AVCS MCP server

by izagood·io.github.izagood/avcs·v0.42.0·1 stars

No reviews yet

AI-native version control where intent, operation, evidence and decision are first-class objects.

A92/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A92/100

full report

Adoption

Growing

1 stars206 downloads/wk

Reviews

Write one

Nobody has reviewed AVCS yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

AVCS tools (39, 6 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

avcs.approval.record
Record a reviewer verdict on a checkpoint, signed with the reviewer's local key. Requires role >= reviewer.
avcs.blame
Who currently owns an entity (file:<path> or symbol:<path>#<name>) and WHY — the accepted head op with actor, intent title, and purpose. Stronger than git blame.
avcs.blame.lines
Per-line provenance: the op that last wrote each line, with actor, intent and purpose. Why THIS line is here.
avcs.checkpoint.createwrite action
Freeze a verified (ops + policy + materializer + evidence) state vector for a view.
avcs.conflict.list
List the conflicts that require a human/owner decision in a view.
avcs.contention.check
Other actors' live concurrent ops and overlapping lease holders for given keys. Run while editing, so overlap surfaces before finalize.
avcs.context.build
Assemble working context for a scope under a byte budget: provenance, decisions, risks, history. Deterministic truncation.
avcs.decision.recall
Prior human decisions for a conflict key plus the policies they taught. Read precedent before re-deciding.
avcs.decision.record
Record a human owner's conflict resolution. Owner-confirmed and signed with their local key; an agent cannot forge it.
avcs.diff
Diff two views/lines. format 'paths' (default) or 'patch' (unified diff).
avcs.evidence.attach
Attach machine-checkable evidence (test/typecheck/lint/...) to operations. Behavior changes need a passing test to be accepted.
avcs.governance.status
Read-only review state for a view: protection rules, head, your role, and the effective approvals.
avcs.guide
How to use AVCS: the canonical loop, agent rules, tool index, error recovery. Call this first.
avcs.history
History of one entity in causal order. Paged: limit (default 20) + cursor.
avcs.integration.status
Idempotent lookup of an integration ticket's recorded verdict on a remote hub (polling companion to avcs.integration.submit).
avcs.integration.submitwrite action
Submit a checkpoint to the integration queue. Verdict is advanced, conflict, needs_evidence or queued — never 'pull and redo'.
avcs.intent.createwrite action
Open an intent: the goal + constraints + allowed scopes for a unit of work. Agents must work within an intent.
avcs.intent.list
List intents in the repo. Bounded: limit (default 50).
avcs.intent.read
Read an intent (goal, constraints, allowed scopes). An agent should read this BEFORE proposing operations so it works within the constraints.
avcs.key.list
Which actors this machine can sign as, and which public keys the repo trusts. Ids only, never key material.
avcs.key.provision
Mint a local signing key for an actor so its decisions and hub writes can be signed. Idempotent.
avcs.lease.request
Request a soft write-lease over entity scopes BEFORE editing, to avoid duplicating another agent's in-flight work. Returns the lease oid, or the conflicting holders.
avcs.line.createwrite action
Fork a long-lived line (e.g. 'v1.x') from another at its current state. It inherits history to the fork, then diverges.
avcs.line.list
List the lineage lines in the repo (besides the implicit 'main').
avcs.metrics
In-process metrics snapshot for this server (reduce cache hit/miss, reduce.ms timing, materialize.calls).
avcs.object.show
Read an object by oid. Blobs return decoded content (utf8 text or base64); other types return the structured object.
avcs.operation.backport
Cherry-pick an operation onto another line: mints a new op carrying the change, with derivedFrom provenance. Source line untouched.
avcs.operation.propose
Propose a semantic change (MVP: file writes). Declare effects honestly — policy gates on them. baseText/baseBlobOid authors a 3-way-mergeable edit_file.
avcs.release.cut
Cut a release: a conflict-free checkpoint plus evidence, SBOM and artifact references. Refuses if the view has open conflicts.
avcs.repair.context
Minimal repair packet for ops whose validation failed: failing output, related decisions, a fix instruction. Cheaper than re-reading the repo.
avcs.session.start
Begin a work session for an agent/human against an intent. Returns a session id used on every operation.
avcs.sync.land
Land work on a protected head in one call: push, merge-check, checkpoint, integrate. Result is landed or a conflict packet.
avcs.sync.pull
Pull objects from the hub (conflict-free gossip). dryRun reports what would arrive without importing.
avcs.sync.push
Push local objects to the hub. Returns how many were accepted and how many the gate rejected.
avcs.validate.runwrite action
Run validation commands against a view and attach treeHash-bound evidence. Pass dir to reuse an existing build environment.
avcs.view.materialize
Reduce a view's operation graph into a tree, per-op status and open conflicts — how an agent checks that its work merges.
avcs.workspace.land
Land a workspace onto its base line: its isolated ops join the base view and merge there. Idempotent.
avcs.workspace.list
List this repo's workspaces: `workspaces` names them all, `landed` the subset joined onto the base view. The rest stay isolated.
avcs.workspace.projectwrite action
Write a view to a directory on disk, so build/test loops outside validate.run need no CLI.

