"General Information or Concepts About Thinking" matching MCP servers:

Provides tools to monitor host system health including CPU load, disk usage, and network status while enabling file system management tasks like searching and moving files. It includes built-in safety guards to prevent operations on critical system directories.

Enables users to ask natural-language questions about a local folder's contents, including file names, sizes, and timestamps, with rollups by type and age and cleanup suggestions for stale or large files. It returns metadata only and cannot read, move, or delete files.

Reads and searches local email archives (.mbox or .eml) with full MIME parsing, enabling queries about senders, subjects, dates, and bodies while keeping all data on your machine.

Searches and browses local Claude Code and Cowork session histories stored on your machine, enabling questions about past work without uploading data.

MCP server that exposes agent-memory-daemon to any MCP-compatible client — Kiro (CLI & IDE), Claude Desktop, Cursor, and others. The daemon does the thinking (consolidation + extraction); this server is a thin filesystem bridge so agents can read, append, and search memory through the Model Context Protocol.

Enables users to access local files, manage persistent notes via CRUD, fetch URLs, inspect system information, and analyze or transform text through MCP tools.

Runs as an MCP server providing file system operations, shell execution, and system information tools, allowing Claude or any MCP client to edit files and control the machine.

Enables saving AI conversation histories as clean, organized markdown notes with automatic filtering of thinking processes and tool execution details, timestamping, and customizable conversation turn limits.

A general-purpose MCP server that provides utility tools for echo, date/time, and file operations within Claude Code and Claude Desktop. It functions as an extensible framework designed to help developers easily build and register custom Python-based tools.

Enables MCP clients to search, read, and record reviewed conclusions from policy-gated allowlisted files, with sanitized chunks and create-only drafts or append-only lessons, without granting general filesystem or execution access. It supports lexical ranking and optional loopback embeddings while rejecting likely credentials and raw challenge flags.

Enables storing durable AI memories linked to local JSON or text sources, automatically superseding outdated structured values, flagging ambiguous changes for review, excluding expired information, and preserving revision history in a local SQLite database.

A minimal server that provides Claude AI with secure file system access and sequential thinking capabilities, allowing Claude to navigate directories, read files, and break down complex problems into structured thinking steps.

A read-only MCP server that lets local AI agents inspect open Mac windows, browser tabs, PDFs, clipboard contents, Finder selections, and Messages history so they can answer questions about what the user is currently viewing.

Enables Claude to read and analyze project schedule files in OmniPlan (.oplx) and Microsoft Project (.mpp) formats, answering questions about tasks, milestones, resources, and progress.

MCP server that allows AI agents to read, search, summarize, and answer questions about local PDF, DOCX, XLSX, and TXT files through five tools.

Enables natural-language queries about disk usage by driving WizTree scans and analyzing cached CSV snapshots. Users can find large files, duplicate data, folder breakdowns, and more without repeatedly rescanning the disk.

Enables users to read Moodle course information, list courses, outlines, resources, assignments, and deadlines, and download or extract text from course files locally via an MCP-compatible client.

Enables web AI agents to operate local projects through MCP, with real-time display of the actual model name and thinking effort.

Enables an AI assistant to read and write a local, file-based .emd document through shaped tools — 28 for any document, 85 with the ledger pack — rather than a general query, with every write a dry run until committed, a copy kept beside the document first, and values that break a declared type or rule refused as they are written. On hosts that support MCP Apps it also draws sheets, boards and roadmaps directly in the conversation, falling back to text elsewhere.

A persistent SQLite-backed storage server that enables Cursor IDE's AI assistant to remember information across sessions with global or project-specific scopes. It supports complete CRUD operations, tag-based organization, and keyword search to manage user preferences and context effectively.

Converts CAD drawings (DXF/DWG) into structured data, enabling Claude to read drawings and answer questions about their content.

A TypeScript MCP server example providing basic developer tools: hello world greeting, arithmetic calculator, and file information retrieval.

Enables exporting Claude Code chat sessions to Markdown, HTML, or JSON, including full details such as thinking blocks, tool calls, diffs, and subagents, with optional secret redaction.

Connects AI assistants and IDEs such as Claude Desktop, Claude Code, Cursor, Windsurf and Codex to a local long-term memory store of plain-text .dai files on disk. Enables saving and recalling conversation history through the save_memory and recall_memory tools, with the store readable by any model, editor, or grep and using about a tenth of the tokens.

Enables Claude to perform file operations, retrieve system information, run calculations, and generate timestamps on the local system.

Exposes system tools (disk usage, file listing) and weather information via Open-Meteo to MCP-compatible LLMs.

This server converts PDFs to markdown with intelligent academic paper detection and dual processing engines (marker-pdf for academic content, PyMuPDF for general documents), supporting URL and local file handling, page extraction, batch processing, and PDF link crawling for Claude Code analysis.

An MCP server for GitHub Copilot that enables reading and processing Excel workbooks (.xlsx) via Docker Compose. Users can extract data from entire workbooks or specific sheets by name or index, returning the information in JSON format.

Enables AI applications to convert local text PDFs or saved HTML files into clean Markdown with tables kept as real Markdown tables through the convert_to_markdown tool.

An MCP server for local PDF inspection that classifies, searches, extracts text and tables without uploading documents or relying on OCR, surfacing reliability warnings for garbled or scanned content.