# sequentialthinking A detailed tool for dynamic and reflective problem-solving through thoughts. This tool helps analyze problems through a flexible thinking process that can adapt and evolve. Each thought can build on, question, or revise previous insights as understanding deepens. When to use this tool: - Breaking down complex problems into steps - Planning and design with room for revision - Analysis that might need course correction - Problems where the full scope might not be clear initially - Problems that require a multi-step solution - Tasks that need to maintain context over multiple steps - Situations where irrelevant information needs to be filtered out Key features: - You can adjust total_thoughts up or down as you progress - You can question or revise previous thoughts - You can add more thoughts even after reaching what seemed like the end - You can express uncertainty and explore alternative approaches - Not every thought needs to build linearly - you can branch or backtrack - Generates a solution hypothesis - Verifies the hypothesis based on the Chain of Thought steps - Repeats the process until satisfied - Provides a correct answer Parameters explained: - thought: Your current thinking step, which can include: * Regular analytical steps * Revisions of previous thoughts * Questions about previous decisions * Realizations about needing more analysis * Changes in approach * Hypothesis generation * Hypothesis verification - nextThoughtNeeded: True if you need more thinking, even if at what seemed like the end - thoughtNumber: Current number in sequence (can go beyond initial total if needed) - totalThoughts: Current estimate of thoughts needed (can be adjusted up/down) - isRevision: A boolean indicating if this thought revises previous thinking - revisesThought: If is_revision is true, which thought number is being reconsidered - branchFromThought: If branching, which thought number is the branching point - branchId: Identifier for the current branch (if any) - needsMoreThoughts: If reaching end but realizing more thoughts needed You should: 1. Start with an initial estimate of needed thoughts, but be ready to adjust 2. Feel free to question or revise previous thoughts 3. Don Agent View of the PolicyLayer registry record for `sequentialthinking`. HTML page: https://policylayer.com/tools/cowork-bench/sequentialthinking ## Facts - Tool: `sequentialthinking` - Server: Cowork Bench (`0717376/cowork_bench`) — https://policylayer.com/tools/cowork-bench.md - Homepage: https://github.com/0717376/cowork_bench - Risk category: Destructive (Critical risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Hidden ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "sequentialthinking", "arguments": {} } } ``` ## Why sequentialthinking is rated Critical An AI agent that decides to call sequentialthinking doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Cowork Bench is gone. There is no undo for destructive operations. Risk signals: Bulk/mass operation — affects multiple targets ## Use case AI agents call sequentialthinking to permanently remove resources in Cowork Bench, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo. ## Recommended policy (PolicyLayer) Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Cowork Bench: ```json { "version": "1", "default": "deny", "hide": [ "sequentialthinking" ] } ``` ## Other tools on Cowork Bench (432) - `canvas_delete_announcement` — Destructive — https://policylayer.com/tools/cowork-bench/canvas-delete-announcement.md - `canvas_delete_assignment` — Destructive — https://policylayer.com/tools/cowork-bench/canvas-delete-assignment.md - `canvas_delete_conversation` — Destructive — https://policylayer.com/tools/cowork-bench/canvas-delete-conversation.md - `canvas_delete_course` — Destructive — https://policylayer.com/tools/cowork-bench/canvas-delete-course.md - `canvas_delete_quiz` — Destructive — https://policylayer.com/tools/cowork-bench/canvas-delete-quiz.md - `canvas_delete_quiz_question` — Destructive — https://policylayer.com/tools/cowork-bench/canvas-delete-quiz-question.md - `delete_draft` — Destructive — https://policylayer.com/tools/cowork-bench/delete-draft.md - `delete_email` — Destructive — https://policylayer.com/tools/cowork-bench/delete-email.md - `delete_emails` — Destructive — https://policylayer.com/tools/cowork-bench/delete-emails.md - `delete_entities` — Destructive — https://policylayer.com/tools/cowork-bench/delete-entities.md - `delete_event` — Destructive — https://policylayer.com/tools/cowork-bench/delete-event.md - `delete_folder` — Destructive — https://policylayer.com/tools/cowork-bench/delete-folder.md - `delete_footnote_from_document` — Destructive — https://policylayer.com/tools/cowork-bench/delete-footnote-from-document.md - `delete_footnote_robust` — Destructive — https://policylayer.com/tools/cowork-bench/delete-footnote-robust.md - `delete_observations` — Destructive — https://policylayer.com/tools/cowork-bench/delete-observations.md - `delete_page` — Destructive — https://policylayer.com/tools/cowork-bench/delete-page.md - `delete_paragraph` — Destructive — https://policylayer.com/tools/cowork-bench/delete-paragraph.md - `delete_range` — Destructive — https://policylayer.com/tools/cowork-bench/delete-range.md - `delete_relations` — Destructive — https://policylayer.com/tools/cowork-bench/delete-relations.md - `delete_sheet_columns` — Destructive — https://policylayer.com/tools/cowork-bench/delete-sheet-columns.md - `delete_sheet_rows` — Destructive — https://policylayer.com/tools/cowork-bench/delete-sheet-rows.md - `delete_worksheet` — Destructive — https://policylayer.com/tools/cowork-bench/delete-worksheet.md - `drop_databases` — Destructive — https://policylayer.com/tools/cowork-bench/drop-databases.md - `drop_schemas` — Destructive — https://policylayer.com/tools/cowork-bench/drop-schemas.md - `drop_tables` — Destructive — https://policylayer.com/tools/cowork-bench/drop-tables.md - `unprotect_document` — Destructive — https://policylayer.com/tools/cowork-bench/unprotect-document.md - `woo_coupons_delete` — Destructive — https://policylayer.com/tools/cowork-bench/woo-coupons-delete.md - `woo_orders_delete` — Destructive — https://policylayer.com/tools/cowork-bench/woo-orders-delete.md - `woo_products_delete` — Destructive — https://policylayer.com/tools/cowork-bench/woo-products-delete.md - `browser_navigate` — Execute — https://policylayer.com/tools/cowork-bench/browser-navigate.md - …and 402 more: https://policylayer.com/tools/cowork-bench.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=cowork-bench · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/cowork-bench