Agent Economy Index · MCP census · probed 2026-10-12 · JSON
ai.limitguard.api/limitguard
Verdict: reachable, 10 tools, no description flags. Endpoint https://api.limitguard.ai/mcp. Latency 11,804 ms.
Tools (10 fingerprinted)
| tool | description length | flags | first seen | last seen |
|---|---|---|---|---|
check_agent_wallet | 1,040 | 2026-10-12 | 2026-10-12 | |
check_entity | 643 | 2026-10-12 | 2026-10-12 | |
get_compliance_report | 1,050 | 2026-10-12 | 2026-10-12 | |
get_risk_score | 524 | 2026-10-12 | 2026-10-12 | |
get_trust_score | 722 | 2026-10-12 | 2026-10-12 | |
sanctions_preview | 574 | 2026-10-12 | 2026-10-12 | |
sanctions_screen | 551 | 2026-10-12 | 2026-10-12 | |
verify_lead | 1,672 | 2026-10-12 | 2026-10-12 | |
verify_wallet | 1,119 | 2026-10-12 | 2026-10-12 | |
wallet_sanctions_preview | 883 | 2026-10-12 | 2026-10-12 |
Tool changes (0)
| when | tool | kind |
|---|---|---|
| none yet |
Probe history
2026-10-12 ok (10 tools)
Depend on this server? Watch it with ToolDrift, $29/month: an alert within six hours when it changes a tool or trips a detector. Flags here are pattern matches on tool descriptions, not verdicts; read the description before deciding.
Run this server? Show today's check on your README or site with a badge that refreshes daily: 
<a href="https://index.agentexchange.work/mcp-server/ai.limitguard.api%2Flimitguard"><img src="https://index.agentexchange.work/badge/mcp/ai.limitguard.api%2Flimitguard.svg" alt="MCP server check by agentexchange.work"></a>
Claim this server — prove you operate
api.limitguard.ai and this page gets a "Claimed by the operator" line, the badge gets a CLAIMED prefix, and you get a JSON webhook alert when a daily probe records a tool change or more flagged descriptions than the day before (at most one alert per 6 hours). No account, no email, nothing to install.
- Put a text file at
https://api.limitguard.ai/.well-known/agentexchange-claim.txtwhose entire content is exactlyai.limitguard.api/limitguard. - Submit this form. We fetch that URL once (7-second timeout, User-Agent
agentexchange-index-claim) and compare the trimmed body with the registry name.
Alert payload: {event, server, day, drift:[{tool, kind, detected_at}], findings, previous_findings, page_url, badge_url}. Public list of claims (names and hosts only): /v1/claims.json.
Run this server? MCP servers process users' data and often accept content; the laws that follow are a 45-day privacy request process, an opt-out path, and for hosted content a takedown or notice-and-action process. Check your site free or get a hosted desk.
Pay-per-call tools and data for agents, no key: store gateway (300+ routes, one origin, Coinbase-settled) · AI media and inference from $0.001 · the x402 directory · sector gap lists (card or USDC) · MCP integrity report.