PluginBench
MCP Server
Active
MIT

The High Council MCP Server

io.github.muad-yasin/the-high-council

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the The High Council MCP server?

Several models from different labs plan in a blind proposal, debate and review loop. Your own keys.

How to install The High Council

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • ANTHROPIC_API_KEY
    secret

    Your own Anthropic API key. Needed only by chains that seat Anthropic models.

  • OPENAI_API_KEY
    secret

    Your own OpenAI API key. Needed only by chains that seat OpenAI models.

  • GOOGLE_API_KEY
    secret

    Your own Google (Gemini) API key. Needed only by chains that seat Google (Gemini) models.

  • MISTRAL_API_KEY
    secret

    Your own Mistral API key. Needed only by chains that seat Mistral models.

  • DEEPSEEK_API_KEY
    secret

    Your own DeepSeek API key. Needed only by chains that seat DeepSeek models.

  • GROQ_API_KEY
    secret

    Your own Groq API key. Needed only by chains that seat Groq models.

  • TOGETHER_API_KEY
    secret

    Your own Together API key. Needed only by chains that seat Together models.

  • COHERE_API_KEY
    secret

    Your own Cohere API key. Needed only by chains that seat Cohere models.

  • OPENROUTER_API_KEY
    secret

    Your own OpenRouter API key. Needed only by chains that seat OpenRouter models.

  • ZAI_API_KEY
    secret

    Your own Z.ai API key. Needed only by chains that seat Z.ai models.

  • MAX_USD_PER_RUN

    Per-run spend ceiling in US dollars. The run stops before any stage that could pass it. Default 7.

  • COUNCIL_MAX_USD_LIMIT

    A hard per-run ceiling in US dollars that the MCP client cannot raise or remove (max_usd above it, or "none", is refused). Set it to the same value as MAX_USD_PER_RUN to lock the cap.

  • COUNCIL_WORKDIR

    Folder for task files and run output. Default: the directory the client starts the server in.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "the-high-council": {
      "command": "npx",
      "args": [
        "-y",
        "the-high-council",
        "--mcp"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "GOOGLE_API_KEY": "<YOUR_GOOGLE_API_KEY>",
        "MISTRAL_API_KEY": "<YOUR_MISTRAL_API_KEY>",
        "DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>",
        "GROQ_API_KEY": "<YOUR_GROQ_API_KEY>",
        "TOGETHER_API_KEY": "<YOUR_TOGETHER_API_KEY>",
        "COHERE_API_KEY": "<YOUR_COHERE_API_KEY>",
        "OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
        "ZAI_API_KEY": "<YOUR_ZAI_API_KEY>",
        "MAX_USD_PER_RUN": "<YOUR_MAX_USD_PER_RUN>",
        "COUNCIL_MAX_USD_LIMIT": "<YOUR_COUNCIL_MAX_USD_LIMIT>",
        "COUNCIL_WORKDIR": "<YOUR_COUNCIL_WORKDIR>"
      }
    }
  }
}

Related MCP servers

MCP server for Mudrex futures trading enabling AI agents to securely access data and risk tools.

View repository →

Recraft AI Image Generation MCP Server for AI coding agents

0
TypeScript
MIT
View repository →
DIdistil logo

distil

Maintained

Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.

1
Rust
View repository →

Signed Buildability Oracle for AI-for-science papers. ed25519 receipts, Wave proofs, divergence.

View repository →

Generate daily standup notes from git commits across multiple repositories with AI summaries.

5
JavaScript
MIT
View repository →

Secure local-first MCP server exposing ArcGIS Pro's ArcPy engine to Claude with 100 geoprocessing tools.

12
Python
Apache-2.0
View repository →