Start a telemetry audit session to track agent compliance and tool success metrics for multi-step coding tasks, returning a unique session ID.
MIT
204,009 tools. Last updated 2026-06-14 22:14
"Improving Cursor Functionality with Structured Plans and Multi-Step Tasks" matching MCP tools:
- Break down complex problems into atomic reasoning steps with decomposition-contraction at depth 5. Use for implementation plans, architecture decisions, and multi-step verification.MIT
- Plan multi-step VM operations by validating actions and checking target existence in vSphere, generating a structured plan with rollback information for each step.MIT
- Apply step-by-step reasoning with web grounding to complex questions. Ideal for math, logic, comparisons, and multi-step arguments. Returns reasoned answers with numbered citations. Supports recency, domain, and search context filters.MIT
- Find step-by-step MCP tutorials for installing, configuring, comparing, and building servers to solve setup issues with clients like Claude, Cursor, and Cline.MIT
- Record structured reasoning steps to plan, analyze, and process complex multi-step tasks before acting. Use when you need to navigate detailed policies or challenge conclusions.MIT
Matching MCP Servers
Structured-shofficial
Alicense-qualityBmaintenanceMCP server providing managed persistent memory for AI agents. Read and write structured state across sessions, tools, and restarts at 1000+ requests per second, with no infrastructure to self-host or operate.Last updated2Apache 2.0- AlicenseAqualityCmaintenanceEnables automated export, compression, and cloud upload of Figma design assets by simply providing Figma links. Supports batch processing of nodes and children, returning structured data with publicly accessible image URLs.Last updated13MIT
Matching MCP Connectors
A fully autonomous, Agent-to-Agent (A2A) patent data marketplace powered by the Model Context Protocol (MCP) and A2A standards. This server provides highly structured, AI-optimized JSON patent datasets curated for autonomous R&D agents, LLMs, and Quants. Currently exclusively hosting AI-ready patents from IPC/CPC Sections G (Physics & Computing) and H (Electricity).
Autonomous A2A marketplace providing AI-ready, structured USPTO patent JSON datasets. Features IPC/CPC Sections G (Physics/Computing, e.g., G01 Sensors, G06 AI/ML) and H (Electricity, e.g., H01 Semiconductors, H04 5G). Enables instant M2M data delivery via automated on-chain payment verification. Networks: Base (USDC), Polygon (USDC), Oasis (ROSE).
- Generate a step-by-step consultation plan for multi-agent systems by assessing project complexity and providing structured recommendations with architecture diagrams.AGPL 3.0
- Retrieve added, modified, and removed Planner tasks since the last poll, using a saved cursor for incremental synchronization. Returns change envelopes and cursor status.MIT
- Executes a pre-configured AI agent workflow for tasks like due diligence, portfolio review, or market scanning. Provide the agent slug and inputs; receive step-by-step execution status and final output.MIT
- Translate natural language design tasks into multi-step plans that classify intent, build execution steps, and run them automatically.MIT
- Retrieve API endpoints with dependencies and schemas to plan multi-step workflows for accomplishing tasks, enabling structured API call execution.MIT
- Automatically decompose complex tasks into multi-step pipelines across multiple LLMs, routing each step to the optimal model. Supports templates for common patterns or auto-decomposition.MIT
- Record professional demo videos of browser automation sequences with cursor highlighting, step annotations, and customizable visual effects.MIT
- Retrieve workflow guides for Arcadia addresses, automation setup, strategy templates, and pool evaluation. Use before multi-step LP management tasks.AGPL 3.0
- Split complex tasks into manageable subtasks with defined dependencies, priorities, and structured updates. Ideal for streamlining workflows and adapting plans dynamically.MIT
- Create a TODO list with optional tasks and markdown support to organize multi-step work, track bug fixes, or plan feature development. Use for explicit requests and structured task management.
- Navigate back to the previous step in a multi-step form or screen flow assignment. Optionally update fields and attachments while moving backward.Apache 2.0
- Update a subtask's completion status in a chore to track progress on multi-step tasks without completing the whole chore.MIT
- Execute complex multi-page crawling tasks by providing a natural-language goal. The agent autonomously plans, navigates, and extracts structured data.MIT
- Delegate complex multi-step tasks to autonomous agents for independent execution with dedicated context, maintaining conversation continuity across sessions.MIT