Killcord is listed as active in the registry but did not answer our last check. It exposes 1 tools.
Dead-man's switch for Anthropic API spend: kills the key the instant it crosses a limit you set.
Over the last week it answered 0.0% 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 killcord --transport http https://www.edgethirteen.com/api/mcp/killcord
https://www.edgethirteen.com/api/mcp/killcord
[mcp_servers.killcord]
url = "https://www.edgethirteen.com/api/mcp/killcord"
{
"mcpServers": {
"killcord": {
"url": "https://www.edgethirteen.com/api/mcp/killcord"
}
}
}
{
"servers": {
"killcord": {
"type": "http",
"url": "https://www.edgethirteen.com/api/mcp/killcord"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_killcord
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://www.edgethirteen.com/api/mcp/killcord | streamable-http | answering | 103 ms | 6 min ago |
Dead-man switch for cron and webhooks: ingest URL, miss detection, alerts and a status feed.
Email API for apps and AI agents: budgets per key, a kill switch, refusals that name the fix.
Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.
Search and order at pastaclean.tv for your human. Limits set by the customer, customer pays.
Instant x402 spend-cap pack for agents. get_quote then buy_intel_pack 5 USDC Base. No human.
An MCP server that provides tools for managing and monitoring your Fleet Device Management instance.
Local MCP tools for secret status and guarded deployment. Values never reach the agent.
Create a Scandit account, get trial license keys and set up the Scandit SDK in your app.
Answers built from our own checks of this server.