_ registry / mcp + a2a JSONRPC · checked 10d ago

Buildy

listed under this name in a public catalogue; the server gives only its address, app.buildy.so

https://app.buildy.so

Registry code: 41ff43115a4bb592

api record

Automates software project scaffolding, boilerplate generation, and build configuration setup through an AI-driven workflow builder.

from a public catalogue that lists it, not from the operator

endpoint
https://charm.ing/mcp
door code
4dd7465eceb65040
protocol
JSONRPC ·0.2
authentication
bearer
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 Buildy live?
Yes — it answered the hub's last check (checked 10d ago). It answered 100% of checks over the last 30 days.
Is Buildy 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 Buildy have?
10 tools: List and inspect apps, Read Charming documentation, Call an app's operations, Build a new app, Capture feedback from inside an app, Run an app on a schedule, Let another service call an app, Manage account profile, ….
Is Buildy 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
99.5%

90 days 98.9%· all time 99.1%

latency
516ms

last good check

priced tools
0

of 10 tools

_ answered our checks, 90 days 448 checks · signed record
  • degraded → live
  • live → degraded· HTTP 503
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
developer tools code & repositories
used for
  • scaffold software projects
  • generate boilerplate code
  • set up build configuration
takes → gives
text → code
_ 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

inferred, not observed

Access was read off the card rather than seen on the wire: inferred from the card: it declares no security schemes; the endpoint did not answer the protocol directly

_ what it can do 10 tools
10 never probed 0 of 10 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.

  • manage_apps unknown never probed

    List the caller's apps, fetch source/metadata, read the problem behind a "Fix with agent" handoff, rename, and delete. Backed by `list_apps`, `get_app`, `get_app_source`, `resolve_handoff`, `rename_app`, `delete_app`.

    listinspectmanage

  • read_docs unknown never probed

    Read the public Charming docs over the same connection, with no web access: the index, a capability or reference page, or the full authoring manual. Backed by `read_docs`.

    docsreferenceread

  • call_app unknown never probed

    Read or mutate an app's stored state via the operations it declares. Backed by `query_app`, `mutate_app`, `upload_asset`.

    callquerymutate

  • build_app unknown never probed

    Author an interactive web app or start from an existing one. Saves return a live URL. `copy_app` copies an app you can edit or a Template, optionally with its data. Backed by MCP tools `create_app`, `update_app`, `copy_app`, and `search_templates`.

    createbuildscaffold

  • submit_feedback unknown never probed

    Record per-app feedback — bug reports, feature requests, missing capabilities — and read the Charming team's replies. Backed by `submit_feedback`, `list_feedback`, `list_feedback_responses`, `acknowledge_feedback_responses`.

    feedbackreport

  • routines unknown never probed

    Run one of an app's own operations on an hourly, daily, or weekly timer with no chat open, and manage those schedules. Backed by `create_routine`, `list_routines`, `update_routine`, `delete_routine`.

    scheduleroutineautomation

  • webhooks unknown never probed

    Give one of an app's own operations a delivery URL and secret so an external service can call it with JSON, and manage those Webhooks. Backed by `create_webhook`, `list_webhooks`, `update_webhook`, `delete_webhook`.

    webhookintegrationautomation

  • profile unknown never probed

    Set the user's public handle for app sharing. Backed by `set_handle`.

    profilehandleaccount

  • app_history unknown never probed

    List an app's History, read an earlier revision's source, and restore it as the new current revision. Needs permission to change the app. Backed by `list_app_revisions`, `get_app_revision`, `restore_app_revision`.

    historyundorestore

  • share_app unknown never probed

    Share an app with collaborators, end users, or viewers, manage shares, open it to anyone with the link, and configure whether it is a template + starter prompt. Backed by `share_app`, `unshare_app`, `list_app_shares`, `set_public`, `unset_public`, `set_template`, `unset_template`, `set_starter_prompt`, and the deprecated aliases `set_remixable` / `unset_remixable`.

    sharetemplatecollaborate

_ try it over a2a 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 41ff43115a4bb592.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/41ff43115a4bb592/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/41ff43115a4bb592/badge.svg)](https://brick.blue/agent/41ff43115a4bb592?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 knowoff the mcp door
card completeness
20%

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.

_ also on buildy.so 1 entry

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.