# 404_mcp

404.directory MCP Streamable HTTP endpoint. Discover and compare ecosystem tools, inspect approved remote MCP schemas, and invoke curated read-only third-party tools through a controlled gateway.

Agent View of the PolicyLayer registry record for `404_mcp`. HTML page: https://policylayer.com/tools/404-directory/404-mcp

## Facts

- Tool: `404_mcp`
- Server: 404 Directory (`MM-sheng/404-directory`) — https://policylayer.com/tools/404-directory.md
- Homepage: https://github.com/MM-sheng/404-directory
- Risk category: Execute (High risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "404_mcp",
    "arguments": {}
  }
}
```

## Why 404_mcp is rated High

Invokes third-party tools via a gateway; execution effects depend on arguments passed.

From the tool's own definition: "invoke curated read-only third-party tools through a controlled gateway"

## Use case

AI agents invoke 404_mcp to trigger actions in 404 Directory. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 404 Directory:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "404_mcp": {
      "limits": [
        {
          "counter": "404_mcp_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on 404 Directory (10)

- `invoke_registered_tool` — Execute — https://policylayer.com/tools/404-directory/invoke-registered-tool.md
- `compare_tools` — Read — https://policylayer.com/tools/404-directory/compare-tools.md
- `get_capability_graph` — Read — https://policylayer.com/tools/404-directory/get-capability-graph.md
- `get_tool` — Read — https://policylayer.com/tools/404-directory/get-tool.md
- `get_trust_score` — Read — https://policylayer.com/tools/404-directory/get-trust-score.md
- `inspect_tool_server` — Read — https://policylayer.com/tools/404-directory/inspect-tool-server.md
- `list_capabilities` — Read — https://policylayer.com/tools/404-directory/list-capabilities.md
- `recommend_tools` — Read — https://policylayer.com/tools/404-directory/recommend-tools.md
- `search_official_docs` — Read — https://policylayer.com/tools/404-directory/search-official-docs.md
- `search_tools` — Read — https://policylayer.com/tools/404-directory/search-tools.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=404-directory · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/404-directory