MCP server providing cognitive enhancement tools for LLM agents: structured reasoning, mental models, and literate programming notebooks
Connect Thoughtbox to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server providing cognitive enhancement tools for LLM agents: structured reasoning, mental models, and literate programming notebooks. The thoughtbox mcp server is what makes that connection.
Thoughtbox exposes exactly two MCP tools using the Code Mode pattern:
vitest on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Testing — The Testing tool exposed by this serverStorage — Data is stored at ~/.thoughtbox/ by default (FileSystemStorage): text ~/.thoughtbox/ ├── config.json # Global configuration └── projects/ └──Configuration is passed through the environment: THOUGHTBOX_AGENT_ID, SUPABASE_URL, SUPABASE_SERVICE_ROLE_KEY, PROMETHEUS_URL, GRAFANA_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Thoughtbox's toolset — Testing, Storage — is a fair guide to whether it matches your workflow. It is maintained by kastalien-research; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Testing | The Testing tool exposed by this server. |
| Storage | Data is stored at ~/.thoughtbox/ by default (FileSystemStorage): text ~/.thoughtbox/ ├── config.json # Global configuration └── projects/ └── {project}/ └── sessions/ └── {date}/ └── {session-id}/ ├── manifest.json └── { |
{
"mcpServers": {
"thoughtbox": {
"command": "npx",
"args": ["-y", "vitest"],
"env": {
"THOUGHTBOX_AGENT_ID": "your-value",
"SUPABASE_URL": "your-value",
"SUPABASE_SERVICE_ROLE_KEY": "your-value",
"PROMETHEUS_URL": "your-value",
"GRAFANA_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| THOUGHTBOX_AGENT_ID | Configuration value read at startup. | Optional |
| SUPABASE_URL | Endpoint or connection string the server talks to. | Yes |
| SUPABASE_SERVICE_ROLE_KEY | Credential the server authenticates with. | Yes |
| PROMETHEUS_URL | Endpoint or connection string the server talks to. | Yes |
| GRAFANA_URL | Endpoint or connection string the server talks to. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.