Peer Agents Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Peer Agents Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server that lets other AI coding tools (Codex, Claude, Cursor, etc.) call the Grok CLI and Antigravity CLI as peer reviewers and collaborators.
This server wraps the local grok and agy (Antigravity) CLIs behind a clean Model Context Protocol (MCP) interface.
Any MCP-capable agent can now:
The primary agent (Codex, Claude, etc.) stays in control. It simply delegates specific tasks to these peers when it wants a second (or different) opinion.
Instead of one model doing everything, your main coding agent can use Grok and Antigravity as peers:
Smart routing happens automatically based on the type of request.
| Tool | Purpose | Routed to |
|---|---|---|
peer_review_diff | Review a unified diff or patch | Grok (usually) |
peer_plan | Create an implementation plan | Grok |
peer_debug | Diagnose failures from logs/stack traces | Grok |
peer_verify | Check test/build output for safety | Grok |
peer_ask | General grounded Q&A | Antigravity |
peer_debate | Independently compare Plan A vs Plan B | Grok |
peer_turn | Continue a multi-turn peer session | Same peer |
peer_compare | Low-level side-by-side call to both CLIs | Both |
Additional session tools: peer_summarize, peer_transcript, peer_list_sessions, peer_reset, and peer_health.
All routed tools accept full file contents via the files parameter and diffs via diff. Never send summaries — send the actual content.
Codex, Claude, or any other MCP client connects to this server over stdio. Once connected, the agent can call the peer tools exactly like any other tool.
Typical flow:
peer_review_diff, peer_plan, peer_debug, etc.sessionId.peer_turn using that sessionId.This gives you persistent, contextual peer conversations without the primary agent having to manage CLI invocation itself.
grok CLI (or set GROK_COMMAND)agy CLI (Antigravity, or set ANTIGRAVITY_COMMAND)Both CLIs must be authenticated and working on your machine.
git clone https://github.com/Rakeen70210/peer-agents-mcp
cd peer-agents-mcp
npm install
npm run buildRun directly:
node dist/index.jsAdd it to your client's MCP servers config (example for a typical stdio setup):
{
"mcpServers": {
"peer-agents": {
"command": "node",
"args": ["/absolute/path/to/peer-agents-mcp/dist/index.js"],
"env": {
"GROK_COMMAND": "/home/you/.grok/bin/grok",
"ANTIGRAVITY_COMMAND": "/home/you/.local/bin/agy"
}
}
}
}GROK_COMMAND — path to grok binary (default: grok)ANTIGRAVITY_COMMAND — path to agy binary (default: agy)GROK_ARGS / ANTIGRAVITY_ARGS — JSON array of extra CLI argsPEER_AGENTS_STORAGE_DIR — where sessions are persisted (default: ~/.peer-agents/sessions)PEER_AGENTS_TURN_TIMEOUT_MS — per-turn timeout (default 120s for Grok, 300s for Antigravity)PEER_AGENTS_MAX_PROMPT_CHARS — safety limit on prompt sizeEach routed call returns a sessionId. Use peer_turn to continue the conversation:
Sessions are persisted to disk, so they survive across restarts of the MCP server.
MIT (or as specified in the repo).
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.