# Mm Sheng 404 Directory MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.mm-sheng%2F404-directory
Registry id: `mcp-registry/io.github.mm-sheng/404-directory`
Status: dead (checked 2026-10-25T09:33:21.939Z)

## Measurements (30 days)

- Uptime: 99.53%
- Checks: 3420
- Outages (90 days): 19

## Install

```json
{
  "mcpServers": {
    "mm-sheng-404-directory-mcp-server": {
      "type": "http",
      "url": "https://404.directory/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http mm-sheng-404-directory-mcp-server https://404.directory/mcp
```

## Tools (16)

- `compare_tools`: Compare up to 5 ecosystem tools side-by-side (capabilities, trust dimensions, usage).
- `evaluate_prediction_market`: Evaluate one specific Polymarket market before an AI Agent observes or contemplates buying or selling a Yes/No position. Use immediately before a decision when 
- `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.directory. Use this immediately b
- `get_capability_graph`: Return a Capability Graph snapshot (nodes, shared-capability edges, capability index) for agent planning.
- `get_tool`: Fetch one registered ecosystem tool by id or slug, including trust profile and usage stats.
- `get_trust_score`: Return the machine-readable Trust Profile for a catalog tool (ownership, availability, compatibility, security, usage).
- `inspect_tool_server`: Live-inspect one active, provider-verified, operator-curated public MCP server from the 404.directory catalog. Returns only the remote read-only tools approved 
- `invoke_registered_tool`: Invoke exactly one approved read-only tool on an active, provider-verified, operator-curated public MCP server registered in 404.directory. First use search_too
- `list_capabilities`: List capabilities in the 404 catalog with tool counts. Use to explore the Capability Graph before searching.
- `recommend_tools`: Given one known tool, recommend similar catalog tools via the Capability Graph (shared capabilities + protocol/category affinity).
- `report_prediction_market_outcome`: Close the behavioral feedback loop for one prior evaluate_prediction_market receipt. Call after the Agent proceeds, reduces position size, changes side, waits, 
- `report_tool_outcome`: Close the feedback loop for one prior evaluate_tool_risk receipt. Call after the Agent proceeds, changes tools, requests review, or aborts. Submit only the boun
- `search_official_docs`: Search current first-party OpenAI, Microsoft Learn, AWS, and Cloudflare documentation in one call. Use this as the default documentation research tool for quest
- `search_tools`: Find third-party catalog tools using short provider/capability keywords, for example 'official documentation' or 'OpenAI docs'. All meaningful query terms must 
- `understand_webpage`: Reads one public human-facing webpage and returns a compact, evidence-linked AgentPageModel: page type, entities, login/current state, forms, enabled actions, a
- `verify_web`: Independently verifies that a public website is reachable and meets deployment expectations (HTTP status, HTTPS validity, optional expected text). Returns struc

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.