ContextPilot
Provides MCP tools for Alexa+ to run multi-step personal productivity workflows with durable session context, including capturing, triaging, planning the day, drafting follow-ups, and committing plans.
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., "@ContextPilotCapture my meeting notes, triage my tasks, and plan tomorrow's follow-ups."
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.
ContextPilot
Self-hosted MCP server for Alexa+ that runs multi-step personal productivity workflows with durable session context — not a single-turn API wrapper.
Hackathon | Build Ship Shape ( |
Primary track | Alexa+ |
Mini-challenges | AWS Builder · Open Source |
Deadline | 23 Oct 2026, 12:00 PDT |
Devpost | |
Status | Scaffold + OpenSpec bootstrap (implementation in progress) |
License | MIT |
Why it exists
Most “Alexa + LLM” demos wrap one prompt. ContextPilot exposes small MCP tools that run a durable workflow:
capture → triage → plan day → draft follow-ups → commit plan
Alexa+ (and Cursor/Claude) act as MCP clients. A web-sim client calls the same Streamable HTTP tools so we can demo from Colombia if US Preview/device access fails.
Related MCP server: Notion Workflow MCP
Architecture (short)
Clean Architecture TypeScript monorepo:
packages/domain— entities & use cases (deterministic core)packages/mcp-server— MCP Streamable HTTP (spec 2025-11-25+)packages/auth— OAuth 2.1 + PKCE S256 + PRM (RFC 9728)packages/adapters— in-memory now; DynamoDB/Google laterpackages/web-sim— simulated Alexa+ UX for judgespackages/alexa-addon— addon package artifacts foralexa-aiCLI
Details: docs/architecture.md · Engineering: docs/engineering.md · Agent manual: AGENTS.md
OpenSpec
Source of truth for product & engineering decisions:
Requirements:
openspec/requirements/ADRs:
openspec/decisions/(includes ADR-006 engineering principles)Specs:
openspec/specs/Active change:
openspec/changes/bootstrap-contextpilot/
Development (soon)
# Node ≥ 20
npm install
npm run typecheck
npm run test
npm run dev:mcp
npm run dev:web-simSee tasks: openspec/changes/bootstrap-contextpilot/tasks.md.
Security
Fail closed without Bearer token on tool calls
Never commit secrets — copy
.env.example→.envNo invented AWS account IDs or OAuth client secrets in this repo
Sibling
Local sibling of Catalog Greenlight (same Clean Architecture / OpenSpec style).
This server cannot be deployed
Maintenance
Related MCP Connectors
Cross-tool persistent memory and context for AI assistants over MCP.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Agent-native notes, tasks, dev-docs, vaults, sync & handoffs. MCP + OpenAPI dual surface.
Work management where AI agents are first-class members: tasks, projects, memory over hosted MCP
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAI-native productivity backend that gives your AI assistant persistent memory, pattern awareness, and computed intelligence about your work. 14 MCP tools for task management, daily planning, weekly review, and personal context.MIT
- FlicenseAqualityDmaintenanceEnables personal workflow management by turning Notion into a task and knowledge system via slash commands and 19 integrated MCP tools. It supports project-based task tracking, subtask management, and automated note summarization directly through the Claude interface.192-
- AlicenseAqualityFmaintenanceProvides persistent personal context (identity, projects, decisions, knowledge) to MCP-compatible AI tools, eliminating the need to re-explain yourself across sessions.251 npm1MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that enables Alexa+ to autonomously orchestrate multi-step household tasks by decomposing goals into parallel tool calls — cross-session memory and dietary/allergy auditing, culinary planning with wine pairings, Amazon Fresh cart assembly with human-in-the-loop purchase approval, smart-home ambiance and climate control, and calendar scheduling. It pairs AWS Bedrock multi-agent reasoning with Streamable HTTP transport and interactive generative UI cards, carousels, and live IoT sliders.MIT