INDIVIDUAL MCP TOOL

get_capability_graph

Return a Capability Graph snapshot (nodes, shared-capability edges, capability index) for agent planning.

404.directorynone authenticationAvailability not checked

LIVE ENDPOINT

https://404.directory/mcp

No auth detected

Connect to this endpoint to inspect the live schema for get_capability_graph and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.404-directory]
url = "https://404.directory/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "404-directory": {
      "type": "http",
      "url": "https://404.directory/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: 404-directory
Remote MCP URL: https://404.directory/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "404-directory": {
      "url": "https://404.directory/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "404-directory": {
      "type": "http",
      "url": "https://404.directory/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "404-directory",
  "transport": "streamable-http",
  "url": "https://404.directory/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

understand_webpage — Reads one public human-facing webpage and returns a compact, evidence-linked AgentPageModel: page type, entities, login/current state, forms, enabled actions, and confidence.
verify_web — Independently verifies that a public website is reachable and meets deployment expectations (HTTP status, HTTPS validity, optional expected text).
evaluate_tool_risk — Make a contextual allow, review, or block decision before an AI Agent installs or invokes a third-party tool registered in 404.
report_tool_outcome — Close the feedback loop for one prior evaluate_tool_risk receipt.
evaluate_prediction_market — Evaluate one specific Polymarket market before an AI Agent observes or contemplates buying or selling a Yes/No position.
report_prediction_market_outcome — Close the behavioral feedback loop for one prior evaluate_prediction_market receipt.
search_tools — Find third-party catalog tools using short provider/capability keywords, for example 'official documentation' or 'OpenAI docs'.
get_tool — Fetch one registered ecosystem tool by id or slug, including trust profile and usage stats.