Access 15 mental models for structured reasoning. Each model provides a complete prompt with process steps, examples, and pitfalls. Mental models are process scaffolds that tell you HOW to think about a problem, not WHAT to think. They're infrastructure for your reasoning. Operations: - get_mod...
Single-target operation
Part of the Thoughtbox MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call mental_models to retrieve information from Thoughtbox without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though mental_models only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
mental_models:
rules:
- action: allowSee the full Thoughtbox policy for all 4 tools.
Agents calling read-class tools like mental_models have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Access 15 mental models for structured reasoning. Each model provides a complete prompt with process steps, examples, and pitfalls. Mental models are process scaffolds that tell you HOW to think about a problem, not WHAT to think. They're infrastructure for your reasoning. Operations: - get_model: Retrieve a specific mental model prompt - list_models: List available models (optionally filtered by tag) - list_tags: List all available tags with descriptions - get_capability_graph: Get structured data for knowledge graph initialization Available tags: debugging, planning, decision-making, risk-analysis, estimation, prioritization, communication, architecture, validation Use list_models with a tag filter to discover relevant models for your task. For example, use tag "debugging" when stuck on an issue, or "decision-making" when choosing between options.. It is categorised as a Read tool in the Thoughtbox MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for mental_models. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Thoughtbox MCP server.
mental_models is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mental_models 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 mental_models. 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.
mental_models 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