOKEN— when set, requireAuthorization: Bearer …(401 withoutWWW-Authenticate)GITHUB_TOKEN+GITHUB_REPOS— live hygiene; otherwise fixturesAWS default credential chain +
AWS_REGION/BEDROCK_MODEL_ID— live Bedrock; otherwise mock brief
Do not commit secrets. Prefer IAM roles in deployed environments.
Demo: curl initialize + tools/list
# Initialize (stateless JSON response)
curl -sS http://127.0.0.1:3000/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-H 'MCP-Protocol-Version: 2025-11-25' \
-d '{
"jsonrpc":"2.0",
"id":1,
"method":"initialize",
"params":{
"protocolVersion":"2025-11-25",
"capabilities":{},
"clientInfo":{"name":"curl","version":"0.0.1"}
}
}'
# tools/list
curl -sS http://127.0.0.1:3000/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-H 'MCP-Protocol-Version: 2025-11-25' \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'If MCP_AUTH_TOKEN is set, add -H "Authorization: Bearer $MCP_AUTH_TOKEN" to both calls.
Alexa+ track notes
This repo imports and runs
@modelcontextprotocol/sdkat runtime (StreamableHTTPServerTransport).Transport is Streamable HTTP on
POST /mcp(not legacy standalone HTTP+SSE).Simulated UI proves the agent loop without Alexa+ Preview.
Later registration (when you have Preview): use the Alexa+ MCP Toolkit /
alexa-aiCLI to add an Add-on Agent Skill pointed at your public HTTPS MCP URL, with Bearer token matchingMCP_AUTH_TOKEN.Phase 2: OAuth 2.1 / PRM for production account linking (out of scope for v1).
AWS Builder mini-challenge
Bedrock Runtime
InvokeModelwith Nova Pro inus-east-1forget_daily_ops_briefDockerfile included for ECS / Fargate / AgentCore-ready container packaging
Document IAM:
bedrock:InvokeModelon the chosen model ID; no long-lived keys in the repo
Scripts
Script | Action |
| Compile TypeScript + copy static assets |
| Run compiled server |
|
|
| Minimal MCP initialize + tools/list smoke tests |
Contest links
Draft write-up:
DEVPOST.mdFriction log:
FRICTION-LOG.mdBrief:
PROJECT-BRIEF.md
License
MIT — see LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Summarize URLs, repurpose content, daily news digests, find competitors. Cost telemetry built in.
- mcpOAuthcom.vibgrate
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
- KumbukaOAuthai.kumbuka
Governed, auditable knowledge your team curates for its AI assistants, self-hostable
A personal RAG database you build from chat, so AI creates work that sounds like you.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceExposes search over internal documents and company lookup via authenticated API, enabling LLMs to access firm files and data.-
- AlicenseNot gradedqualityBmaintenanceEnables external AI clients to query and interact with a personal knowledge assistant using retrieval-augmented generation and long-term memory.MIT
- AlicenseNot gradedqualityAmaintenanceEnables semantic and keyword search across locally indexed PDF shelves—device manuals, meeting minutes, and scientific papers—with date, device, and author filters, returning structured citations and neighbouring passage context for a speech assistant. It also exposes shelf and document metadata, plus a reindex signal, over streamable HTTP backed by Postgres with pgvector.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables LLM clients to search a firm's precedent vault and draft grounded contract clauses, legal memos, and document summaries.1Apache 2.0