mcp-document-architect
Allows Google Workspace to serve as the document store backend, enabling agents to list, read, write, and search corporate documents through the MCP server.
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., "@mcp-document-architectTurn the Q3 revenue mission script into a report outline."
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.
@vibeleading/mcp-document-architect
The Ecosystem Connector.
An MCP server granting NPC Agents read/write access to the corporate paper trail so their reports and cross-references always align with the Pilot's Mission Script (the high-fidelity strategic intent: outcome, scope, constraints, verification).
Context
Agents acting inside the corporate ecosystem need a stable, shared document layer and a drafting discipline. This server:
exposes a document store of the corporate trail (
list/read/write/search), andturns a Mission Script into a structured report outline + section scaffolds, each annotated with the requirement it must fulfill, so drafts stay aligned to intent.
Related MCP server: OrgX MCP
Installation
npm install -g @vibeleading/mcp-document-architect
# or run directly without installing:
npx -y @vibeleading/mcp-document-architect
# or run straight from the GitHub source (builds automatically):
npx -y github:VibeLeading/mcp-document-architectRequirements
Node.js >= 22 — required. The server is ESM-only and uses modern Node built-ins. On older Node versions the process fails to start, which MCP clients report generically as "connection closed".
No other runtime dependencies — everything ships with the package.
Quick Start (Agent Setup)
Give your agent the full VibeLeading methodology in one paste:
Give me the Vibe Leading methodology: install the 5 agent skills so I can lead AI agents by intent + real-time telemetry, and add the 4 MCP servers so I get hands in the corporate engine.
SKILLS (npx skills add):
npx skills add VibeLeading/mission-script VibeLeading/ira-prompting VibeLeading/hud-setup VibeLeading/pit-stop-audit VibeLeading/org-geometryMCP SERVERS (@vibeleading scope, add to YOUR agent's MCP config):
@vibeleading/mcp-hybrid-data-engine@vibeleading/mcp-document-architect@vibeleading/mcp-real-time-scout@vibeleading/mcp-privacy-shieldENV VARS:
MCP_STONE_PATH=data/stone.dbMCP_LIGHT_PATH=data/light.jsonMCP_FLOW_PATH=data/flow.jsonMCP_DOCS_ROOT=~/.vlb-docsMCP_SHIELD_NAMES=1NOTE: MCP installation method varies by agent. Examples:
OpenCode:
opencode mcp add document-architect -- npx -y @vibeleading/mcp-document-architectClaude Code / Cursor: add to
.mcp.json/claude_desktop_config.jsonwithcommand=npx, args=[-y, @vibeleading/mcp-document-architect]Codex: configure via its MCP settings UI Use the method appropriate for your agent.
Paste the block above into your AI agent (OpenCode, Claude Code, Cursor, Codex, etc.). It will install the skills, write the MCP config, and you're ready to lead.
Client configuration
Add to your MCP client config (e.g. Claude Code .mcp.json or Cursor mcp.json):
{
"mcpServers": {
"document-architect": {
"command": "npx",
"args": ["-y", "@vibeleading/mcp-document-architect"]
}
}
}Tools
Tool | Description | Key args |
| List documents in the paper trail |
|
| Read a document by path |
|
| Create/overwrite a document (guarded, UTF-8) |
|
| Case-insensitive ranked keyword search |
|
| Mission Script → structured outline + scaffolds |
|
Environment variables
Variable | Default | Purpose |
|
| Root directory of the document store |
Paths are resolved against the document root; any path that escapes the root is rejected (traversal-guarded).
Production adapters
The backend is intentionally swappable. src/document-store.ts defines a single
interface (list / read / write / search / stat) that a Google Workspace,
Office 365, or SharePoint adapter can implement in place of the local filesystem
store. Similarly, src/drafter.ts emits a normalized outline that an LLM provider
can expand into full prose.
Drafting a Mission Script
A mission script is plain text; the engine heuristically parses outcome, scope,
constraints, and verification lines, then emits a deterministic outline with
scaffolds and alignment notes.
Example:
Outcome: Ship the Q3 revenue report.
Scope: Q3 actuals, regional breakdown, forecast deltas.
Constraints: Accounting sign-off required; max 5 pages.
Verification: Numbers reconcile to the general ledger.Publishing
Published to the npm registry via OIDC trusted publishing — no npm tokens stored
anywhere. Pushing a version tag triggers the .github/workflows/publish.yml workflow:
npm version patch -m "release: v%s"
git push origin main --follow-tagsOne-time bootstrap. The very first published version cannot use trusted publishing (the trust relationship attaches to an existing package). Publish
0.1.1once manually (npm publishafternpm login, or a short-lived publish-scoped token), then configure Trusted Publisher on npmjs.com → the package → Settings → Trusted publishing → GitHub Actions → ownerVibeLeading, repomcp-document-architect, workflowpublish.yml, actionallow npm publish(requires 2FA once per package).Requires Node.js >= 22 and npm >= 11.5.1 on the runner (handled by the workflow).
License & Attribution
MIT — Copyright (c) 2026 Jean Machuca (see LICENSE).
This server implements concepts from the book Vibe Leading The AI: The Corporate Race Against Machines by Jean Machuca (ISBN 9798252505008, © 2026 Jean Machuca). The book is copyrighted commercial material; this repository does not republish its text. Buy the book at https://vibeleading.org or https://a.co/d/04L5YatK. Author website: jeanmachuca.com · Support on GitHub Sponsors: github.com/sponsors/jeanmachuca. See NOTICE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent docs and memory for AI agents — read, write, organize & search a shared workspace.
Create and improve live, shared interactive documents with your agent.
- MemocoreOAuthai.memocore
Shared memory for all your AI agents, your whole team and every MCP client — save, search, recall.
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to search, deep-read, and build knowledge bases from Markdown, PDF, DOCX, and PPTX documents via MCP tools for retrieval, document navigation, and ingestion.16 npm633MIT
- FlicenseNot gradedqualityAmaintenanceProvides organizational memory for AI agents, enabling shared company memory, decision recall, artifact management, approval review, task delegation, and initiative tracking.2-
- AlicenseNot gradedqualityBmaintenanceProvides AI agents with persistent knowledge storage, enabling them to store, search, and retrieve text, documents, and files using semantic and keyword search via MCP tools.32Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to persistently store and semantically search shared knowledge via MCP tools.2MIT