Agent Rescue is answering right now. Last checked 6 min ago. It exposes 3 tools.
Cross-session idempotency, URLs as schema-validated JSON, and a record of missing capabilities.
Over the last week it answered 61.2% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
claude mcp add agent-rescue --transport http https://agent-rescue.vercel.app/api/mcp
{
"mcpServers": {
"agent-rescue": {
"url": "https://agent-rescue.vercel.app/api/mcp"
}
}
}
[mcp_servers.agent-rescue]
url = "https://agent-rescue.vercel.app/api/mcp"
{
"mcpServers": {
"agent-rescue": {
"url": "https://agent-rescue.vercel.app/api/mcp"
}
}
}
{
"mcpServers": {
"agent-rescue": {
"url": "https://agent-rescue.vercel.app/api/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
check_and_claim
request_capability
fetch_structured
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agent-rescue.vercel.app/api/mcp | streamable-http | answering | 249 ms | 6 min ago |
Micro-settled web content extraction and JSON schema validation utilities for AI agents via XRPL.
Regex matching, email/URL format validation, and JSON Schema validation.
A live, curated feed of new AI agent capabilities across MCP, SDKs, models, and APIs.
Deterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.
Resolve capability gaps: validate native MCPs, search live web, and record unmet demand.
Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.
Document tooling for AI agents: PDF/text reading, chunking, schema-validated JSON output.
Policy checks, approvals, records, and governed HTTP capabilities for unattended agents.
Answers built from our own checks of this server.