Log inSubmit server
AVCS logo

AVCS

Experimental Git-incompatible version control for AI agents, using operation graphs, evidence, policies, and recorded decisions.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install AVCS

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "avcs": {
      "command": "npx",
      "args": [
        "-y",
        "@izagood/avcs"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @izagood/avcs

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 2d ago.

Overview

AVCS MCP server gives AI agents access to an agent-oriented version-control model built around intents, sessions, operations, evidence, and decisions. It computes the working tree by reducing an append-only operation graph with a policy and materializer, rather than storing commits and resolving merges with conflict markers. Reach for it when multiple humans or agents need concurrent changes with provenance, evidence gates, deterministic merging, and durable conflict rationale.

Use cases

  • Coordinate concurrent edits by humans and AI agents
  • Record evidence for behavior-changing operations
  • Resolve overlapping edits with durable decisions
  • Build agent context from intent and operation history

Key features

  • Operation-graph version history
  • Intent, evidence, and decision objects
  • Deterministic policy-based reduction
  • Evidence-gated changes
  • Recorded conflict rationale
  • MCP core profile with 13 tools

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

5/5 checks healthy over the last 42d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 14d ago via OSV.dev · @izagood/avcs (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads1.1kPackage downloads in the last 30 days.
Last commit23d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How AVCS works

What the AVCS MCP server does

The AVCS MCP server exposes an agent-oriented version-control system through MCP. AVCS is designed for humans and AI agents that edit the same codebase concurrently. It does not present Git’s commit, branch, merge, and conflict-marker model as its primary abstraction. Instead, work is represented by content-addressed objects, including intents, sessions, operations, evidence, decisions, checkpoints, views, releases, and policies.

The central record is an operation graph. An operation describes a semantic change, while an intent carries the goal, constraints, and permitted scope. Sessions connect work episodes to intents. Evidence records machine-checkable results such as tests, type checks, linting, or scans. Decisions preserve the rationale for conflict resolution or design choices instead of leaving only the resulting bytes.

How it works

AVCS derives a code tree from a base state, an operation DAG, decisions, a policy, and a materializer. Identical inputs produce the same projected tree on each replica. Merging is therefore a deterministic reduction rather than a text-selection step.

The policy grades concurrent work. Changes to different entities or disjoint line regions can be merged automatically. Overlapping edits can produce a policy decision that is recorded in the history. Behavior changes without trusted evidence can be blocked, and public-API breaks require a human decision routed to the relevant owners. Code does not default to last-write-wins.

The AVCS MCP server is intended to reduce the version-control context an agent must consume. A stale-head change can be absorbed without a branch rebase, and a same-line collision becomes a decision object rather than conflict markers. The project describes itself as Git-incompatible, although Git bridge documentation exists for interoperability scenarios.

Tools and capabilities

Through MCP, the server provides an agent-facing surface for working with AVCS objects and repository state.

Supported concepts include:

  • Recording and working with intents, sessions, operations, evidence, and decisions.
  • Building agent context from the operation history and intent.
  • Applying deterministic policy-based reduction to concurrent operations.
  • Preserving conflict rationale as signed or recorded decision data.
  • Using checkpoints, views, releases, and policies as version-control objects.
  • Applying evidence gates so untrusted or insufficiently supported changes can be blocked.

Limitations and notes

AVCS is explicitly marked experimental and described as a research prototype. The current implementation reaches working-MVP depth for language-neutral text three-way merge and Ed25519 signing. Structure-aware merge, semantic-break detection, multi-signature trust, and hardened distributed synchronization are listed as future roadmap work.

The system is deliberately Git-incompatible at its core, so existing Git workflows should not be assumed to transfer directly.

Evidence trust is significant: an operation’s author cannot independently vouch for its own evidence. The evidence gate and passing-test bonus require evidence from a trusted, non-authoring actor such as CI or a human. The AVCS MCP server should therefore be evaluated alongside the project’s trust, policy, and collaboration requirements rather than treated as a drop-in Git replacement.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about AVCS

AVCS is an MCP server that connects AI agents to the AVCS agentic version-control system and its operation graph. Its main tools work with intents, sessions, operations, evidence, decisions, and projected repository state, helping agents coordinate concurrent changes, apply policy-based reduction, and preserve conflict rationale without relying on Git-style conflict markers.

Consult the AVCS repository’s install and agent-connection documentation for the supported setup steps.

Check the repository’s MCP connection instructions before selecting a client.

AVCS is not a drop-in Git replacement because it uses a deliberately Git-incompatible object and reduction model.

AVCS handles conflicts through policy-based reduction and recorded decision objects rather than conflict markers. Disjoint changes can auto-merge, overlapping edits can receive a policy decision, unsupported behavior changes can be blocked, and public-API breaks require a human decision.

Related MCP servers

All in Version Control All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAVCS AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/avcs?style=directory)](https://allmcps.com/mcp/avcs)
HTML Embed
<a href="https://allmcps.com/mcp/avcs"><img src="https://allmcps.com/api/badge/avcs?style=directory" alt="AVCS on AllMCPs" /></a>