"Using Windsurf and Claude Tools or Technologies" matching MCP servers:

MCP server and CLI for Windsurf/Devin server-side web search, exposing a web_search tool that returns JSON hits from the GetWebSearchResults API.

A persistent semantic memory system for Claude Code that provides a structured, versioned document store with semantic search and graph visualization. It acts as a memoization layer to store and retrieve research, design decisions, and codebase insights across different work sessions.

Multi-agent AI consultation framework for Claude Code via MCP — get second opinions from OpenAI, Gemini, Qwen, DeepSeek

Enables Claude Code to retain persistent cross-session memory with semantic search, automatically tracking user corrections as behavioral patterns that move through lifecycle stages. It also extracts signals from every session to evolve and promote behavioral frameworks, giving the assistant developing judgment over time.

Enables Claude Code sessions to persist identity and cross-session memory through a local SQLite store with semantic search, so past facts, decisions, and lessons can be recalled by meaning. It also detects and classifies user corrections into behavioral patterns that progress from new to internalized, letting reflection cycles evolve skills that work over time.

MCP server for compressing AI embeddings by 5-7x using TurboQuant (PolarQuant + QJL), with tools to compress, decompress, estimate savings, and embed+compress vectors.

Enables Claude Code to retain cross-session memory of facts, decisions, and lessons with semantic search, while tracking user corrections as behavioral patterns and evolving self-improving frameworks over time. All processing runs locally through an MCP server and hooks, requiring no cloud service or API key.

Enables structured team communication for Claude Code agents through Slack-like channels and direct messages. Supports project isolation, subscription management, and agent notes for sophisticated multi-agent collaboration workflows.

Enables Claude to search past coding transcripts stored locally — by exact words or by meaning — read them page by page, and reopen them in a terminal to resume work in the original directory. Everything stays on the machine, with a year-long archive.

Serves plain-text notes that an Obsidian user has explicitly published for AI over streamable HTTP, with full-text and embedding-based search. MCP clients can read and search those notes and queue suggested edits that the user's own client applies only if the AI rules allow it.

Gives Claude Code persistent memory across sessions with semantic search, tracks and classifies user corrections to surface behavioral patterns, and evolves behavioral frameworks over time based on accumulated evidence. Runs entirely locally through 15 MCP tools and hooks, requiring no API key or cloud service.

Gives Claude Code persistent cross-session memory with semantic search, automatic detection and classification of user corrections, and evolving behavioral frameworks that develop over time. Runs fully locally through Claude Code's hooks and 15 MCP tools, requiring no API key or cloud service.

Enables Claude to index and retrieve context from codebases using self-hosted Milvus for semantic search, with hardened reliability and security for production use.

Enables Claude Code to retain persistent identity and cross-session memory, storing facts, decisions, and lessons in a local searchable database that can be queried semantically by meaning. It also detects and classifies user corrections over time, tracking behavioral patterns through lifecycle stages so repeatedly confirmed working practices are promoted and failures retired.

Enables Claude Code to retain identity, memories, and behavioral frameworks across sessions — saving facts and decisions for later semantic search, detecting and classifying user corrections, and evolving learned frameworks over time. Everything runs locally through a SQLite-backed engine with 15 MCP tools plus hooks, requiring no cloud service or API key.

Gives Claude Code persistent cross-session memory with semantic search over saved facts, decisions, and journals, alongside automatic detection and classification of user corrections as trackable behavioral patterns. It also extracts behavioral signals from sessions and evolves self-authored frameworks over time, so the assistant develops judgment that carries forward between conversations — all local, with no cloud or API key required.

Enables users to create notebooks, upload documents and court rulings, query their contents, and generate audio, video, presentation, or flashcard outputs.

Enables Claude Code to search and retrieve information from its past session transcripts, including tool calls, errors, and project-specific history, via an SQLite FTS5 full-text search index.

Gives Claude Code a persistent identity and cross-session memory with semantic search over saved facts, decisions, and journals. It also detects and classifies user corrections into behavioral patterns with lifecycle trends, reflecting periodically to promote or retire working frameworks.

