"How to modify local files" matching MCP servers:

A local, read-only stdio MCP server that lets a Grok Build CLI agent check how much of its weekly SuperGrok / Grok Build usage pool is left, when the period resets, and its Extra Usage cap via tools like get_budget. It reads the existing grok login session and returns per-product figures as JSON, mirroring the TUI /usage screen, so agents can pause before expensive work when quota runs low.

Enables Claude to fetch web pages from the user's own local network connection instead of AI datacenter IPs, including optional authenticated sessions, with verdicts for bot challenges, login walls, and other failures.

Evaluates task suitability for local models before cloud API calls, routing to Ollama or similar to reduce costs.

A thin MCP server that delegates lightweight tasks from Claude Code or any MCP-compatible client to local or cloud LLMs via LiteLLM, supporting models like Ollama and cloud APIs as subagents.

A local MCP server that lets Claude Code orchestrate Codex CLI and OpenCode CLI as sub-agents with strict security, concurrency, and output limits.

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 web ChatGPT to drive durable, sandboxed Claude Code sessions on a local Mac, with controlled read, modify, verify, and recover operations via six session control tools.

MCP server that lets you drive Claude Code sessions hands-free by voice from any MCP client, enabling remote models to send prompts, monitor progress, and get results read back.

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

MCP server that delegates Claude Code subagents to alternative backends such as local models, DeepSeek, or AWS Bedrock, while keeping your Claude Code orchestrator session intact.

AutoVault is an MCP server that provides a local-first vault for AI agent skills, enabling validation, signing, and serving of SKILL.md files to agents through stdio or HTTP.

Enables routing tasks to the right specialist agents, assembling the needed context from a layered catalog of agents, skills, knowledge, runbooks, topics, tools, and connectors, while remembering how a business wants work done.

A Model Context Protocol server that provides AI agents with secure access to local filesystem operations, enabling reading, writing, and managing files through a standardized interface.

Enables AI agent hosts to exchange durable, local sender/receiver messages through a SQLite mailbox exposed as MCP tools (connect, send, receive, reply, ack, status, disconnect), so a coordinator can dispatch commands and an executor can return results without model polling while idle. A configured host wake adapter is still required to turn an incoming event into an Agent turn.

Provides safe local-model MCP support tools (summarization, classification, critique, draft) for a cloud owner agent, with strict boundary guards to prevent risky actions.

Teach any AI agent how you use an MCP server – Soft-Landing to your AI integrations

Enables direct MCP-based pairing with T3 Code environments, allowing users to manage environments and projects, start and continue turns, and inspect thread history over stdio without requiring T3 Connect or a local turn CLI.

Enables a cloud orchestrator to query a local Ollama model over Tailscale or a LAN as a side-channel for drafts, summaries, and other helper output, with tools to list available models and to redact text. Answers leaving the server are passed through output-only DLP that masks card numbers, IBANs, emails, phone numbers, API keys, and similar secrets before they reach the cloud.

MCP server that routes Claude Desktop chat into Claude Code, enabling headless execution and terminal handoff with session continuity.

Verbatim context compaction for coding agents. Moves spent tool outputs to a local hash-checked stash the agent can recall, keeps every message byte for byte, and writes a JSON report of each cut. Offline, no API key. Tools: compact, compact_transcript, recall, inspect, prepare, explain, intake.