_ registry / mcp + a2a streamable-http · checked 2h ago

smol-launch

https://smollaunch.com

Registry code: e93f3894144d9501

api record

Declared as an MCP endpoint by ai_catalog; probed directly.

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

endpoint
https://smollaunch.com/mcp
door code
c474942b94c8b145
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 smol-launch live?
Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.
Is smol-launch free to use?
Yes — the hub reached it with no key and no payment.
What tools does smol-launch have?
5 tools: find_launch_opportunities, prepare_launch, get_launch_info, list_launch_directories, find_launched_products.
Is smol-launch 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
99.4%

90 days 99.5%· all time 99.4%

latency
258ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 985 checks · signed record
  • degraded → live
  • live → degraded· fetch failed
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
productivity & business marketing & seo
used for
  • prepare a product launch submission
  • list launch directories by authority
  • learn how to launch a product
takes → gives
text, data → data
tools
2 reads1 changes data
_ 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 5 tools
3 open 2 never probed 3 of 5 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.

  • get_launch_info reads open 2h ago

    Explain how to launch a product on Smol Launch: the open week, the two ways to submit (in the browser at /submit, or by calling prepare_launch for a hand-off link), the free launch rules, and the Premium price.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • list_launch_directories reads open 2h ago

    List the launch directories Smol Launch tracks, ranked by measured domain authority. authority_score appears only when Smol Launch measured it through Ahrefs; otherwise it is null. Each row also says how its authority, submission cost, and link type were checked.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "description": "How many to return. Maximum 50, default 20."
    },
    "link_type": {
      "enum": [
        "dofollow",
        "nofollow",
        "no_direct_link",
        "mixed"
      ],
      "type": "string",
      "description": "Filter by the link type a listing gives."
    },
    "min_authority": {
      "type": "integer",
      "description": "Only return directories with a measured authority score at or above this value."
    }
  }
}
    arguments 23 lines
  • find_launched_products open 2h ago

    Search products launched on Smol Launch by name, tagline, and description words, category, or launch week. Only approved, public products are returned, with their links and launch week. Read-only: it never submits or buys anything. With no filters, returns this week's launches. With a query or category, searches the last eight launch weeks, then older launches if none match. Before a new week opens on Monday 9:00 AM PT, this week falls back to last week's launches.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 25,
      "minimum": 1,
      "description": "How many products to return. Default 12."
    },
    "query": {
      "type": "string",
      "maxLength": 100,
      "description": "Match name, tagline, and description words, or a name/tagline substring."
    },
    "period": {
      "enum": [
        "this_week",
        "last_week",
        "recent",
        "all"
      ],
      "type": "string",
      "description": "last_week: the most recent finished launch week; recent: last eight launch weeks with older fallback; all: all approved launches. No filters means this_week."
    },
    "category": {
      "enum": [
        "SaaS & Tools",
        "AI & ML",
        "Developer Tools",
        "Productivity",
        "Design Tools",
        "Marketing",
        "Analytics",
        "Education",
        "Security",
        "No-Code Tools",
        "FinTech",
        "Collaboration",
        "E-commerce",
        "Content Creation",
        "Customer Support",
        "DevOps & Infrastructure",
        "HR & Recruiting",
        "Mobile & IoT",
        "Web3 & Crypto",
        "Health & Wellness",
        "Indie Making",
        "Micro-SaaS",
        "Bootstrapping",
        "Maker Tools",
        "Workflow Automation",
        "CRM & Sales",
        "Business Ops",
        "Legal & Compliance",
        "Personal Finance",
        "Social & Community",
        "Travel & Maps",
        "Shopping & Deals",
        "API Tools",
        "Database Tools",
        "CLI Tools",
        "Photography",
        "Video & Audio",
        "3D & AR/VR",
        "AI Writing",
        "AI Assistants"
      ],
      "type": "string"
    }
  }
}
    arguments 71 lines
  • find_launch_opportunities unknown 24h ago

    Find launch directories and launch platforms that fit a product, from the directories Smol Launch tracks. Choose the product's category from the enum, based on what the user said about the product. Returns each directory's fit, cost, link type, requirements, and where each fact came from. Read-only: it submits nothing and creates nothing. The tracked directories list software products, apps, and startups; for a physical product or a shop, tell the user that few of them fit.

