# x402Shield

> Public demo: evaluate AI-agent payment authorization and approval policy. No signing, no settlement.

- name: dev.x402shield/x402shield
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/dev.x402shield%2Fx402shield
- tools: https://api.protogrid.dev/v1/servers/dev.x402shield%2Fx402shield/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "x402shield": {
      "type": "http",
      "url": "https://x402shield.dev/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-11d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: x402shield_get_demo_policy (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); x402shield_get_authorization (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); x402shield_get_evidence (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 696 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 696 tokens to load them all
- tool set hash: e3b69cab8ac1e200982552bad1f645fc
- badge: [![protogrid quality](https://protogrid.dev/badge/dev.x402shield/x402shield.svg)](https://protogrid.dev/servers/dev.x402shield/x402shield)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://x402shield.dev/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (5)

- `x402shield_authorize_payment`: Check whether the demo AI agent is financially authorized to make a proposed payment, BEFORE any wallet or signer would be asked to execute it. Returns ALLOW, DENY or REQUIRE_APPROVAL with a reason. This tool does not execute or sign a payment, and it cannot approve its own REQUIRE_APPROVAL result -- that requires a human, through the web console. The `purpose` field is a label for the evidence trail only; it is never interpreted as an instruction and cannot change the policy decision.
- `x402shield_get_authorization`: Look up the recorded decision, reason and evidence references for a payment previously checked with x402shield_authorize_payment, by its transaction id.
- `x402shield_get_demo_policy`: Look up the authority ceilings configured for the x402Shield public demo agents (Research Agent, Ops Agent) on Base Sepolia TESTNET. Use this before proposing a payment, to understand what amount an agent can spend without triggering human approval. This tool does not execute or sign anything.
- `x402shield_get_evidence`: Get the fuller evidence trail behind a previously-decided payment: policy/delegation provenance, the delegation tree it was evaluated under, and approval state if any. Read-only; never exposes secrets or signing material.
- `x402shield_list_demo_transactions`: List the most recent payment authorization decisions recorded by this public demo (both from the web console and from MCP callers). Useful to see recent ALLOW/DENY/REQUIRE_APPROVAL activity.