Skip to content
ToolCargo

Remote MCP servers / Publisher setup metadata

Remote MCP server directory.
Find a server URL.

Browse 3,137 listings with publisher-declared remote URLs in ToolCargo’s dated, partial index of the official MCP Registry. Search by task, inspect transports and setup metadata, then check the provider’s instructions before connecting.

Where will your next task take you?

Code & developmentResearch & knowledgeData & databases

Free discovery · no account · no API key

Let your agent do the finding.

Paste into your AI agent
Read https://toolcargo.com/agents.txt, then find remote MCP server URLs for my task and inspect their transport, headers and URL-template variables before helping me connect. Ask me what I want to do first.

Or add https://toolcargo.com/mcp as a Streamable HTTP MCP server. Discovery is free and needs no account.

Compare task fit, publisher, permissions and a small acceptance test with the MCP server selection guide.

Browse all servers and local packages →

Not sure which connection to choose? Read local vs remote MCP servers. Building a discovery workflow? See the MCP server search API reference.

Spiderbrain

Close details

Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.

Publisher name: ai.spiderbrain/spiderbrain · Version: 0.2.3

Publisher connection metadata
{
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://mcp.spiderbrain.ai/mcp",
      "headers": [
        {
          "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.",
          "isSecret": true,
          "placeholder": "Bearer sb_live_...",
          "name": "Authorization"
        }
      ]
    }
  ],
  "packages": [
    {
      "registryType": "npm",
      "registryBaseUrl": "https://registry.npmjs.org",
      "identifier": "spiderbrain",
      "version": "0.2.3",
      "runtimeHint": "npx",
      "transport": {
        "type": "stdio"
      },
      "packageArguments": [
        {
          "description": "Subcommand that starts the stdio MCP server. Without it the binary prints help to stdout and exits.",
          "isRequired": true,
          "value": "mcp",
          "type": "positional"
        }
      ],
      "environmentVariables": [
        {
          "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.",
          "isRequired": true,
          "format": "filepath",
          "name": "SPIDERBRAIN_ROOT"
        },
        {
          "description": "Optional. Enables the cloud why-layer used by the sb_ask tool. The structural tools work offline without it.",
          "isSecret": true,
          "name": "SPIDERBRAIN_API_KEY"
        },
        {
          "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.",
          "name": "SPIDERBRAIN_REGISTRY"
        }
      ]
    }
  ]
}

Remote URLs go into your client's MCP settings. Local packages need a compatible runtime. Check required headers, environment variables, permissions and provider costs before setup.

Publisher repository ↗

3,137 results

Index updated 2026-10-02

PreviousNext results

Read the remote connection details

URL and transport

Open a listing’s connection details to inspect its remotes. Streamable HTTP is the preferred registry transport; SSE is a legacy option. Use a transport your client supports. A listing may also include a local package.

Template variables

A URL containing a placeholder such as {tenant_id} needs the provider’s value before setup. Review any declared variables, choices, defaults and secret flags. The published template is not a ready-to-use URL.

Headers and authentication

Review declared headers, required values and secret flags. Missing headers do not prove anonymous access: the provider may require OAuth or other setup. ToolCargo keys authenticate its own hosted connectors, not third-party servers.

These are publisher declarations, not availability, security or client-compatibility checks by ToolCargo. Confirm permissions and pricing with the provider. See the official remote-server metadata reference.

This is a dated index of publisher-provided listings, not the complete registry or a ToolCargo verification. Third-party servers run with their own providers, credentials and pricing. ToolCargo discovery supplies setup metadata; it does not run their tools. Explore ToolCargo's hosted connectors.