MCP serverio.github.MM-sheng/404-directory

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

UNRATEDActivestreamable-http404.directory

Overview

Score?

UNRATED 0.443

of what a free look can see, on 26 looks

Looks

last 5 days ago

Tools

More info

URL

404.directory/mcp

streamable-http

Says it is

404.directory 0.10.3

protocol 2025-06-18

In the record since

32 days ago

Among servers18,413 with a card

0median 0.606 · this server 0.443 · highest on record 0.8561

Toolsfrom sha256:f932c1a40a…678763

The tools this server lists, read out of the definition it returned
Tool	Schema
compare_tools Compare up to 5 ecosystem tools side-by-side (capabilities, trust dimensions, usage).	input · no output
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,	input · no output
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 o	input · no output
get_capability_graph Return a Capability Graph snapshot (nodes, shared-capability edges, capability index) for agent planning.	input · no output
get_tool Fetch one registered ecosystem tool by id or slug, including trust profile and usage stats.	input · no output
get_trust_score Return the machine-readable Trust Profile for a catalog tool (ownership, availability, compatibility, security, usage).	input · no output
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 executio	input · no output
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 serve	input · no output
list_capabilities List capabilities in the 404 catalog with tool counts. Use to explore the Capability Graph before searching.	input · no output
recommend_tools Given one known tool, recommend similar catalog tools via the Capability Graph (shared capabilities + protocol/category affinity).	input · no output
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, abo	input · no output
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 fi	input · no output
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 o	input · no output
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, d	input · no output
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. Prefe	input · output
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 a	input · output

Verify it yourselfnpx teppi-check https://404.directory/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2CYQTZ0QMM3B2EH7J0FG