Orca MCP Server

io.github.jascal/orca-mcp-server·v0.1.27·Other

Quality Score

/100

Go from natural language to verified finite state machines — topology bugs caught before code runs.

Repository →

§01 Install

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "orca-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@orcalang/orca-mcp-server"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "ORCA_PROVIDER": "anthropic",
        "ORCA_MODEL": "<orca_model>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "orca-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@orcalang/orca-mcp-server"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "ORCA_PROVIDER": "anthropic",
        "ORCA_MODEL": "<orca_model>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y @orcalang/orca-mcp-server

§02 Environment variables

ANTHROPIC_API_KEY

secret

Anthropic API key for LLM-powered tools (generate_machine, generate_multi_machine, refine_machine, generate_actions with use_llm). Not required for parse_machine, verify_machine, compile_machine, or server_status.

ORCA_PROVIDER

LLM provider to use: anthropic (default), openai, grok, or ollama.

ORCA_MODEL

Model name to use for LLM tools. Defaults to claude-sonnet-4-6 for Anthropic.

§03 MCP Quality Score · methodology

freshness

completeness

installability

documentation

stability

§04 Alternatives in Other

agency.lona/trading