MultiSAFE
Multi-Model chat, code review and analysis MCP Server for Claude Code
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/religa/multimcp/actions) [](https://pypi.org/project/multi-mcp/) [](https://pepy.tech/project/multi-mcp) [](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) [](https://github.com/religa/multimcp/stargazers)
A multi-model AI orchestration MCP server for automated code review and LLM-powered analysis. Multi-MCP integrates with Claude Code CLI and OpenCode to orchestrate multiple AI models (OpenAI GPT, Anthropic Claude, Google Gemini) for code quality checks, security analysis (OWASP Top 10), and multi-agent consensus. Built on the Model Context Protocol (MCP), this tool enables Python developers and DevOps teams to automate code reviews with AI-powered insights directly in their development workflow.
Features
- 🔍 Code Review - Systematic workflow with OWASP Top 10 security checks and performance analysis
- 💬 Chat - Interactive development assistance with repository context awareness
- 🔄 Compare - Parallel multi-model analysis for architectural decisions
- 🎭 Debate - Multi-agent consensus workflow (independent answers + critique)
- 🤖 Multi-Model Support - OpenAI GPT, Anthropic Claude, Google Gemini, and OpenRouter
- 🖥️ CLI & API Models - Mix CLI-based (Gemini CLI, Codex CLI) and API models
- 🏷️ Model Aliases - Use short names like
mini,sonnet,
a14781722374OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add multi-mcp --env OPENAI_API_KEY=${OPENAI_API_KEY} --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env GEMINI_API_KEY=${GEMINI_API_KEY} --env OPENROUTER_API_KEY=${OPENROUTER_API_KEY} -- None multi-mcp==0.1.1Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (13)
.coveragerc
module = importlib.import_module(module_path)
self._plugins[name] = importlib.import_module(module_name)
exec(f"local_value = {raw}", {}, local)hash_val = int(hashlib.md5(str(user_id).encode()).hexdigest(), 16)
@ln -sf ../../.githooks/pre-commit .git/hooks/pre-commit
monkeypatch.setenv("ARTIFACTS_DIR", "../../../tmp")escape_path = "../../../etc/passwd"
"../../../etc/passwd",
You are a Senior Technical Guide, Codebase Expert, Pragmatic Architecture Partner and Collaborative Brainstorming Partner. Your mission is to navigate the codebase, debug complex issues, validate idea
You are a Principal Engineer serving as a strict Quality Gate. Your responsibility is to evaluate code with architectural depth and static analysis precision. You must verify reported issues, uncover
You are a Senior Technical Expert, Codebase Analyst, and Pragmatic Solution Architect participating in multi-model comparison analysis. Your mission is to provide clear, evidence-backed answers that d
Gates applied: no_behavioural_pass.
a14781722374full audit observations/trust-audit/mcp-server/religa__multi-4.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | a14781722374 | SAFE | B | 89 | first audit |
Questions
What is the Multi MCP server?
Multi-Model chat, code review and analysis MCP Server for Claude Code
Is Multi safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Multi need?
It reads ANTHROPIC_API_KEY, AZURE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, TEST_KEY_OVERRIDE and TEST_KEY_PRECEDENCE from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Multi run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as multi-mcp.
How current is this page?
The grade is for one exact copy of the source (a14781722374), read on 2026-10-08. The repository is watched and re-audited when it changes.