"How to work with local files" matching MCP servers:

Read selected local folders from ChatGPT on macOS, with per-folder read-only or read-write access and hash-checked, recoverable edits. Requires local installation and a private ChatGPT app. The Glama container is a synthetic evaluation demo; it does not connect to files on your Mac.

Demonstrates how to secure an MCP server with OAuth 2.1 using AWS Cognito, with support for dynamic client registration and client ID metadata documents.

Enables MCP-compatible AI assistants to list, inspect, read, search, and modify local files and directories within configured filesystem roots, with permission controls and optional read-only or deletion restrictions.

A secure MCP server that allows Claude to read and write local files on your machine with explicit approval gating for each access.

Enables ChatGPT Web Developer Mode to securely read, search, list, and edit files inside user-approved local folders, and optionally run approved developer commands on the user's Windows machine.

Enables read-only listing and reading of files in an Azure Files SMB share, enforcing each user's NTFS permissions per request.

Routes web requests from AI tools through Tor for anonymized fetching, with selective per-URL routing to bypass Tor-blocking sites.

An MCP server that enables AI agents to securely add secrets to .env files by prompting the user to input the value through a local masked dialog, ensuring the agent never sees the secret.

Lets AI agents check whether an EVM wallet address carries an EIP-7702 delegation across eight chains (Ethereum, Base, BNB Chain, Arbitrum, OP, Polygon, Gnosis, Unichain) and learn how to obtain a deeper paid report with delegate bytecode heuristics and risk levels. Read-only, never touching private keys or seed phrases.

MCP server that gates API calls to AI agents using proof-of-work (free) or Lightning payment (3 sats), providing challenge, verify, and status tools for per-call authentication without accounts.

Anonymizes documents via the Stript desktop app locally, ensuring personal data never enters the conversation. Provides tools to anonymize files and clipboard content, fetch results, and restore original values to local files.

Enables local SOC 2 compliance work by scanning Infrastructure-as-Code, mapping findings to SOC 2 Trust Services Criteria, explaining risks in plain English, and drafting audit-ready documents without uploading files.

Lets AI assistants work on sensitive files by reasoning over schemas and masked output while deterministic local code handles raw data, never exposing real values to the model.

Enables AI agents to investigate synthetic fraud cases by pulling transactions, running deterministic rules evaluations, pivoting across devices, and recording auditable case files with provenance.

A local-first MCP server that scores your codebase's Build Readiness by reading code and running tests on your machine, outputting a diligence-grade score and risk register without uploading your source.

Enforces mandatory human approval before LLM agents can edit files, create files, or execute shell commands, using session tokens and audit logging.

Registers a set of inert, tempting decoy tools with any MCP-capable client so that any call from a hijacked or prompt-injected agent instantly raises an alert with full attack context and a per-call trace token. Also plants worthless canary tokens in honeypot files that trigger zero-false-positive leak alerts when they surface in agent output, files, or outbound requests.

Enables cloud-based MCP clients to delegate privacy-sensitive or large-output tasks to a local LLM, returning sanitized placeholders or digested summaries so private data never leaves the user's network.

Verifies C2PA Content Credentials for local files or URLs and returns an LLM-ready verdict on trust, AI generation, and provenance.

Enables assistants to analyze files and URLs for malware by integrating with security services like VirusTotal and ANY.RUN, returning threat reports.

Provides local, secure access to Enpass password vaults via MCP. Enables unlocking vaults, listing entries, retrieving passwords, TOTP codes, and attachments, with optional write support.

Enables AI agents to obtain permission before acting and verify afterward against destination systems' own records, confirming whether the permitted work actually happened.

Runs a regular expression on real engines — JavaScript (V8), Python (CPython re), PCRE2 and RE2 — reporting each engine's own compile errors with positions, every match with its groups and named groups, replacement results, and where the engines disagree. It also detects catastrophic backtracking (ReDoS), naming the at-risk part of the pattern, generating an attack string, and timing how long each engine actually takes on it.

Enables AI agents to create cryptographically verifiable receipts of their delegated work, with capabilities for multi-party approval and offline verification.

A modular MCP server for analyzing PCAP files using protocol-specific analysis tools, enabling LLMs to read and analyze network packet captures from local paths or remote URLs.

Local-first MCP proxy with BM25 tool discovery, quarantine security, Docker isolation, OAuth support, activity logging, and web UI. Routes multiple upstream MCP servers through a single endpoint.

Enables local inspection and analysis of Wi-Fi PCAP and PCAPNG files through tools for loading captures, summarizing them, filtering packets, and dissecting packet details.

Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_file, redact_file and detokenize.

Enables AI agents to store and retrieve self-hosted memories over MCP (stdio or Streamable HTTP) using local embeddings that work fully offline. Writes are redacted before they hit storage and every read is recorded in an exportable, append-only audit log.

Enables Claude Code to work with personal data that stays on the local machine, running SQL, Python, and file/schema inspection in a sandboxed compute-to-data setup that returns only aggregates, schemas, synthetic fixtures, and pseudonymized results. Raw records, file names, and protected values never reach the Anthropic API, so Auto mode can stay hands-off.