"Scratch" matching MCP servers:

Enables clients to interact with a bundled documentation corpus through MCP tools and resources over HTTP or stdio, and provides a trajectory evaluation harness for grading agent performance.

Generates crash-proof Python LLM pipelines from plain English descriptions. Pipelines resume from the last successful node after a crash instead of restarting from scratch. IProvider-agnostic , works with Groq, Gemini, Ollama, OpenAI, or any Python callable. Zero infrastructure, runs entirely on free-tier APIs.

Enables autonomous agents to snapshot execution-tree and context states, evaluate branch viability, and roll back to previous checkpoints when an exploration path fails without restarting from scratch.

Provides a 'think' tool that allows Claude and other LLMs to add dedicated thinking steps during complex tool use scenarios, creating space for structured reasoning and improving problem-solving capabilities.

Shared rooms for AI agents (AgentsChat): channels, DMs, proposals & voting, OKR trees, and human handoff. Existing MCP clients (Claude Code, Cursor, and others) join live rooms instead of building a crew from scratch.

Enables long-running autonomous agents to snapshot environment and context states, evaluate the viability of competing reasoning branches, and roll back to an earlier checkpoint when an exploration path fails without restarting from scratch. Exposes this tree-of-thoughts state management over the Model Context Protocol for use in Claude Desktop, Cursor, and custom agentic frameworks.

scratchpad-mcp is an MCP server that gives AI agents persistent, token-efficient storage. Eight tools versioned file writes, structured line-diffs since a prior version, append-only logs with cursor pagination, on-demand summaries with per-version caching, and per-agent quotas. The point is to stop agents from re-reading files they've already seen and re-summarizing documents.

Compiles locally captured screen activity into deterministic, evidence-backed records and executable workflows that agents can consume through MCP tools. Enables agents to fetch recent context, day summaries, click-by-click replay steps, repetitive-workflow patterns, and communication surfaces so routine tasks can be repeated instead of re-derived from scratch.

Provides persistent agent workspaces with MongoDB storage for file management and real-time task progress tracking. It enables secure, isolated user environments with full activity logging for workspace operations.