Enables Claude Code to remember facts, decisions, and lessons across sessions through semantic and keyword memory search, and to track user corrections as behavioral patterns that evolve over time. It also exposes tools for loading identity and frameworks, recording signals, and triggering reflection cycles so the assistant's judgment improves with use.

Enables Claude Code to retain persistent identity, searchable cross-session memory, and self-evolving behavioral frameworks across conversations. It tracks user corrections as patterns, detects improvement trends, and reflects on accumulated signals to refine judgment over time.

Provides Claude Code with cross-session memory, semantic recall of facts and decisions, and tracking of user corrections as behavioral patterns. Enables persistent identity, self-evaluation, and framework evolution so the assistant learns from past sessions.

Enables Claude Code to use local markdown notes as persistent, searchable memory with hybrid recall, episodic memory, note-graph traversal, design memory, and optional cloud sync.

Enables searching and retrieving Claude Code conversation history via hybrid semantic and keyword search, allowing the agent to access its own past interactions.

A multi-function Streamable HTTP MCP tool aggregation server that provides web search via Brave, Exa, and SearXNG with multi-key rotation and cross-provider fallback, and supports extensible tool families (URL fetch, code search, RAG) through a pluggable architecture.

Cross-machine context sharing MCP server for Claude Code, enabling shared memory of decisions, patterns, and knowledge across multiple Claude Code instances on different machines.

Enables persistent cross-session memory, correction-pattern tracking, and evolving behavioral frameworks within Claude Code, exposing 15 MCP tools for saving and semantically searching facts, decisions, and lessons, loading identity and framework context, and triggering reflection cycles so the assistant improves over time.

Enables Claude Code to retain facts, decisions, and lessons across sessions through local semantic search, and to automatically detect, classify, and trend user corrections as behavioral patterns. It also runs reflection cycles that promote or retire learned frameworks, all through 15 MCP tools and hooks with no cloud dependency.

Enables Claude Code to retain cross-session memory, track and classify user corrections, and evolve behavioral frameworks through local MCP tools and hooks.

Gives Claude Code persistent cross-session memory with semantic search over facts, decisions, and lessons, plus automatic tracking of user corrections and behavioral patterns. Enables a Claude that evolves reusable frameworks over time — promoting what works and retiring what doesn't — all locally through MCP tools and hooks.

This MCP server gives Claude Code persistent cross-session memory with semantic search, automatic detection and tracking of user corrections as behavioral patterns, and reflective framework evolution that improves judgment over time. Everything runs locally through Claude Code's hooks and extension points, with no cloud, accounts, or API keys required.

Enables Claude Code to retain persistent identity and cross-session memory through local semantic search over saved facts, decisions, and lessons, plus automatic detection and classification of user corrections to track behavioral patterns over time. It also reflects on accumulated behavioral signals to evolve and retire working frameworks, so responses adapt toward the user's judgment across sessions without cloud services or API keys.

Enables clinical question answering via OpenEvidence with citation verification, including tools to ask questions, retrieve results, and follow up, plus an integrated skill to check citations against primary sources.

MCP server that indexes Markdown files into a local SQLite vector store and provides semantic search tools for Claude Code.

Enables Claude to search locally indexed exported chat history and project docs, retrieving full messages and conversation IDs via full-text search.

Gives Claude Code persistent cross-session memory with semantic search, automatic detection and classification of user corrections into behavioral patterns, and self-evolving frameworks that refine judgment over time. Everything runs locally through hooks and MCP tools, with no cloud, API keys, or telemetry.

Provides memory and project tracking for Claude Code via MCP, enabling semantic search over past transcripts, durable notes, and structured project management with milestones, epics, tickets, and todos.

MCP server scaffold that exposes stubbed tools for listing, searching, and summarizing sources, with built-in OAuth 2.1 authorization flow for Claude integration.

Enables AI assistants to search a curated database of 200+ AI tool cards with pricing, platforms, use cases, and source links, so users can ask which tool to use for a task and get grounded recommendations.

Provides web search capabilities to Claude AI using the Anthropic API, allowing LLMs to access up-to-date information from the web with customizable domain filtering.