alignmink-context-mcp
MCP server that stores and queries shared company context, strategic spines, documents, and decision traces with citations and versioning.
README
alignmink-context-cursor
Shared company context for a small team — the git-repo equivalent of organizational intent.
OSS utility that stores Spine (strategic + domain OKR-style intent), Documents (SOPs, AOPs, playbooks, brand guidelines), and Decision traces (alignmink-dtp / DTP v0.1) in a local SQLite or Supabase Postgres store. Agents and humans query it through MCP with citable records.
No hard deletes. Records are versioned, superseded, or deprecated.
Status
Chunks 0–11 complete on this branch — shared context store, compile engine, CLI, MCP (stdio + HTTP/OAuth), web review UI, DTP import, Hermes docs, Slack slash connector, Google Drive ingest, Docker deploy. See docs/chunks.
| Chunk | Status | Outcome |
|---|---|---|
| 0 | done | Repo, CI, schema package smoke tests |
| 1 | done | DB + immutable lifecycle |
| 2 | done | Compile engine (evidence-bound) |
| 3 | done | CLI + local MCP serve + tokens |
| 4 | done | MCP core + Claude connectors |
| 5 | done | Remote HTTP MCP + OAuth PKCE (ChatGPT/Claude connectors) |
| 6 | done | Non-technical web UI |
| 7 | done | DTP import |
| 8 | done | Hermes connector |
| 9 | done | Slack /context connector |
| 10 | done | Google Workspace ingest |
| 11 | done | Docker + Compose HTTP MCP on :8787 |
Quickstart
# Node 20+; enable pnpm once
corepack enable
pnpm install
pnpm --filter @alignmink/context-schema build
pnpm --filter @alignmink/context-db build
pnpm --filter @alignmink/context-compile build
pnpm --filter @alignmink/context-auth build
pnpm --filter @alignmink/context-mcp-server build
pnpm --filter @alignmink/context-cli build
CLI (Chunk 3)
# Initialize a local SQLite workspace (~/.alignmink-context)
pnpm --filter @alignmink/context-cli exec alignmink-context init --name "Acme" --slug acme
# Compile + commit an evidenced spine proposal, mint an MCP token, query with citations
pnpm --filter @alignmink/context-cli exec alignmink-context --help
# Stdio MCP server (bin: alignmink-context-mcp)
pnpm --filter @alignmink/context-mcp-server exec alignmink-context-mcp
Knowledge model
- Strategic Spine / Domain Spines — mission, stage, bets, ranked priorities, explicit not-doing, metrics
- Documents — versioned markdown (SOPs, plans, playbooks, research)
- Decision traces — DTP v0.1 JSON (what/why/alternatives/revisit triggers)
Connectors (planned)
Claude (all apps), ChatGPT (Chat + Codex), Hermes, Slack, Google Workspace.
License
Apache-2.0 — see LICENSE.
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
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.
E2B
Using MCP to run code via e2b.