mcpField
P
planetary-agents

planetary-agents

Local
github.com/gregcastro23Games & Entertainment0Updated 13w ago
Repository

About planetary-agents

Converse with planetary-agent personas, council feeds & culinary debates from alchm.kitchen

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "gregcastro23-planetary-agents": {
      "command": "uvx",
      "args": [
        "alchm-planetary-agents-mcp"
      ],
      "env": {
        "PLANETARY_AGENTS_BACKEND_URL": "<PLANETARY_AGENTS_BACKEND_URL>",
        "PLANETARY_AGENTS_FRONTEND_URL": "<PLANETARY_AGENTS_FRONTEND_URL>",
        "PLANETARY_AGENTS_MCP_MODEL_TIER": "<PLANETARY_AGENTS_MCP_MODEL_TIER>"
      }
    }
  }
}
Run commanduvx alchm-planetary-agents-mcp
Environment variables to set
PLANETARY_AGENTS_BACKEND_URLBase URL of the Planetary Agents FastAPI backend that serves persona chat. Defaults to http://localhost:8000 for local dev; set to https://api.agents.alchm.kitchen to use the hosted service.
PLANETARY_AGENTS_FRONTEND_URLBase URL of the Planetary Agents frontend, used by get_agent_feed_discussion to read council-feed threads. Defaults to http://localhost:3000; set to https://agents.alchm.kitchen for the hosted feed.
PLANETARY_AGENTS_MCP_MODEL_TIERDefault model tier for persona responses: free | cheap_fast | primary | reflective. Defaults to free (the hosted backend reserves paid tiers).

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypialchm-planetary-agents-mcp1.0.0

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
contextobjectNoOptional structured context to pass through to /api/chat.
messagestringYesUser message for the agent.
agentNamestringYesAgent name or slug, e.g. Socrates, Rumi, Galileo, Jung, socrates.
modelTierenumNoOptional backend model tier override.free | cheap_fast | primary | reflective
conversationHistoryarrayNoOptional recent turns to provide as lightweight context.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.