_ registry / mcp http-sse · checked 50m ago

MoonScroll

https://api.moonscroll.ai

Registry code: 2144258462ad09d8

api record

MoonScroll API tools for brands, audiences, pattern analysis, ideas, and scripts. Authenticate every request with Authorization: Bearer <msk_api_key>. Start by listing brands, then explore audiences and patterns for a brand, then generate ideas and scripts.

endpoint
https://api.moonscroll.ai/mcp
protocol
http-sse ·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 MoonScroll live?
Yes — it answered the hub's last check (checked 50m ago). It answered 98% of checks over the last 30 days.
Is MoonScroll 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 MoonScroll have?
13 tools: get_idea, get_audience_patterns, get_brand, get_audience, get_script, list_ideas, list_brand_audiences, get_audience_highlights, ….
Is MoonScroll 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
97.6%

90 days 98.6%· all time 98.6%

latency
423ms

last good check

priced tools
0

of 13 tools

_ answered our checks, 90 days 431 checks · signed record
  • down → live
  • degraded → down· timeout after 20000ms
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
used for
  • generate content ideas for a brand
  • generate a video script
  • analyze audience patterns
  • list brand audiences
takes → gives
text → text, data
tools
11 reads2 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 13 tools
5 auth-required 8 never probed 5 of 13 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_scripts reads auth-required 20h ago

    List scripts. Requires brand_hash and/or idea_hash.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 50
        },
        "idea_hash": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        },
        "brand_hash": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        }
      }
    }
    arguments 31 lines
  • generate_idea changes data auth-required never probed

    Generate one idea for a brand. Optional promotion_rating 0-10.

    mcp-tool

    {
      "type": "object",
      "required": [
        "brand_hash"
      ],
      "properties": {
        "brand_hash": {
          "type": "string"
        },
        "promotion_rating": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        }
      }
    }
    arguments 22 lines
  • list_brands reads auth-required 20h ago

    List brands visible to this API token.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 50
        }
      }
    }
    arguments 9 lines
  • generate_script changes data auth-required never probed

    Generate a script from idea_hash, or from brand_hash (creates one idea first). Optional promotion_rating 0-10.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "idea_hash": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        },
        "brand_hash": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        },
        "promotion_rating": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        }
      }
    }
    arguments 38 lines
  • list_audiences reads auth-required 20h ago

    List project audiences visible to this API token.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 50
        }
      }
    }
    arguments 9 lines
  • get_idea reads unknown 14h ago

    Retrieve a single idea by hash.

    mcp-tool

    {
      "type": "object",
      "required": [
        "idea_hash"
      ],
      "properties": {
        "idea_hash": {
          "type": "string"
        }
      }
    }
    arguments 11 lines
  • get_audience_patterns reads unknown 17h ago

    Get pattern analysis for an audience. pattern_type is required (one of: type, format, structure, categories, main_topic, content_angle, tone, audience, language, hook_type, hook_phrase, hook_visual, cta_type, cta_style). Optional upload_timeframe, more_than_one_video, show_other_options, sort.

    mcp-tool

    {
      "type": "object",
      "required": [
        "audience_hash",
        "pattern_type"
      ],
      "properties": {
        "sort": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        },
        "pattern_type": {
          "enum": [
            "type",
            "format",
            "structure",
            "categories",
            "main_topic",
            "content_angle",
            "tone",
            "audience",
            "language",
            "hook_type",
            "hook_phrase",
            "hook_visual",
            "cta_type",
            "cta_style"
          ],
          "type": "string",
          "description": "Pattern type to analyze. One of: type, format, structure, categories, main_topic, content_angle, tone, audience, language, hook_type, hook_phrase, hook_visual, cta_type, cta_style."
        },
        "audience_hash": {
          "type": "string"
        },
        "upload_timeframe": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        },
        "show_other_options": {
          "type": "boolean",
          "default": false
        },
        "more_than_one_video": {
          "type": "boolean",
          "default": true
        }
      }
    }
    arguments 62 lines
  • get_brand reads unknown 17h ago

    Retrieve a single brand by hash.

    mcp-tool

    {
      "type": "object",
      "required": [
        "brand_hash"
      ],
      "properties": {
        "brand_hash": {
          "type": "string"
        }
      }
    }
    arguments 11 lines
  • get_audience reads unknown 14h ago

    Retrieve a single audience by hash.

    mcp-tool

    {
      "type": "object",
      "required": [
        "audience_hash"
      ],
      "properties": {
        "audience_hash": {
          "type": "string"
        }
      }
    }
    arguments 11 lines
  • get_script reads unknown 14h ago

    Retrieve a single script by hash.

    mcp-tool

    {
      "type": "object",
      "required": [
        "script_hash"
      ],
      "properties": {
        "script_hash": {
          "type": "string"
        }
      }
    }
    arguments 11 lines
  • list_ideas reads unknown 4h ago

    List ideas for a brand. Requires brand_hash.

    mcp-tool

    {
      "type": "object",
      "required": [
        "brand_hash"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 50
        },
        "brand_hash": {
          "type": "string"
        }
      }
    }
    arguments 15 lines
  • list_brand_audiences reads unknown 4h ago

    List audiences with fit scores for a brand. High-fit only unless include_low_fit=true.

    mcp-tool

    {
      "type": "object",
      "required": [
        "brand_hash"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 50
        },
        "brand_hash": {
          "type": "string"
        },
        "include_low_fit": {
          "type": "boolean",
          "default": false
        }
      }
    }
    arguments 19 lines
  • get_audience_highlights reads unknown 17h ago

    Brand-specific audience highlights. Requires brand_hash.

    mcp-tool

    {
      "type": "object",
      "required": [
        "audience_hash",
        "brand_hash"
      ],
      "properties": {
        "brand_hash": {
          "type": "string"
        },
        "audience_hash": {
          "type": "string"
        }
      }
    }
    arguments 15 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 2144258462ad09d8.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/2144258462ad09d8/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/2144258462ad09d8/badge.svg)](https://brick.blue/agent/2144258462ad09d8?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.