_ registry / mcp streamable-http · checked 27m ago

scout

https://scout.clarved.com

Registry code: e8e10029b70a09ac

api record

Scout watches public store collection URLs and emails the account owner when new products appear. Start with account_status, then list_watches or add_watch. URL must be a public collection/category page; the first scan of a new watch is a baseline and emails nothing.

endpoint
https://scout.clarved.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is scout live?
Yes — it answered the hub's last check (checked 27m ago). It answered 100% of checks over the last 30 days.
Is scout free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does scout have?
7 tools: list_watches, delete_watch, account_status, get_watch, add_watch, update_watch, trigger_scan.
Is scout 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
235ms

last good check

priced tools
0

of 7 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. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 7 tools
7 auth-required 7 of 7 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.

  • list_watches auth-required 27m ago

    List the signed-in Scout account's watches (store collection URLs being monitored), including cadence, active state, and last check time.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • delete_watch auth-required never probed

    Remove a watch. The watch is archived (no further scans or emails); its stored items stay in Scout history.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "watchId": {
          "type": "string",
          "description": "Watch id from list_watches."
        }
      },
      "additionalProperties": false
    }
    arguments 10 lines
  • account_status auth-required 27m ago

    Show the Scout account's plan, watch limit, allowed cadences, and how digest emails are delivered.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_watch auth-required 27m ago

    Inspect one watch in detail: its settings, the most recent scan result, and the newest products seen on the page.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "watchId": {
          "type": "string",
          "description": "Watch id from list_watches."
        },
        "itemLimit": {
          "type": "number",
          "description": "How many recent items to return (default 20, max 50)."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • add_watch auth-required never probed

    Start watching a public store collection or category URL (e.g. a Shopify /collections/new-arrivals page) and email the account owner when new products appear. The first scan is a baseline: nothing is emailed. Watch out: the dogfood plan caps watches per account.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Public collection or category page URL (https)."
        },
        "email": {
          "enum": [
            "instant",
            "daily",
            "weekly"
          ],
          "type": "string",
          "description": "When to email about this watch: instant emails right after a scan finds something; daily/weekly hold finds for one roll-up email at the account's chosen slot. Default: instant."
        },
        "label": {
          "type": "string",
          "description": "Optional human name for the watch."
        },
        "notes": {
          "type": "string",
          "description": "Optional free-text note."
        },
        "cadence": {
          "enum": [
            "hourly",
            "six_hours",
            "daily",
            "weekly"
          ],
          "type": "string",
          "description": "How often to re-check the page. Default: daily."
        }
      },
      "additionalProperties": false
    }
    arguments 37 lines
  • update_watch auth-required never probed

    Update one of the account's watches: rename it, change its check frequency, change when it emails you, add notes, or pause/resume scanning.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "email": {
          "enum": [
            "instant",
            "daily",
            "weekly"
          ],
          "type": "string",
          "description": "When to email about this watch: instant, or held for the daily/weekly roll-up."
        },
        "label": {
          "type": "string",
          "description": "New name for the watch."
        },
        "notes": {
          "type": "string",
          "description": "Free-text note."
        },
        "active": {
          "type": "boolean",
          "description": "false pauses the watch, true resumes it."
        },
        "cadence": {
          "enum": [
            "hourly",
            "six_hours",
            "daily",
            "weekly"
          ],
          "type": "string",
          "description": "New check frequency."
        },
        "watchId": {
          "type": "string",
          "description": "Watch id from list_watches."
        }
      },
      "additionalProperties": false
    }
    arguments 41 lines
  • trigger_scan auth-required never probed

    Run a scan of one watch right now. This on-demand scan does NOT email a digest; scheduled scans send the digest emails. Scans are locked for a few minutes, so repeat calls may report the in-flight scan instead.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "watchId": {
          "type": "string",
          "description": "Watch id from list_watches."
        }
      },
      "additionalProperties": false
    }
    arguments 10 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 e8e10029b70a09ac.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/e8e10029b70a09ac/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/e8e10029b70a09ac/badge.svg)](https://brick.blue/agent/e8e10029b70a09ac?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
100%

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.