"File system requirements: mounted directory, persistent state, and full R/W access" matching MCP servers:

Provides secure file read and write operations within a sandboxed directory, allowing AI assistants to safely create, modify, and access files without risk of accessing the broader file system.

Provides full access to a local Windows computer via MCP, enabling arbitrary command execution, file operations, and process management through a secure stdio or HTTP tunnel.

Pre-trade risk validation and position sizing for AI trading agents via G-formula and Iron Fist.

A comprehensive MCP (Model Context Protocol) server for file system operations, providing Claude and other AI assistants with access to local files and directories.

A secure, sandboxed file system server that enables reading, writing, searching, and managing files through MCP-compatible AI clients with path traversal protection and size limits.

An agentic file-system assistant that lets users read, write, list, and search local files through natural language, using a LangChain agent with an Ollama LLM backed by a FastMCP server.

Provides a read-only interface to audit and continue coding agent sessions by extracting plans, intents, and edit authorship from history across multiple agents (Claude, Codex, OpenCode, Antigravity, Pi) via MCP, CLI, and Python SDK.

econ-r-mcp is a local MCP server plus companion skill for reproducible applied econometrics and statistics workflows powered by headless R execution.

Enables AI assistants to execute R code, create visualizations, analyze data, and manage packages through a local Rscript CLI.

MCP server for querying a cross-referenced directory of evidence-based therapies and interventions, enabling search by query, tier, problem, population, modality, and registry.

Enables MCP clients to read, search, and manage a Yahoo Mail mailbox over IMAP and send or forward messages over SMTP, with multiple accounts selectable per call and writes defaulting to drafts, trash, or dry-runs until explicitly confirmed.

Enables management of software requirements in compliance with IEC 62304 Class C medical device standards, including requirement creation, versioning, traceability matrix generation, and risk control integration.

Provides state and log management tools designed for long-lived AI agents that may be interrupted and resumed. It enables tracking agent progress and maintaining an append-only event history to ensure continuity across multiple sessions.

Full-featured Notion MCP server enabling deep page reading, block editing, snapshot/restore, file uploads, table manipulation, page restore, and destructive page copying.

Provides full control over the locally-hosted Voicebox TTS/voice-cloning app, exposing 102 tools for speech generation, voice cloning, audio project management, and system operations.

Provides read-only, source-attributed access to current CRAN and Bioconductor package metadata, dependencies, function documentation, vignettes, and version compatibility checks for AI assistants. It also enables retrieval of official Shiny, Quarto, Positron, and visualization docs alongside static analysis of R, ggplot2, and Quarto source code without executing it.

A stateless MCP server for AI film and video production that tracks project state, shot status, and updates, enabling consistent characters and continuity across generative video tools.

A lightweight memory layer for MCP servers that persists user context across LLM sessions with minimal token cost, supporting key-value dedup, multi-tenant namespaces, and optional TTL.

Enables read-only querying of live brokerage state across Alpaca and Kraken, including account balances, positions, order history, and combined exposure summaries.

An MCP server that gives AI agents file system access: read, write, search, hash, directory trees — 12 tools, zero dependencies, pure Python stdlib.