"Scratch" matching MCP servers:

Enables AI agents to control Assimilate SCRATCH / Live FX through tools generated from its REST API, with a read-only default and configurable safe or full access modes.

Enables AI agents to build, playtest, and publish Scratch projects headlessly over MCP, with 112 tools covering the website/social graph, block-level project editing, headless VM execution, and Python-to-blocks workflows.

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.

Enables learning and integration testing of the Model Context Protocol by evolving from a minimal server toward production-grade tools, resources, prompts, and agent interoperability.

A Flask-based MCP server designed for testing deployment on Google App Engine. Provides a deeplink checking endpoint that accepts flattened JSON parameters and forwards them as nested objects to external APIs.

Enables AI agents to validate wireless communication ideas by providing standardized channel instances and physical measurements through MCP, eliminating the need to write simulations from scratch.

A Python MCP server implemented from scratch, providing tool execution capabilities like system time and file hashing via stdio or HTTP transport.

Lets users discover, compare, and audit public MCP servers from the official registry, validate server.json metadata, and generate installation snippets and publication checklists.

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.

MCP server providing persistent memory and context for AI tools, including semantic memory, knowledge graph, and session history to avoid starting from scratch in every conversation.

A demonstration MCP server providing basic tools for returning greetings and performing mathematical addition. It serves as a practical workshop guide for setting up and configuring Model Context Protocol servers from scratch using Python.

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.

A simple MCP server that exposes stock price lookup tools, demonstrating how to set up MCP from scratch with Ollama.

Enables AI assistants to read and decode, generate from scratch, and reset Crocodile Physics 1.7 circuit files (.cyp) without opening the GUI, exposing components, wires, electrical nodes and saved voltages and currents as MCP tools. Generated circuits open and simulate directly in Crocodile, and the whole format is exposed byte by byte.

Manages a global scratchpad file on your Desktop for tracking interruptions, ideas, tasks, and focus across all projects with secure input validation and rate limiting.

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.

MCP server for Databricks Unity Catalog, enabling table listing, schema description, and read-only SQL query execution via natural language. Built from scratch to demonstrate JSON-RPC 2.0 protocol depth.

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.

Enables a coding agent to search the last year of papers, repositories and packages for dated evidence that the library, format reader or model its plan assumes is unavailable already exists. This lets it reuse published work instead of rebuilding it from scratch or declaring the task impossible.