_ registry / mcp streamable-http · checked 16h ago

agentshield-facts

https://agentshield.live

Registry code: 97684f8032944132

api record

agentshield.live is a verify-before-you-act layer: deterministic pay-per-call checks an agent runs before money moves, an invoice goes out, or a deadline is promised. Cheaper and more reliable than reasoning the check out yourself. Call choose_route before you search or pay. It returns pay, compute, or skip. It does not pay, does not call a route, and does not return the fact. If it says pay, call that url and pay the live HTTP 402. Unknown input returns 404 and is not charged.

endpoint
https://agentshield.live/mcp
protocol
streamable-http ·2024-11-05
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
10 · newcomer
_ is it live, free and safe measured by this hub
Is agentshield-facts live?
Yes — it answered the hub's last check (checked 16h ago). It answered 100% of checks over the last 30 days.
Is agentshield-facts free to use?
Yes — the hub reached it with no key and no payment.
What tools does agentshield-facts have?
3 tools: describe_route, choose_route, list_routes.
Is agentshield-facts safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
107ms

last good check

priced tools
0

of 3 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts, and USDC settlements on base into the address this listing's priced doors name, read off the chain. Every caller and every payer counts the same; the chain total is counted from three payers. The address stands behind 197 doors on this origin, so the chain figures are the operator's. How it is counted.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

payers on base
23

distinct

settlements
740

last 2026-11-21

received on chain
4.456 USDC

concentrated

_ what it can do 3 tools
3 open 3 of 3 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • describe_route open 16h ago

    Free detail lookup for exactly one paid route. Input is the route path such as /iban or /transfer; the result is a JSON object with its price in USDC, parameters it needs, what it checks, limits and 402/404 behavior. Returns a short error text "Unknown route ... Call list_routes" if the path does not exist. Use it after choose_route or list_routes when you know which route you want and need its exact inputs before paying. Read-only: it does not call the route and spends no USDC.

    mcp-tool

    {
      "type": "object",
      "required": [
        "path"
      ],
      "properties": {
        "path": {
          "type": "string",
          "description": "Route path starting with a slash, exactly as shown by list_routes or choose_route, for example /iban, /transfer or /deadline."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • choose_route open 16h ago

    Free decision step. Call this FIRST, before you search the web, reason a check out yourself, or pay any route. Input is one plain-language sentence about what you are about to look up or verify (for example "validate a German IBAN before a transfer" or "is 2028 a leap year"). Returns JSON with decision = "pay", "compute" or "skip". On pay it also returns method, route, url, price_usdc and a short why: you then call that url and pay the HTTP 402 yourself with x402 (USDC on Base). On compute the task is simple arithmetic you should do locally and not pay for. On skip there is no matching route; do not guess one. Read-only and free: it never pays, never calls the paid route and never returns the fact itself. An empty task returns skip.

    mcp-tool

    {
      "type": "object",
      "required": [
        "task"
      ],
      "properties": {
        "task": {
          "type": "string",
          "description": "One plain-language sentence describing what you are about to look up or verify, for example \"check an invoice where net plus VAT may not equal gross\". Not a route path; use describe_route for that."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • list_routes open 16h ago

    Free catalog. Returns every paid route as a JSON array with path, HTTP method, url, price in USDC, what it checks, its limits and what unpaid and unknown input do (HTTP 402 and HTTP 404 without charge). Takes no arguments. Use it when choose_route said skip but you want to browse, or to see all bundles (/transfer, /invoice, /fields, /routing, /deadline, /holidays, /cryptopay, /settle, /value) and single checks at once. The list is long; to inspect just one route use describe_route. Read-only: it does not call any route and spends no USDC.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 97684f8032944132.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/97684f8032944132/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/97684f8032944132/badge.svg)](https://brick.blue/agent/97684f8032944132?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
70%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.