MCP Server
AVC includes a built-in Model Context Protocol server. Any agent that speaks MCP can call AVC’s commands as tools — no separate process to manage, no HTTP layer to configure.
Start the server
Section titled “Start the server”avc mcp serve # default pretty-printed outputavc mcp serve --compact # compact JSON for token-sensitive contextsThe server runs over stdio: it reads JSON-RPC 2.0 messages on stdin and writes responses on stdout. Agent frameworks spawn it as a subprocess.
Available tools
Section titled “Available tools”| Tool | Maps to |
|---|---|
avc_snapshot | avc snapshot |
avc_list | avc list |
avc_info | avc info |
avc_delete | avc delete |
avc_diff | avc diff |
avc_restore | avc restore |
avc_branch_create | avc branch create |
avc_branch_list | avc branch list |
avc_branch_switch | avc branch switch |
avc_branch_diff | avc branch diff |
avc_merge_preview | avc merge --preview |
avc_merge | avc merge |
avc_merge_abort | avc merge --abort |
avc_run_in_workspace | Run a shell command inside a branch workspace |
Each tool’s JSON Schema is published via tools/list so the agent can discover them programmatically.
Don’t configure it by hand
Section titled “Don’t configure it by hand”Use the one-shot setup instead:
avc init --skills claude-code,cursor,windsurf,genericThis writes the right config files for each framework into your project. See the per-framework guides:
Manual integration
Section titled “Manual integration”For custom agents not covered by --skills, here’s the minimal config snippet:
{ "mcpServers": { "avc": { "command": "avc", "args": ["mcp", "serve", "--compact"] } }}Drop that into whatever MCP config file your framework uses. Most frameworks (Claude Desktop, Cline, etc.) follow this convention.
When the agent should use each tool
Section titled “When the agent should use each tool”AVC ships agent skill files (e.g., .claude/skills/avc-snapshot/SKILL.md) that document when to call which tool. These are written by avc init --skills and serve as instructions to the agent — “always snapshot before risky changes”, “use branches for non-trivial refactors”, etc.
If you write your own agent, you can copy the skill files as a starting point for your prompt engineering.