Propagation breaker for agent fleets is answering right now. Last checked 6 min ago. It exposes 6 tools.
Propagation breaker: egress quarantine + fingerprint outbreak telemetry for fleets.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 23 October 2026. No other catalogue keeps this.
Over the last week it answered 99.2% 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 propagation-breaker-agent-worms --transport http https://textforagents.com/products/propagation-breaker-agent-worms/mcp
https://textforagents.com/products/propagation-breaker-agent-worms/mcp
[mcp_servers.propagation-breaker-agent-worms]
url = "https://textforagents.com/products/propagation-breaker-agent-worms/mcp"
{
"mcpServers": {
"propagation-breaker-agent-worms": {
"url": "https://textforagents.com/products/propagation-breaker-agent-worms/mcp"
}
}
}
{
"servers": {
"propagation-breaker-agent-worms": {
"type": "http",
"url": "https://textforagents.com/products/propagation-breaker-agent-worms/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
store_read
store_write
controls_verify
egress_check
fingerprint_query
telemetry_report
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://textforagents.com/products/propagation-breaker-agent-worms/mcp | streamable-http | answering | 357 ms | 6 min ago |
The open vocabulary of print for AI agents: terms, product envelopes, validation, fingerprint.
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
Anti-poisoning memory for agents: provenance, conflicts, quarantine gate.
Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.
Standby rescue agent for fleets: prohibition, pre-brief, MAYDAY rescue.
Puts Approve/Deny on your phone before an agent acts, and waits for your fingerprint.
Conflicts check and ethical walls: fingerprint register, gated consent, signed walls, breach query.
AI agent token-cost telemetry + 429 prediction. Per-agent attribution, anomaly + routing + quota.
Answers built from our own checks of this server.