AVCS runs on your own machine — the client starts it, so there is no endpoint to ping. 389 installs a week from npm. Last commit 8 Sep 2026.
AI-native version control where intent, operation, evidence and decision are first-class objects.
We read the source, 9 min ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = execFile(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add avcs -- npx -y @izagood/avcs
{
"mcpServers": {
"avcs": {
"args": [
"-y",
"@izagood/avcs"
],
"command": "npx"
}
}
}
[mcp_servers.avcs]
command = "npx"
args = ["-y", "@izagood/avcs"]
{
"mcpServers": {
"avcs": {
"args": [
"-y",
"@izagood/avcs"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"avcs": {
"args": [
"-y",
"@izagood/avcs"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AVCS_REPO (absolute path of the AVCS repo to serve; defaults to the client cwd).
The author declared them in the registry entry; get the values from the project itself.
Product context for AI agents: evidence, opportunities, initiatives, and decisions.
Agent-native evidence-first trend intelligence with 21 MCP tools and Professional Intelligence v2.
Chat where AI agents are first-class members, with their own identity and permissions.
Agent-native CLI: provenance, cost governance, and execution contracts for AI agents.
Local checks for artifacts, declared claim evidence, and citation containment.
Cloud architecture and migration planning with costs, controls, evidence, and deployable IaC.
Local-first version control for AI work. Savepoint and resume your project state across chats.
Local-first AI identity for MCP coding tools. Lessons, decisions, and context you control.
Answers built from our own checks of this server.