agentvc MCP server
Commit Nov 2, 2026Provides version control for AI coding agents to checkpoint, branch, diff, and rollback workspace states during autonomous tasks.
Also known as nintechio/agentvc
- Stars
- 0
- Tools
- 8
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 2, 2026
- License
- MIT
What is agentvc MCP?
agentvc provides version control for AI coding agents to checkpoint, branch, diff, and rollback workspace states during autonomous tasks. It exposes 8 tools, such as avc_save, avc_status, avc_log.
Summary generated from the project's README
About agentvc MCP server
Providing a time machine for AI coding agents is what agentvc enables by offering version control designed for machine-speed workspace mutations. It allows developers to protect their projects from accidental deletions or failed refactors by creating instant, content-addressed checkpoints. Unlike standard Git, which is built for human pacing, this tool handles dozens of file changes per minute and ensures that every rollback is lossless by automatically saving the current state before restoring a previous one.
Developers can integrate this via an MCP server with clients like Claude Code, Cursor, or Codex. It provides eight specific tools including avc_save, avc_rollback, and avc_branch to manage workspace states. The system runs locally within a .avc directory, ensuring privacy with no cloud telemetry or external daemons required. It also supports automated workflows through a file watcher or hooks that trigger checkpoints after every agent turn.
What you can do with it
- 1Undo accidental file deletionsAn AI agent can instantly restore a workspace to a known-good state if it deletes important files during a task.
- 2Test parallel coding approachesA developer can instruct an agent to fork the current session into a new branch to try a different implementation strategy.
- 3Automate session safety checkpointsYou can configure the system to automatically save the workspace state after every turn an agent makes.
- 4Review agent changes with diffsDevelopers can inspect exactly which lines of code an agent modified between two specific points in time.
Written from the project's README. Every use case is checked against a quote from it.
agentvc MCP tools 8
Detected from the READMEavc_saveavc_statusavc_logavc_branchavc_switchavc_rollbackavc_diffavc_timeline
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablenintechio/agentvc is public and reachablegithub.com/nintechio/agentvc ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-02github.com/nintechio/agentvc ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model8 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubWhy agentvc
Git was built for humans committing at human pace. AI agents mutate your workspace at machine pace: dozens of files per minute, wrong turns, half-finished refactors, deletions you never asked for. By the time you notice, git stash isn't going to save you.
agentvc gives every agent session a time machine. It snapshots the entire workspace in milliseconds, forks parallel attempts onto branches, and restores any previous state instantly — with zero data loss by design.
Features
| ⏱ Instant checkpoints | Snapshot every file with one command or one tool call. Content-addressed, deduplicated, milliseconds. |
| ↩ Lossless rollback | Every restore auto-saves your current state first. Rolling back is itself reversible. |
| ⑃ Parallel attempts | Branch the session, try approach B, compare, keep the winner. |
| 🤖 MCP-native | 8 tools so Claude Code, Cursor, and Codex checkpoint and recover themselves. |
| ⚡ Auto-save | avc watch checkpoints whenever files go quiet; avc hook claude checkpoints after every agent turn. |
| 🔍 Real diffs | See exactly what the agent touched between any two points in time — down to the line with avc diff -p. |
| 🔒 Local & private | Everything lives in .avc/. No daemon, no cloud, no telemetry. |
Why not just git?
| git | agentvc | |
|---|---|---|
| Designed for | human commits | machine-speed agent steps |
| Staging dance | add / commit required |
one command captures everything |
| Rollback safety | checkout can destroy uncommitted work |
auto safety-checkpoint before every restore |
| "Try another approach" | heavyweight branching, easy to tangle | one tool call — agents do it themselves |
| Agent interface | none | first-class MCP server + TypeScript API |
| Per-step metadata | manual notes | structured JSON (task, attempt, model, tokens) |
agentvc doesn't replace git for shipping code. It sits underneath the agent loop: cheap, disposable, rewindable history that never pollutes your git log.
Requirements
Node.js 20 or newer. No other runtime dependencies.
Install
npm install -g agentvc
Or run it without installing:
npx agentvc init
Quickstart
mkdir demo && cd demo
avc init # initialise .avc/
echo "v1" > app.txt
avc save -m "known good state" # checkpoint everything
echo "v2" > app.txt # ...agent goes wrong...
avc status # see what changed
avc diff -p # see exactly which lines changed
avc rollback HEAD # instant undo — nothing lost
avc branch plan-b && avc switch plan-b # fork a parallel attempt
avc save -m "trying redis instead"
avc timeline # every attempt, side by side
Give your agent a time machine
Register the bundled MCP server once and your agent can checkpoint and recover on its own.
Claude Code
claude mcp add agentvc -- avc mcp
Cursor · Codex · any MCP client — add to .mcp.json (or see examples/mcp-config.json):
{
"mcpServers": {
"agentvc": { "command": "avc", "args": ["mcp"] }
}
}
Set AVC_ROOT=/path/to/project if the server shouldn't use its working directory.
Checkpoint automatically
You don't have to rely on the agent remembering. Pick one (or both):
avc hook claude --install # Claude Code: checkpoint after every agent turn
avc hook claude --install --on-edit # ...and after every Edit/Write tool call
avc watch # any agent: checkpoint whenever files stop changing for 2s
avc hook claude merges a Stop hook running avc save --auto into .claude/settings.json
(re-running it is a no-op). avc save --auto only writes a checkpoint when something actually
changed, so history never fills with duplicates; avc log --no-auto hides automatic entries.
Other agents can call the same command from their own hook or post-turn script.
