MCP SERVERRuns your code past several AI models at once and sorts the findings by how many agreed — unanimous, majority, disagreement, or caught by one model only.
LABSCO SUMMARY
A single model misses things and also invents them; four of them agreeing on a SQL injection is a much stronger signal than one of them saying so. Cost scales with the size of the council, so check list_review_config before pointing it at a large diff, and use review_plan first — catching the problem in the plan is cheaper than catching it in the review.
A multi-model review server. Each review fans out to several models through OpenRouter and comes back as a consensus report rather than one opinion.
An OpenRouter API key in OPENROUTER_API_KEY — every review calls several models through OpenRouter, so it costs whatever those models cost. Run it over stdio with npx -y @klitchevo/code-council. The same package doubles as a CLI for CI use and can generate a GitHub Actions workflow that posts findings as inline PR comments with one-click fix suggestions.
One command plus a key — npm install -g @klitchevo/code-council, then supply credentials
USE CASES
Point the council at the staged diff and read the findings by consensus level.
Put the implementation plan in front of the council first.
Send the code with its language and context and see where the models diverge.
Use the backend review, which weights security and architecture concerns.
Audit the repository for flow and bottlenecks and read the HTML report it produces.
Open a discussion, then keep going with the session ID as each model holds its own thread.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
discuss_with_councilStart or continue a multi-turn discussion with the AI council. First call (without session_id) starts a new discussion and returns a session_id. Subsequent calls with the session_id continue the conversation. Each model maintains its own conversation history for authentic perspectives.
init_configGenerate a Code Council configuration file with default values. Creates a TypeScript or JavaScript config file with model settings, consensus options, and LLM parameters.
list_review_configShow current model configuration
review_backendReview backend code for security, performance, architecture, and best practices using multiple AI models in parallel
review_codeReview code for quality, bugs, performance, and security issues using multiple AI models in parallel
review_frontendReview frontend code for accessibility, performance, UX, and best practices using multiple AI models in parallel
review_git_changesReview git changes (staged, unstaged, diff, or specific commit) using multiple AI models in parallel
review_planReview implementation plans BEFORE coding to catch issues early using multiple AI models in parallel
tps_auditToyota Production System audit - analyze a codebase for flow, waste, bottlenecks, and quality. Scans the repository, identifies entry points, maps data flow, and provides actionable recommendations. Outputs interactive HTML report by default, or markdown/JSON.
BEFORE YOU INSTALL
9 tools when we connected.
All 4 documented setups run the server on your machine.
CONTEXT COST
Rated by the size of the 9 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npm install -g @klitchevo/code-council{
"mcpServers": {
"code-council": {
"command": "npx",
"args": [
"-y",
"@klitchevo/code-council"
],
"env": {
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}{
"mcpServers": {
"code-council": {
"command": "code-council",
"env": {
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}MCP servers
YuChenSSR
nesquikm
BeehiveInnovations
heltonteixeira