"How to login and extract information from my B2B website" matching MCP servers:

Enables small local models to persist and retrieve long-term user facts through remember and recall tools, using SQLite FTS5 keyword search for lightweight memory without external vector databases or heavy VRAM.

Serves a git-backed folder of Markdown notes over MCP so AI agents can search, read, write, move and delete them, with every write recorded as a git commit attributed to the calling client. Supports full-text section search with snippets, wikilinks and typed relations, LFS-backed searchable attachments, optimistic concurrency for multiple agents, and per-client token or OAuth 2.1 access.

A MCP server that provides persistent memory for AI assistants, storing personal information, relationships, and observations to enable personalized and contextual conversations.

A simple MCP server that recalls and saves memories from and to Apple Notes.

Enables persistent memory for MCP clients over Streamable HTTP, with token authentication and SQLite storage in a Docker volume. It provides fact storage, recall, topic-based recall, consolidation, and plugin support.

Turns GitHub repository history into a cited maintainer skill for coding agents, providing tools to collect evidence, query the knowledge graph, and inspect bundles.

Turn Obsidian notes into agent-ready context, preview-only plans, and safe repo handoffs.

A note management MCP server that enables users to store, retrieve, and summarize personal notes via a custom URI scheme. It provides tools for adding content and prompts for generating brief or detailed summaries of stored information.

A self-hosted MCP server providing persistent memory for AI tools, allowing them to remember, recall, and manage information across sessions using a SQLite database.

Enables precise measurement of live HTTP and WebSocket services while maintaining an append-only, evidence-based ledger of claims that agents can query with explicit timestamps, staleness indicators, and instructions for re-verification.

MCP server for local Zotero on Windows and WSL, enabling read access to items, collections, annotations, and notes via the Local API, and safe write operations through a plan/apply workflow with Web API verification.

Enables AI agents to store and retrieve project context, bugs, decisions, and session logs by reading and appending markdown files in a local Obsidian vault, without requiring any cloud services.

Enables Claude and ChatGPT to share a single study-progress database for interview prep, coursework, and spaced repetition, with per-user data isolation and server-side SM-2 scheduling for due reviews and study plans.

MCP server for Ultrathink: save and search your knowledge base from Claude Desktop, Claude Code, and any MCP client.

Enables researchers to turn property-history questions into reviewable evidence dossiers by gathering sources, tracing people and places, linking conclusions to supporting or opposing passages, and exporting portable backups.

TheWeave is a markdown-native memory architecture for Claude and any MCP-aware agent. Your agent's memory lives as plain .md files you own: a 5-verb MCP core over the vault, query-driven PageRank retrieval, bi-temporal facts (valid_from / valid_until), and a persona-as-vault model. No database and no embeddings server. The files are the memory, inspectable in your editor and versionable in git.

Enables local MCP clients to list, read, write, and search notes in an Obsidian vault via an HTTP server running inside Obsidian.

Enables managing personal vehicle history including mileage, maintenance, expenses, reminders, and document references through MCP tools and resources, all stored locally in SQLite.

Enables users to add, get, and list notes, with state persisted to a JSON file in the home directory.

Enables converting PDF, EPUB, and TXT books into validated chapter analyses, guarded Obsidian notes, and installable Agent Skills that can be reused across Codex, Claude Code, or other MCP-capable clients.

MCP server that connects AI agents to Google NotebookLM, enabling natural language interaction with notebooks, including Q&A, source ingestion, and audio overview generation.

Enables MCP-capable AI clients to read and write a self-hosted todo list, quick memos, and a plain-Markdown knowledge base through 16 tools covering search, tasks, notes, and identity checks. Tool visibility is scoped per API key with directory-level permissions, and every call is audit-logged.

A local Mem0 MCP server for macOS with a menu bar toggle, storing memories locally in Chroma and using any OpenAI-compatible LLM for fact extraction.

Enables local-first knowledge management for Codex, providing tools for guided discussions, contextual recall, review, and daily topics.

Builds a searchable memory bank from persona-specific PDF content and exposes it as an MCP tool for querying.

Enables MCP clients to add, retrieve, update, delete, and list notes stored in a configurable local JSON file, with atomic saves behind a write lock.

Enables managing personal notes through Claude Desktop with add, get, update, delete, and list tools, using atomic saves and a configurable notes file.

Enables adding, retrieving, updating, deleting, and listing notes through MCP tools, with atomic saves and a configurable notes file path.

Metis gives AI agents expert know-how that named reviewers have approved, and only where its recorded conditions match the situation. High-risk situations go to a person. When an agent sees practice depart from procedure, it can send the expert one short question. Every retrieval is recorded on a hash-linked evidence chain.

Stores and retrieves personal information fields securely, allowing Claude to access your name, address, email, and professional details without re-typing them.