_ registry / mcp streamable-http · checked 1h ago

nicklaunches

https://nicklaunches.com

Registry code: 4b5acfd7729900fd

api record

Nick Launches is a launch platform for AI products. Reading is anonymous and needs no setup: search_products, get_product, list_launch_directories and check_launch_readiness all work straight away. Writing needs a one time approval: the first call to submit_product or get_my_launches comes back with a link, which you should show to the person you are working with so they can approve it in a browser, and then you call the tool again. An agent can open a launch draft here, and can never publish a launch, pick a plan, pick a launch week, or pay, so finish every submission by handing the human…

endpoint
https://nicklaunches.com/api/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 nicklaunches live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is nicklaunches free to use?
Yes — the hub reached it with no key and no payment.
What tools does nicklaunches have?
7 tools: submit_product, get_product, check_launch_readiness, connect_account, list_launch_directories, get_my_launches, search_products.
Is nicklaunches 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
313ms

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
3 open 4 never probed 3 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_launch_directories open 1h ago

    List the launch directories Nick Launches has vetted, with domain rating, link type, traffic band, whether a badge is required, and what submitting each one involves. Use it to plan where else to submit a product. Returns 25 entries by default and 100 at most.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 25,
          "maximum": 100,
          "minimum": 1
        }
      }
    }
    arguments 11 lines
  • get_my_launches open 1h ago

    List the launches owned by the connected account at any status, including unfinished drafts, with plan, requested week, upvotes, impressions, clicks, badge status and the dashboard link. Use it to answer where a launch stands, or to find the slug of a draft that still needs finishing. If this session is not connected to an account yet, the result comes back with status needs_approval and a link: relay the link, wait for the human to approve, then call this tool again.

    mcp-tool

    {
      "type": "object",
      "properties": {}
    }
    arguments 4 lines
  • search_products open 1h ago

    Search products that have launched on Nick Launches. Use it to see what already launched in a category, to check whether a product is listed, or to research competitors before planning a launch. Only live, published launches are returned, never drafts or rejected submissions. Returns 10 results by default and 50 at most; pass the returned nextCursor back as cursor to page further.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 50,
          "minimum": 1
        },
        "query": {
          "type": "string",
          "maxLength": 120
        },
        "cursor": {
          "type": "string"
        },
        "category": {
          "type": "string"
        }
      }
    }
    arguments 21 lines
  • submit_product unknown never probed

    Open a launch draft on Nick Launches from a product URL. The server crawls the site and drafts the listing; any field you pass wins over what the crawl found. This creates a DRAFT ONLY. It never publishes, never picks a plan or a launch week, and never charges anything, so always hand the returned reviewUrl to the human and tell them to finish the launch in their browser. Run check_launch_readiness first and act on what it reports, since the same badge and duplicate rules decide whether the launch is approved. If this session is not connected to an account yet, the result comes back with status needs_approval and a link: relay the link, wait for the human to approve, then call this tool again.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "minLength": 1
        },
        "logo": {
          "type": "string"
        },
        "name": {
          "type": "string"
        },
        "pricing": {
          "enum": [
            "free",
            "freemium",
            "paid",
            "subscription",
            "one_time",
            "contact"
          ],
          "type": "string"
        },
        "tagline": {
          "type": "string"
        },
        "categories": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 3
        },
        "description": {
          "type": "string"
        },
        "screenshots": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 5
        },
        "demoVideoUrl": {
          "type": "string"
        },
        "firstComment": {
          "type": "string"
        },
        "targetKeyword": {
          "type": "string"
        },
        "twitterUsername": {
          "type": "string"
        }
      }
    }
    arguments 61 lines
  • get_product unknown never probed

    Fetch the full public listing for one launched product by slug: description, screenshots, maker, discount, upvotes, and comment and changelog counts. Use it after search_products when the summary is not enough. Accepts a current slug or a retired alias. A slug with no live product is an error result, so drafts stay private.

    mcp-tool

    {
      "type": "object",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "minLength": 1
        }
      }
    }
    arguments 12 lines
  • check_launch_readiness unknown never probed

    Audit a product website before submitting it and report exactly what to fix. Checks whether the Nick Launches badge or a link back is present, whether the URL is already listed or inside its relaunch cooldown, how complete the site metadata is, and which free launch weeks still have room. Run this before submit_product: it needs no account, and the fix field on every failing check is a concrete action you can carry out. Limited to 10 checks per hour per caller because each one crawls the site.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "minLength": 1
        }
      }
    }
    arguments 12 lines
  • connect_account unknown never probed

    Connect this agent session to a Nick Launches account, or check whether it already is. Call it with no arguments to get an approval link to show the human; they open it, approve once in a browser they are already signed into, and you carry on. Call it with a code you were already given to check whether that approval has come through yet. You will not usually need this tool: submit_product and get_my_launches hand out the same link themselves when they need one.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "code": {
          "type": "string"
        }
      }
    }
    arguments 8 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 4b5acfd7729900fd.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/4b5acfd7729900fd/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/4b5acfd7729900fd/badge.svg)](https://brick.blue/agent/4b5acfd7729900fd?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.