toggle-brain MCP Server
Provides access to the Toggle Brain knowledge base, including resources, prompt templates, and executable scripts from the toggle-brain repository.
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., "@toggle-brain MCP Server summarise the Toggle Brain positioning docs"
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.
toggle-brain MCP Server
A Model Context Protocol server that exposes the Toggle Brain knowledge base, prompt templates, and executable scripts to any MCP-compatible AI assistant — Claude Code, Cursor, Windsurf, and more.
Content lives in the toggle-brain repository and is automatically synced here on every push. You never need a GitHub token, API keys, or manual updates at runtime — just clone, build, and connect.
What it exposes
MCP primitive | Source in toggle-brain | Example |
Resources |
|
|
Prompts |
|
|
Tools | Any |
|
Related MCP server: datacore-mcp
Prerequisites
Node.js 20 LTS or later
That's it. No tokens, no API keys, no external services.
Setup
1. Clone the repo
git clone https://github.com/toggle-workspace/toggle-mcp.git
cd toggle-mcp2. Install dependencies and build
npm install
npm run build3. Verify it works
node dist/index.js
# Loaded: 153 resources, 15 prompts, 1 toolsConnecting to Claude Code
From inside the cloned toggle-mcp directory, run:
claude mcp add toggle-brain node "$(pwd)/dist/index.js"Then run /mcp inside a Claude Code session to confirm it is connected:
/mcp
# toggle-brain — ConnectedConnecting to Cursor
Add to ~/.cursor/mcp.json (or via Cursor Settings → MCP):
{
"mcpServers": {
"toggle-brain": {
"command": "node",
"args": ["/path/to/toggle-mcp/dist/index.js"]
}
}
}Replace /path/to/toggle-mcp with the actual path where you cloned the repo.
Connecting to Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"toggle-brain": {
"command": "node",
"args": ["/path/to/toggle-mcp/dist/index.js"]
}
}
}Replace /path/to/toggle-mcp with the actual path where you cloned the repo.
Remote / HTTP mode
Set TRANSPORT=http to run as an SSE server on a fixed port:
TRANSPORT=http PORT=3000 node dist/index.jsPoint any MCP client at http://localhost:3000/sse.
Usage
Once connected, the AI assistant can:
Browse knowledge — ask it to read resources like "summarise the Toggle Brain positioning docs" or reference
kb://brain--services--copywritingdirectlyRun prompt templates — ask it to use a prompt like
generators--email-sequencewith your variables filled inExecute tools — any
.tsor.pyscripts from toggle-brain are callable as tools
In Claude Code, confirm what is loaded at any time:
/mcpFor maintainers
How the sync works
Content in this repo is kept up to date by a two-step GitHub Actions pipeline:
toggle-brain runs
.github/workflows/notify-mcp.ymlon every push tomain. This workflow dispatches arepository_dispatchevent of typetoggle-brain-updatedto thetoggle-mcprepository.toggle-mcp has
.github/workflows/sync-brain.ymlwhich listens for that event, checks out toggle-brain, copies its contents into this repo, and commits and pushes the result.
The MCP server reads from the local content/ directory at runtime — no network calls, no tokens required for end users.
Required secret
The toggle-brain notify workflow needs a GitHub PAT stored as a repository secret named GH_PAT. This token must have:
repo scope (to dispatch events to toggle-mcp)
workflow scope (to trigger Actions workflows)
Add it at: toggle-brain repo → Settings → Secrets and variables → Actions → New repository secret
Adding the notify workflow to toggle-brain
See TOGGLE_BRAIN_SETUP.md for the step-by-step guide. In short, create .github/workflows/notify-mcp.yml in the toggle-brain repository with the content from toggle-brain-notify-workflow.yml in this repo.
Once this is in place, every push to toggle-brain/main will automatically update the content in this repo within seconds.