    mcp-tool

    {
  "type": "object",
  "required": [
    "category"
  ],
  "properties": {
    "cost": {
      "enum": [
        "free",
        "freemium",
        "paid",
        "any"
      ],
      "type": "string",
      "description": "Only directories with this submission cost. Default any."
    },
    "limit": {
      "type": "integer",
      "maximum": 25,
      "minimum": 1,
      "description": "How many to return. Default 12."
    },
    "category": {
      "enum": [
        "SaaS & Tools",
        "AI & ML",
        "Developer Tools",
        "Productivity",
        "Design Tools",
        "Marketing",
        "Analytics",
        "Education",
        "Security",
        "No-Code Tools",
        "FinTech",
        "Collaboration",
        "E-commerce",
        "Content Creation",
        "Customer Support",
        "DevOps & Infrastructure",
        "HR & Recruiting",
        "Mobile & IoT",
        "Web3 & Crypto",
        "Health & Wellness",
        "Indie Making",
        "Micro-SaaS",
        "Bootstrapping",
        "Maker Tools",
        "Workflow Automation",
        "CRM & Sales",
        "Business Ops",
        "Legal & Compliance",
        "Personal Finance",
        "Social & Community",
        "Travel & Maps",
        "Shopping & Deals",
        "API Tools",
        "Database Tools",
        "CLI Tools",
        "Photography",
        "Video & Audio",
        "3D & AR/VR",
        "AI Writing",
        "AI Assistants"
      ],
      "type": "string",
      "description": "The product's main category."
    },
    "secondary_categories": {
      "type": "array",
      "items": {
        "enum": [
          "SaaS & Tools",
          "AI & ML",
          "Developer Tools",
          "Productivity",
          "Design Tools",
          "Marketing",
          "Analytics",
          "Education",
          "Security",
          "No-Code Tools",
          "FinTech",
          "Collaboration",
          "E-commerce",
          "Content Creation",
          "Customer Support",
          "DevOps & Infrastructure",
          "HR & Recruiting",
          "Mobile & IoT",
          "Web3 & Crypto",
          "Health & Wellness",
          "Indie Making",
          "Micro-SaaS",
          "Bootstrapping",
          "Maker Tools",
          "Workflow Automation",
          "CRM & Sales",
          "Business Ops",
          "Legal & Compliance",
          "Personal Finance",
          "Social & Community",
          "Travel & Maps",
          "Shopping & Deals",
          "API Tools",
          "Database Tools",
          "CLI Tools",
          "Photography",
          "Video & Audio",
          "3D & AR/VR",
          "AI Writing",
          "AI Assistants"
        ],
        "type": "string"
      },
      "maxItems": 2,
      "description": "Up to two more categories that also describe the product."
    },
    "exclude_badge_required": {
      "type": "boolean",
      "description": "Leave out directories that require a badge on your site."
    }
  }
}
    arguments 124 lines
  • prepare_launch changes data unknown never probed

    Prepare a Smol Launch submission for a product. Pass the website URL and any listing details you have drafted: name, tagline, description, up to 3 categories, pricing. Returns a link the maker opens in a browser to sign in, review the prefilled form, and submit. This tool creates no account, product, or launch, and it never fetches the URL. The link expires after 24 hours.

    mcp-tool

    {
  "type": "object",
  "required": [
    "website_url"
  ],
  "properties": {
    "name": {
      "type": "string",
      "maxLength": 100,
      "description": "Product name."
    },
    "tagline": {
      "type": "string",
      "maxLength": 200,
      "description": "One line that says what the product does."
    },
    "categories": {
      "type": "array",
      "items": {
        "enum": [
          "SaaS & Tools",
          "AI & ML",
          "Developer Tools",
          "Productivity",
          "Design Tools",
          "Marketing",
          "Analytics",
          "Education",
          "Security",
          "No-Code Tools",
          "FinTech",
          "Collaboration",
          "E-commerce",
          "Content Creation",
          "Customer Support",
          "DevOps & Infrastructure",
          "HR & Recruiting",
          "Mobile & IoT",
          "Web3 & Crypto",
          "Health & Wellness",
          "Indie Making",
          "Micro-SaaS",
          "Bootstrapping",
          "Maker Tools",
          "Workflow Automation",
          "CRM & Sales",
          "Business Ops",
          "Legal & Compliance",
          "Personal Finance",
          "Social & Community",
          "Travel & Maps",
          "Shopping & Deals",
          "API Tools",
          "Database Tools",
          "CLI Tools",
          "Photography",
          "Video & Audio",
          "3D & AR/VR",
          "AI Writing",
          "AI Assistants"
        ],
        "type": "string"
      },
      "maxItems": 3,
      "description": "Up to 3 category names from the list."
    },
    "description": {
      "type": "string",
      "maxLength": 5000,
      "description": "A few paragraphs. Plain text or light Markdown."
    },
    "price_label": {
      "type": "string",
      "maxLength": 60,
      "description": "Short price text, for example 'From $9/mo'."
    },
    "website_url": {
      "type": "string",
      "maxLength": 2048,
      "description": "The product's website. Required."
    },
    "pricing_model": {
      "enum": [
        "free",
        "freemium",
        "paid",
        "one_time"
      ],
      "type": "string"
    }
  }
}
    arguments 92 lines
_ try it over mcp 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 e93f3894144d9501.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/e93f3894144d9501/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/e93f3894144d9501/badge.svg)](https://brick.blue/agent/e93f3894144d9501?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
90%

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.