Load the master Thinking Toolkit — the diagnostic router that maps stuck-types to techniques. Contains the full decision tree, diagnostic questions, technique combinations table, and when-not-to-use guidance. Use this when you want to understand the full system rather than a single technique.
Single-target operation
Part of the Thinking Toolkit MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_thinking_toolkit to retrieve information from Thinking Toolkit 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 get_thinking_toolkit 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:
get_thinking_toolkit:
rules:
- action: allowSee the full Thinking Toolkit policy for all 4 tools.
Agents calling read-class tools like get_thinking_toolkit 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.
Load the master Thinking Toolkit — the diagnostic router that maps stuck-types to techniques. Contains the full decision tree, diagnostic questions, technique combinations table, and when-not-to-use guidance. Use this when you want to understand the full system rather than a single technique.. It is categorised as a Read tool in the Thinking Toolkit MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_thinking_toolkit. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Thinking Toolkit MCP server.
get_thinking_toolkit 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 get_thinking_toolkit 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 get_thinking_toolkit. 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.
get_thinking_toolkit is provided by the Thinking Toolkit MCP server (elbpr/thinking-toolkit). 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