Risk preflight for AI Agent tool actions and Polymarket settlement and execution checks.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 16 tools
Most tools have clearly distinct catalog, risk-evaluation, and web-verification roles. Minor overlap exists between get_tool (which already includes trust profile data) and get_trust_score, and between list_capabilities and get_capability_graph, though the detailed descriptions help resolve most ambiguity.
All tool names follow a consistent snake_case verb_noun pattern (compare_, evaluate_, get_, inspect_, invoke_, list_, recommend_, report_, search_, understand_, verify_). Retrieval, evaluation, and action verbs are used predictably throughout the set.
At 16 tools, the count is just above the ideal 3-15 band but still feels reasonably scoped for a directory/trust/recommendation service. The inclusion of search_official_docs, understand_webpage, and verify_web makes the set slightly broader than the core catalog purpose.
The set covers catalog discovery, comparison, tool inspection, invocation, risk evaluation, and behavioral feedback loops well. Minor gaps exist, such as no obvious browse-all-tools operation and no catalog registration/update path, but the core agent workflows have no critical dead ends.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search_tools6 fields changedInput schema / properties / capability / descriptionAdded value: +"Case-insensitive literal capability substring, e.g. 'documentation-search'. Get available labels from list_capabilities; SQL wildcard syntax is not supported."Input schema / properties / category / descriptionAdded value: +"Exact catalog category, e.g. 'developer-tools'."Input schema / properties / limit / descriptionAdded value: +"Maximum results after relevance ranking and all filters, from 1 to 50."Input schema / properties / protocol / descriptionAdded value: +"Required protocol family when supplied; never relaxed automatically."Input schema / properties / q / descriptionAdded value: +"Short keywords or an exact catalog name, e.g. 'official documentation' or 'openai_docs_mcp'. Keyword order is flexible; docs/doc map to documentation. Omit for filtered browsing. No arbitrary semantic inference."Input schema / properties / trust_threshold / descriptionAdded value: +"Minimum existing catalog trust score. Not a calibrated safety probability; never lowered automatically."evaluate_prediction_marketevaluate_tool_riskreport_prediction_market_outcomereport_tool_outcomesearch_official_docsinspect_tool_serverinvoke_registered_toolcompare_toolsget_capability_graphget_toolget_trust_scorelist_capabilitiesrecommend_toolssearch_toolsunderstand_webpageverify_webDeterministic pre-trade risk checks for autonomous AI trading agents.
Advisory policy preflight for AI-agent spend requests; never executes payments or accesses wallets.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Treasury and risk controls for agent wallets: policies, quotes, prediction-market orders.
Add one secure layer between your agents and this server.