Teach it when to checkpoint
Even with hooks on, a short note in your AGENTS.md / CLAUDE.md makes checkpoints meaningful
rather than merely frequent:
## Session checkpoints (agentvc)
- Before any risky operation (refactors, deletions, dependency upgrades,
schema changes), call `avc_save` with a short message.
- After reaching a working state, call `avc_save` again.
- If an approach fails twice, call `avc_rollback` to the last good checkpoint
and try a different plan — optionally on a new branch via `avc_branch`.
- Never leave more than ~15 minutes of work uncheckpointed.
MCP tools
| Tool | What the agent uses it for |
|---|---|
avc_save |
Snapshot the workspace before risky work or after success (only_if_changed skips duplicates) |
avc_status |
Check what's changed since the last checkpoint |
avc_log |
Review recent checkpoints on the current branch |
avc_branch |
Fork a parallel attempt without losing the current one |
avc_switch |
Move between attempts (auto-saves unsaved work first) |
avc_rollback |
Restore all files to a known-good checkpoint |
avc_diff |
Compare any two points in time, optionally with line-level patches (patch: true) |
avc_timeline |
See every attempt across all branches |
CLI reference
| Command | Description |
|---|---|
avc init |
Initialise a repository in the current directory |
avc save [-m msg] [--meta json] |
Checkpoint the whole workspace |
avc save --auto |
Checkpoint only if something changed, tagged as automatic (for hooks) |
avc watch [-d ms] |
Keep running; auto-checkpoint after files stop changing |
avc hook claude [--install] [--on-edit] |
Print or install Claude Code hooks that run avc save --auto |
avc status |
Show unsaved changes since the last checkpoint |
avc log [-n N] [--no-auto] |
List checkpoints on the current branch |
avc branch [name] [start] |
Create or list branches |
avc switch <branch> |
Switch branches, restoring files |
avc rollback [ref] |
Restore files to a checkpoint (default HEAD) |
avc diff [from] [to] |
Compare refs, or a ref against the working tree |
avc diff -p [-U n] [from] [to] |
Same, as a unified diff with n lines of context (default 3) |
avc timeline |
Every checkpoint across every branch |
avc mcp |
Start the MCP stdio server |
Refs accept HEAD, a branch name, a full checkpoint id, or any unique id prefix.
avc diff -p prints standard unified diffs (--- a/path, +++ b/path, @@ hunks), so the
output pipes straight into patch -p1 or git apply. Binary files are reported as
Binary files … differ; files over 2 MB / 50,000 lines are listed without contents, and
rewrites too large for an exact line diff are shown as a whole-file replacement.
Use it as a library
import { AgentVCS, formatPatch } from "agentvc";
const avc = new AgentVCS(projectRoot);
await avc.ensureInit();
const cp = await avc.save({
message: "before db migration",
meta: { task: "upgrade-postgres", attempt: 2 },
});
const { clean, modified } = await avc.status();
if (!clean) console.log("agent touched:", modified);
await avc.branch("plan-b");
await avc.checkout("plan-b");
await avc.rollback(cp.id); // instant, lossless
for (const p of await avc.diffPatch(cp.id, "work")) {
console.log(formatPatch(p)); // unified diff per file, with hunks available on p.hunks
}
Fully typed. AgentVCS, watchWorkspace, diffTrees, computePatch, formatPatch, and all result types are exported.
How it works
Content-addressed storage, git's good idea without git's ceremony:
.avc/
├── objects/ab/c3ef… blobs + trees, deduplicated by SHA-256
├── checkpoints/ parents, tree, message, structured meta
├── refs/heads/main branch tips
└── index.json id → summary, for fast prefix lookups
- Identical file content is stored once, across every checkpoint and branch.
- Unchanged files are never rewritten on restore.
- Your existing
.gitignoreis respected;.git/andnode_modules/are skipped. - Delete
.avc/and your workspace is untouched.
[!IMPORTANT] The safety guarantee. Every
rollbackandswitchsnapshots your unsaved changes into an automatic safety checkpoint before touching a single file. Rolling back is reversible. There is no code path in agentvc that can lose your work.
Roadmap
- Line-level diffs in the terminal (
avc diff -p) - Branch merging (fast-forward today, 3-way next)
- Auto-save hooks: on file watcher, or after each agent turn
- Multi-agent coordination — two agents, one repo, separate branches
- Named milestones and session tags
- Python SDK with MCP parity
- Optional encrypted remote backup of the checkpoint store
Ideas and PRs welcome — see CONTRIBUTING.md.
Contributing
git clone https://github.com/nintechio/agentvc.git
cd agentvc && npm install
npm run typecheck && npm test && npm run build
Bug reports, feature requests, and pull requests are all welcome. Please read CONTRIBUTING.md and our Code of Conduct. Security issues: see SECURITY.md.
License
Built and maintained by Nintech
The engineers who build it also run it.
Applied AI · resilient software engineering · managed hosting — UK & EU
nintech.io · GitHub · X · YouTube · admin@nintech.io
agentvc MCP questions
What tools does agentvc MCP provide?
It exposes 8 tools, including avc_save, avc_status, avc_log, avc_branch, avc_switch.
How does agentvc differ from Git?
While Git is designed for human-paced commits, agentvc is built for machine-speed agent steps, offering instant snapshots, automatic safety-checkpoints before restores, and first-class MCP integration.
Is my data safe when rolling back?
Yes, agentvc is designed to be lossless; every rollback or switch automatically saves your current state as a safety checkpoint first.
Can I use agentvc with Claude Code?
Yes, you can register the MCP server to allow Claude Code to checkpoint and recover itself automatically.