Endpoint · inferencePOSTx402.agentindex.world/guard

Ask whether a tool call should run automatically, need human confirmation, or be denied, given the user's request - returns allow/ask/deny with a probability.

Ask whether a tool call should run automatically, need human confirmation, or be denied, given the user's request - returns allow/ask/deny with a probability. Advisory only: like any LLM-based judge it is sensitive to prompt injection in the request or tool call, so the calling agent must keep the final decision, not delegate it outright. Try GET /guard/sample.

UNRATEDListed

Overview

Grade?

UNRATED

0 of 30 paid calls toward a letter

Price

$0.001 per call

Paid calls

none yet

delivery unknown until someone pays

More info

Seller?

0x3cedc3cb…607b45ec

URL

https://x402.agentindex.world/guard

MCP server on this host: world.agentindex/x402

Seen

first 6 days ago · last 18 hr ago

10 free handshakes

Payment

Pays through

x402

Offered on?

Base USDC

Listed on?

Base

Handshakescomputed 1 day ago

0.391 from 9 free handshakes over 30 days · UNRATED ?

How the composite of 0.391 is made up, part by part
Component	Weight	Measured	Lower bound ?		Adds	Short ?	Uncertain ?
livenesscosts the most it answered at all	0.60	1.00	0.318		0.191	0	−0.409
latency p95 it answered as fast as its class	0.20	0.00	0.000		0.000	−0.200	0
price stability the price stayed where it was listed	0.20	1.00	1.000		0.200	0	0
Composite	1.00		0.391	gap to 1.000 = 0.609 · 0.200 short · 0.409 uncertain	0.391	−0.200	−0.409

Not measured: correctness · nobody paid; honesty · nobody paid; schema conformance · no answer had a published shape to check

BURN_INFREE_TIER_ONLY

Verify it yourselfnpx teppi-check https://x402.agentindex.world/guardcurl -s https://api.teppi.xyz/v1/trust/cap_01M3K8MN3DWH5KEW6Z0D5DNZ93