Troubleshooting
Symptom | Fix |
| Re-run |
Resources show as empty or missing | Run |
Build fails with type errors | Ensure Node.js 20 or later is installed ( |
Sync Action fails in toggle-brain | Check that the |
Sync Action fails in toggle-mcp | Check that |
HTTP mode not reachable | Confirm |
Available Tools
19 toolsclients_audaura_unitar_assets_build_leadformD
!/usr/bin/env python3
Inputs: args.
clients_toggle_design_system_charts_generatorD
!/usr/bin/env python3
Inputs: args.
clients_toggle_design_system_icons_generatorD
!/usr/bin/env python3
Inputs: args.
tools_brain_bot_hooks_path_guardD
!/usr/bin/env python3
Inputs: args.
tools_remotion_remotion.configD
Inputs: args.
tools_remotion_src_explainer_brand_geometryD
Inputs: args.
tools_remotion_src_explainer_brand_isoformsD
Generated from assets/illustrations/step-form.svg (canonical — regenerate, never redraw).
Inputs: args.
tools_remotion_src_explainer_brand_wordmarkpathsC
Generated from assets/logos/toggle-wordmark.svg (canonical — never re-typeset).
Inputs: args.
tools_remotion_src_explainer_layoutD
Inputs: args.
tools_remotion_src_explainer_tokensD
Source of truth: clients/toggle/design-system/ TOKENS.md + MOTION.md + BRAND-IDENTITY.md
Inputs: args.
tools_remotion_src_indexD
Inputs: args.
tools_remotion_src_onboarding_kit_typesC
Data-driven onboarding video series. One engine (OnboardingVideo.tsx) renders
Inputs: args.
tools_remotion_src_onboarding_registryD
The client-onboarding series, in viewing order. Root.tsx maps this into one
Inputs: args.
tools_remotion_src_onboarding_videos_google_adsC
VIDEO 3 — Google Ads manager (MCC) link + GA4 Editor for conversion import.
Inputs: args.
tools_remotion_src_onboarding_videos_meta_adsD
VIDEO 2 — Meta Ads partner access. Flow (share assets to a partner Business
Inputs: args.
tools_remotion_src_onboarding_videos_permissionsD
VIDEO 6 — the consolidated access checklist + the reassurance quartet. Access
Inputs: args.
tools_remotion_src_onboarding_videos_seoD
VIDEO 5 — SEO access: Search Console (Full), GA4 (Viewer), CMS (Administrator —
Inputs: args.
tools_remotion_src_onboarding_videos_tiktok_adsD
VIDEO 4 — TikTok Business Center. Roles are Admin / Standard / Analyst; events
Inputs: args.
tools_remotion_src_onboarding_videos_welcomeC
VIDEO 1 — the warm intro. No platform steps; sets up why we're about to ask
Inputs: args.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 19 tools
Many tools have overlapping domains (e.g., multiple onboarding videos) and lack clear distinctions in descriptions. The path-like names and sparse descriptions make it impossible for an agent to reliably select the correct tool.
Tool names follow no consistent pattern; they mix file paths, project prefixes, and arbitrary slugs. No verb_noun structure exists, and conventions vary wildly (e.g., clients_ vs tools_).
19 tools is a moderate number, but the set is not scoped to a coherent domain. Many tools appear to be internal files (e.g., config files, video scripts) that do not form a purposeful tool surface.
The domain is entirely unclear, so completeness cannot be assessed meaningfully. The tools appear to be a random dump of files with no obvious operations, missing any semblance of CRUD or lifecycle coverage.
Related MCP Connectors
Hosted MCP server for live public-data APIs and Skills for AI agents.
Official MCP bridge to Exogram—the Personal AI Agent for your work, people, and life.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceWraps TheBrain knowledge graph as an MCP server, enabling AI assistants to search, create, and manage thoughts, links, and notes via natural language.5-

datacore-mcpofficial
AlicenseAqualityBmaintenanceMCP server exposing Datacore's knowledge base, GTD, and engram memory to any AI assistant.530 npmMIT- FlicenseNot gradedqualityDmaintenanceEnables AI clients to connect to example tools, resources, and prompts over MCP, demonstrating integration with IDEs, chatbots, and agent frameworks.-
- AlicenseNot gradedqualityCmaintenanceExposes a Markdown-based second brain as MCP tools, enabling MCP clients like Claude Code, Codex, Claude Desktop, n8n, and bots to read context, search notes, retrieve wiki pages, and optionally register decisions or sources.MIT