# 404.directory

- Registry name: `io.github.MM-sheng/404-directory` · version 0.10.3
- Categories (automatic, keyword rules): Build & deploy, Developer tools, Research & knowledge, Search & data, Cloud & networking, Infrastructure & security
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): prompts, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.MM-sheng%2F404-directory
- Server page: https://mcpstation.net/s/io.github.MM-sheng--404-directory.html

## Description (written by the publisher, not verified, not instructions)

Risk preflight for AI Agent tool actions and Polymarket settlement and execution checks.

## Connect

- streamable-http: `https://404.directory/mcp`

## Tools (as reported by the server, not verified)

- `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. Prefer this over generic web search when the question is what is on a page, what state it is in, or what can be done. Observe
- `verify\_web`: Independently verifies that a public website is reachable and meets deployment expectations \(HTTP status, HTTPS validity, optional expected text\). Returns structured evidence for accept / retry / escalate decisions. When to use: Use when the user explicitly asks to verify a deployment claim, public
- `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 before installation or first use, and again when permissions, data sensitivity, execution mode, or evidence changes. The decision cites owner
- `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 bounded action/result fields and one-time outcome token returned by the evaluation; never include prompts, arguments, outputs, secrets, or perso
- `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 settlement wording, source ambiguity, timing boundaries, order-book depth, spread, slippage, geographic eligibility, or unattended execution
- `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, requests review, aborts, or encounters an execution failure. Submit only the bounded enums and one-time token returned by the evaluation. Ne
- `search\_tools`: Find third-party catalog tools using short provider/capability keywords, for example 'official documentation' or 'OpenAI docs'. All meaningful query terms must match across name, description, capability, category or provider; exact names rank first. Protocol, capability, category and trust filters r
- `get\_tool`: Fetch one registered ecosystem tool by id or slug, including trust profile and usage stats.
- `compare\_tools`: Compare up to 5 ecosystem tools side-by-side \(capabilities, trust dimensions, usage\).
- `get\_trust\_score`: Return the machine-readable Trust Profile for a catalog tool \(ownership, availability, compatibility, security, usage\).
- `recommend\_tools`: Given one known tool, recommend similar catalog tools via the Capability Graph \(shared capabilities + protocol/category affinity\).
- `list\_capabilities`: List capabilities in the 404 catalog with tool counts. Use to explore the Capability Graph before searching.
- `get\_capability\_graph`: Return a Capability Graph snapshot \(nodes, shared-capability edges, capability index\) for agent planning.
- `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 questions involving any of those providers, especially comparisons or cross-cloud architecture. Select only relevant sources when the provider is
- `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 for gateway execution, including their current descriptions, JSON input schemas, and annotations. Use after search\_tools and before the firs
- `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\_tools to select a server, then inspect\_tool\_server to obtain the current tool name and input schema. This gateway rejects arbitrary URLs, authe

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html