20 tools from the Maxential Thinking MCP Server, categorised by risk level.
View the Maxential Thinking policy →get_branch Retrieve complete details of a specific branch. get_history Get your thought history. Optionally filter by branch. get_thought Retrieve a specific thought by its number. list_branches List all reasoning branches with their status and thought counts. search Search through thought history by content or tags. 2/5 session_list Browse available thinking sessions. Shows most recently updated first. session_load Restore a previously saved thinking session into memory. Resumes where you left off — all thoughts, branches, and tags are restored. branch Create a new reasoning branch to explore an alternative path. Like git branches for thoughts. 2/5 close_branch Close a branch with an optional conclusion. 2/5 complete Mark your thinking chain as complete with a final conclusion. 2/5 export Export the thinking chain to markdown or JSON format. 2/5 merge_branch Merge insights from a branch back into main. Strategies: conclusion_only, full_integration, summary 2/5 revise Revise a previous thought. Use when you realize earlier thinking was flawed or incomplete. 2/5 session_save Name and describe the current thinking session for later retrieval. Data is already persisted automatically — this adds a meaningful name and optio... 2/5 session_summary Generate a compressed summary of a thinking session for token-efficient context loading. Includes key findings from conclusions, tagged thoughts, a... 2/5 switch_branch Switch your active context to a different branch (or back to main). 2/5 think Add a thought to your reasoning chain. Use this for step-by-step problem solving. The server automatically tracks thought numbers and history. 2/5 visualize Generate a visual diagram of the thinking chain and branches. 2/5 The Maxential Thinking MCP server exposes 20 tools across 3 categories: Read, Write, Destructive.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Maxential Thinking server.
Maxential Thinking tools are categorised as Read (7), Write (11), Destructive (2). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept