mcpserver.lol
registry/404-directory
Connection check verified live · 27h ago

404-directory

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

Tools 16
GitHub stars
Installs / wk
Licence
Transport streamable-http, stdio
Last checked 27h ago

Tools & capabilities

16 tools

Read from the running server on 27h ago.

compare_tools read-only ids_or_slugs*
Compare up to 5 ecosystem tools side-by-side (capabilities, trust dimensions, usage).
evaluate_prediction_market market*execution_modeintended_action*estimated_notional_usdgeographic_eligibility
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,…
evaluate_tool_risk action*target*permissionsexecution_modedata_sensitivity
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…
get_capability_graph read-only limitmin_similarity
Return a Capability Graph snapshot (nodes, shared-capability edges, capability index) for agent planning.
get_tool read-only id_or_slug*
Fetch one registered ecosystem tool by id or slug, including trust profile and usage stats.
get_trust_score read-only id_or_slug*
Return the machine-readable Trust Profile for a catalog tool (ownership, availability, compatibility, security, usage).
inspect_tool_server read-only id_or_slug*
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…
invoke_registered_tool read-only argumentstool_name*server_id_or_slug*
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…
list_capabilities read-only
List capabilities in the 404 catalog with tool counts. Use to explore the Capability Graph before searching.
recommend_tools read-only limitid_or_slug*
Given one known tool, recommend similar catalog tools via the Capability Graph (shared capabilities + protocol/category affinity).
report_prediction_market_outcome receipt_id*action_taken*failure_typeoutcome_token*execution_result*
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…
report_tool_outcome result*error_typereceipt_id*action_taken*outcome_token*
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…
search_official_docs read-only query*sourceslimit_per_source
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…
search_tools read-only qlimitcategoryprotocolcapabilitytrust_threshold
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…
understand_webpage read-only url*
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…
verify_web read-only url*expected_textexpected_status*
Independently verifies that a public website is reachable and meets deployment expectations (HTTP status, HTTPS validity, optional expected text). Returns structured evidence for a…