Public scan report

scanner v0.1.10 · 2026-10-29 · same rubric, same numbers if you re-run it

no findings

Code scan85 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 5 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How AVCS compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 92/100; higher than 93% of 48,243 servers
Tools: 39; the typical server has 7
Tools that change things: 15%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 1; more than 65% of 28,706 servers
Downloads a week: 206; more than 75% of 12,306 servers with a package

What its tools let an agent do: 30 read · 9 change

Install AVCS in Claude Code, Cursor or VS Code

Runs npx -y @izagood/avcs on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add avcs -- npx -y @izagood/avcs

Add to Cursor

What the publisher says

From the AVCS repository's README, as published. We do not edit it. Read it on GitHub

AVCS — Agentic Version Control System

An AI-native version control system for humans and AI agents working concurrently.

An agent should not spend its context on version control. That is the whole design goal, and it is measured rather than asserted — here is what the same work costs an agent:

git's recovery cost tracks the size of the file — a conflict is bytes inside it, so the agent reads the whole module and writes the whole module back to change one line. AVCS's tracks the size of the change: a conflict is an object naming the two contending operations, so it stays flat as the file grows. There is also no branch to rewrite and nothing to force-push, which is why the round trips differ — and that is one cycle, repeated for every PR that merges ahead of yours. Across the file sizes measured the saving is 37–99%.

None of this is a compression trick bolted on afterwards. It falls out of storing the operation graph instead of snapshots: there is no rebase to perform, so there is nothing to re-read. Method, caveats and the harness that produced the rebase numbers: avcs-demo → what it costs an agent in tokens. The schema figures are the advertised MCP surface itself — 35 KB of JSON against 14 KB, at the usual ≈4 bytes per token.

Git records when the code changed.

AVCS records who changed it, with what intent, on what evidence, and through which conflict decisions the code reached its current state.

AVCS is a new, deliberately Git-incompatible version control system built for a world where humans and many AI agents edit the same codebase concurrently. It drops the commit / branch / merge / conflict-marker model and instead stores intent, session, operation, evidence, and decision as first-class objects. The code tree is not the source of truth — it is a projection computed by deterministically reducing the operation graph:

state = reduce(base, operationDAG, decisions, policy, materializer)

The same objects + the same policy + the same materializer produce the same tree on any replica. Merging is not text selection; it is a pure, deterministic reduction.

Status: research prototype. The implementation is real and test-covered, but every phase is built to a working-MVP depth (language-neutral text 3-way merge, ed25519 signing). Structure-aware merge, semantic-break detection, multi-signature trust, and hardened distributed sync are tracked on the roadmap.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

AVCS: common questions

Is AVCS MCP server safe?: Yes, by our scan: it is graded A (92/100). Read the AVCS safety report
How do I install AVCS?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does AVCS need an API key?: No secret keys are declared. It reads 1 setting from the environment.
Is AVCS maintained?: The last commit was 12 days ago (2026-10-24). The latest release is v0.42.0.
How does AVCS compare with other MCP servers?: safety score 92/100 (higher than 93% of 48,243 servers); tools 39 (the typical server has 7); tools that change things 15% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.