Skip to content

Client Setup

Connect your AI client to the JickleJime MCP server to give it access to your Shadowdark knowledge base.

The repository includes a .mcp.json file that MCP-compatible clients discover automatically:

{
  "mcpServers": {
    "jicklejime": {
      "type": "stdio",
      "command": "dotnet",
      "args": ["run", "--project", "src/JickleJime.Mcp", "--", "--stdio"],
      "env": {
        "DOTNET_ENVIRONMENT": "Development"
      }
    }
  }
}

When you open the repository in VS Code with GitHub Copilot, or in another MCP-aware editor, the server is available automatically — no manual configuration needed.

GitHub Copilot (VS Code)

GitHub Copilot discovers the .mcp.json file when you open the repository. The JickleJime tools appear in Copilot's tool list automatically.

To verify it's working, ask Copilot:

@workspace Use the jicklejime search tool to find rules about critical hits

Claude Desktop

Add the server to your Claude Desktop configuration file:

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

Edit %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "jicklejime": {
      "command": "dotnet",
      "args": [
        "run",
        "--project", "/path/to/jicklejime/src/JickleJime.Mcp",
        "--", "--stdio"
      ],
      "env": {
        "DOTNET_ENVIRONMENT": "Development"
      }
    }
  }
}

Replace /path/to/jicklejime with the actual path to your clone of the repository.

Remote / deployed server

For a deployed MCP server accessible over HTTP:

  1. Endpoint — https://your-server/mcp
  2. Transport — HTTP Streamable
  3. Authentication — Authorization: Bearer <api-key> (if an API key is configured)

Configure your client to connect to the HTTP endpoint instead of launching a stdio subprocess. The exact configuration depends on your client.

Prerequisites

Before the MCP server can connect to your knowledge base, make sure:

  1. PostgreSQL is running — docker compose up -d starts the local database
  2. Credentials are configured — Azure OpenAI endpoint, PostgreSQL connection string, and optionally Azure AI Document Intelligence (see Configuration Reference)
  3. .NET 10 SDK is installed — Required to build and run the server
  4. Documents are ingested — Use the CLI to ingest documents before searching

Troubleshooting

"No results found" — Make sure documents have been ingested. Run jime list to check.

Connection refused — Verify the database is running (docker compose up -d) and credentials are configured.

Authentication errors — If using the HTTP transport with an API key, ensure the Authorization: Bearer <key> header is included in requests.