Notebook toolhost for literate programming with JavaScript/TypeScript. Create, manage, and execute interactive notebooks with markdown documentation and executable code cells. Each notebook runs in an isolated environment with its own package.json and workspace. ✨ NEW: Pre-structured templates ...
Part of the Thoughtbox MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents invoke notebook to trigger processes or run actions in Thoughtbox. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
notebook can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
tools:
notebook:
rules:
- action: allow
rate_limit:
max: 10
window: 60
validate:
required_args: trueSee the full Thoughtbox policy for all 4 tools.
Agents calling execute-class tools like notebook have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
notebook is one of the high-risk operations in Thoughtbox. For the full severity-focused view — only the high-risk tools with their recommended policies — see the breakdown for this server, or browse all high-risk tools across every MCP server.
Notebook toolhost for literate programming with JavaScript/TypeScript. Create, manage, and execute interactive notebooks with markdown documentation and executable code cells. Each notebook runs in an isolated environment with its own package.json and workspace. ✨ NEW: Pre-structured templates for guided workflows - Use template: "sequential-feynman" for deep learning with Feynman Technique - Templates provide scaffolded cells, metacognitive prompts, and progress tracking - Perfect for complex topics requiring validated understanding Available operations: - create: Create a new notebook (optionally from template) - list: List all active notebooks - load: Load notebook from .src.md file - add_cell: Add cell (title/markdown/code) - update_cell: Update cell content - run_cell: Execute code cell - install_deps: Install npm dependencies - list_cells: List all cells in notebook - get_cell: Get cell details - export: Export notebook to .src.md Common operation examples: Create a blank notebook: { operation: "create", args: { title: "My Analysis", language: "typescript" } } Create from Sequential Feynman template: { operation: "create", args: { title: "React Server Components", language: "typescript", template: "sequential-feynman" } } Add a code cell: { operation: "add_cell", args: { notebookId: "abc123", cellType: "code", content: "console.log('hello')", filename: "example.ts" } } Run a cell: { operation: "run_cell", args: { notebookId: "abc123", cellId: "cell_456" } } List notebooks: { operation: "list", args: {} } For detailed schemas of all operations, see the thoughtbox://notebook/operations resource. When to use: - Writing executable documentation - Building reproducible code examples - Creating step-by-step tutorials - Developing and testing code snippets - Prototyping with immediate feedback - Deep learning workflows (with templates). It is categorised as a Execute tool in the Thoughtbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Add a rule in your Intercept YAML policy under the tools section for notebook. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Thoughtbox MCP server.
notebook is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the notebook rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for notebook. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
notebook is provided by the Thoughtbox MCP server (@kastalien-research/thoughtbox). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept