Catalog-cache guard for agent tool catalogs MCP Server
Catalog-cache guard for agent tool catalogs is answering right now. Last checked 4 min ago. It exposes 3 tools.
Cache guard: forced-private partitioning, TTL clamp, fingerprint diffing, exposure verdicts.
Catalog-cache guard for agent tool catalogs does not always answer
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.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.
claude mcp add catalog-cache-guard --transport http https://textforagents.com/products/catalog-cache-guard/mcphttps://textforagents.com/products/catalog-cache-guard/mcp[mcp_servers.catalog-cache-guard]
url = "https://textforagents.com/products/catalog-cache-guard/mcp"{
"mcpServers": {
"catalog-cache-guard": {
"url": "https://textforagents.com/products/catalog-cache-guard/mcp"
}
}
}{
"servers": {
"catalog-cache-guard": {
"type": "http",
"url": "https://textforagents.com/products/catalog-cache-guard/mcp"
}
}
}Available tools 3
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
guard_diff_check
guard_tools_list
cache_exposure_verdict
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://textforagents.com/products/catalog-cache-guard/mcp | streamable-http | answering | 329 ms | 4 min ago |
Alternatives to Catalog-cache guard for agent tool catalogs
same job, measured the same waySandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history
Quota-cliff watch: budgeted-vs-current quota diffing, shadow prices, pre-commit verdicts.
Query-intent privacy for agents: threshold cloaking with signed exposure receipts.
Consistent hashing ring with virtual nodes for distributed LLM cache routing and agent partitioning
Machine catalog for products that want agent clients: surfaces, hops, discovery paths.
Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.
Pre-trade safety verdicts for agents: token rug/honeypot, calldata guard, wallet risk — signed x402.
Causal guardrail: pass/caution/hold verdict on a causal claim before an agent acts.
Catalog-cache guard for agent tool catalogs — questions
Answers built from our own checks of this server.