Spiderbrain

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-08-22T17:25:09.484038Z",
      "publishedAt": "2026-08-22T17:25:09.484038Z",
      "statusChangedAt": "2026-08-22T17:25:09.484038Z"
    }
  },
  "server": {
    "name": "ai.spiderbrain/spiderbrain",
    "title": "Spiderbrain",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://mcp.spiderbrain.ai/mcp",
        "type": "streamable-http",
        "headers": [
          {
            "name": "Authorization",
            "isSecret": true,
            "description": "Optional. This server implements the MCP OAuth flow (dynamic client registration and PKCE), so a client that supports it can connect with no token: leave this blank. For headless or CLI use, set 'Bearer sb_live_...' with an API key from your Spiderbrain dashboard. Either way the hosted brain requires an existing Spiderbrain account with an uploaded brain.",
            "placeholder": "Bearer sb_live_..."
          }
        ]
      }
    ],
    "version": "0.2.3",
    "packages": [
      {
        "version": "0.2.3",
        "transport": {
          "type": "stdio"
        },
        "identifier": "spiderbrain",
        "runtimeHint": "npx",
        "registryType": "npm",
        "registryBaseUrl": "https://registry.npmjs.org",
        "packageArguments": [
          {
            "type": "positional",
            "value": "mcp",
            "isRequired": true,
            "description": "Subcommand that starts the stdio MCP server. Without it the binary prints help to stdout and exits."
          }
        ],
        "environmentVariables": [
          {
            "name": "SPIDERBRAIN_ROOT",
            "format": "filepath",
            "isRequired": true,
            "description": "Absolute path to the repository to serve, which must already contain a committed .spiderbrain/ folder. Set this: an MCP client's working directory is usually not your repository, and without it the server serves the working directory and reports that no understanding layer was found. Equivalent to passing --root."
          },
          {
            "name": "SPIDERBRAIN_API_KEY",
            "isSecret": true,
            "description": "Optional. Enables the cloud why-layer used by the sb_ask tool. The structural tools work offline without it."
          },
          {
            "name": "SPIDERBRAIN_REGISTRY",
            "description": "Optional. Base URL of the public brain registry this server consults on the first tool call when the repository has no committed .spiderbrain/ folder. Defaults to https://spiderbrain.ai/registry."
          }
        ]
      }
    ],
    "repository": {
      "id": "1271064370",
      "url": "https://github.com/aabhisrv/Spiderbrain.ai-Coremind",
      "source": "github",
      "subfolder": "spiderbrain"
    },
    "websiteUrl": "https://spiderbrain.ai/api/",
    "description": "Deterministic context layer for your codebase: change impact, blast radius, answers with receipts."
  }
}