A state-reverting terminal MCP that gives AI agents an undo button for local file operations.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-chronoshell","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
<div align="center"> # 🛡️ mcp-chronoshell [](https://pypi.org/project/mcp-chronoshell/) [](https://pypi.org/project/mcp-chronoshell/) [](https://opensource.org/licenses/MIT) **The safety net for autonomous AI agents.** </div> `mcp-chronoshell` is a Model Context Protocol (MCP) server that grants AI agents the ability to execute terminal commands with a built-in "Undo Button." By utilizing hyper-fast, state-reverting snapshots, agents can safely write code, manipulate files, and run scripts without the risk of permanently breaking your local workspace. ## 🧠 How It Works: The Snapshot Architecture When an agent is connected to Chronoshell, it gains access to a safe execution loop. The server exposes three primary tools to the LLM: 1. 📸 **`run_safe_command` (The Executor):** Before executing a shell command, the server takes a millisecond-fast snapshot of the current working directory, ignoring heavy directories (e.g., `node_modules`, `.venv`, `.git`). 2. ⏪ **`revert_workspace` (The Undo Button):** If the command exits with an error or causes unintended side effects, the agent can call this tool to instantly roll the directory back to its exact previous state. 3. 🗑️ **`commit_workspace` (The Garbage Collector):** If the command succeeds and the agent validates the output, it calls this tool to clear the snapshot cache and save disk space. ## ✨ Core Optimizations & Safety * **Zero-Latency Backups:** Uses hardcoded blocklists and OS-level I/O optimizations to take snapshots in milliseconds, preventing the LLM from timing out. * **Concurrent Multi-Agent Safety:** Injects cryptographic UUIDs into snapshot IDs, guaranteeing race-condition safety when multiple agents invoke commands simultaneously. * **Smart Symlink Evasion:** Dynamically sniffs out an…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.