_ registry / mcp http-sse · checked 2h ago

agent-video

https://mcp.autosophia.io

Registry code: 542a8eb1c99b6272

api record

Script in, finished 1080p narrated video out. Pay per call in USDC via x402.

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

endpoint
https://mcp.autosophia.io/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 agent-video live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is agent-video free to use?
Yes — the hub reached it with no key and no payment.
What tools does agent-video have?
8 tools: payment_info, service_info, get_job, fetch_video, submit_video_job, request_capability, list_jobs, list_voices.
Is agent-video 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 99.5%· all time 99.5%

latency
999ms

last good check

priced tools
0

of 8 tools

_ answered our checks, 90 days 566 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • turn script into narrated video
  • list narration voices
takes → gives
text → video
tools
6 reads1 changes data1 sends messages
_ 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 8 tools
2 open 6 never probed 2 of 8 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_jobs reads open 11h ago

    List recent video jobs. Free. limit: max jobs to return, e.g. 20

    mcp-tool

    {
      "type": "object",
      "title": "list_jobsArguments",
      "properties": {
        "limit": {
          "type": "integer",
          "title": "Limit",
          "default": 20
        }
      }
    }
    arguments 11 lines
  • list_voices reads open 11h ago

    List narration voices you can pass to submit_video_job. Free.

    mcp-tool

    {
      "type": "object",
      "title": "list_voicesArguments",
      "properties": {}
    }
    arguments 5 lines
  • payment_info reads unknown never probed

    How to pay, step by step. Read this if you got a 402 and are not sure what to do.

    mcp-tool

    {
      "type": "object",
      "title": "payment_infoArguments",
      "properties": {}
    }
    arguments 5 lines
  • service_info reads unknown never probed

    Start here. What this server sells, what it will not do, and the exact limits.

    mcp-tool

    {
      "type": "object",
      "title": "service_infoArguments",
      "properties": {}
    }
    arguments 5 lines
  • get_job reads unknown 11h ago

    Poll a video job until it is done. Free. Use after submit_video_job returns a job_id. job_id: id returned by submit_video_job, e.g. a1b2c3d4e5f6

    mcp-tool

    {
      "type": "object",
      "title": "get_jobArguments",
      "required": [
        "job_id"
      ],
      "properties": {
        "job_id": {
          "type": "string",
          "title": "Job Id"
        }
      }
    }
    arguments 13 lines
  • fetch_video reads unknown 2h ago

    Fetch the finished video path and size once the job is done. Free. job_id: id returned by submit_video_job

    mcp-tool

    {
      "type": "object",
      "title": "fetch_videoArguments",
      "required": [
        "job_id"
      ],
      "properties": {
        "job_id": {
          "type": "string",
          "title": "Job Id"
        }
      }
    }
    arguments 13 lines
  • submit_video_job changes data unknown never probed

    Turn a script into a finished 1080p video — narrated, cut to matched stock footage, subtitles burned in, audio normalized to −14 LUFS. Returns a job id; poll get_job, then fetch_video. Use when you need a publishable video and have only text. $0.60 per video in USDC on Solana — no account, no API key, no human in the loop. script: narration body to speak (plain text) title: optional intro title shown for ~4s at the top voice: voice id from list_voices(), e.g. female_warm subtitles: burn-in subtitles (default true) speed: narration speed multiplier, e.g. 1.0 seed: stock-selection seed for reproducible visuals, e.g. 7

    mcp-tool

    {
      "type": "object",
      "title": "submit_video_jobArguments",
      "required": [
        "script"
      ],
      "properties": {
        "seed": {
          "type": "integer",
          "title": "Seed",
          "default": 7
        },
        "speed": {
          "type": "number",
          "title": "Speed",
          "default": 1
        },
        "title": {
          "type": "string",
          "title": "Title",
          "default": ""
        },
        "voice": {
          "type": "string",
          "title": "Voice",
          "default": "female_warm"
        },
        "script": {
          "type": "string",
          "title": "Script"
        },
        "subtitles": {
          "type": "boolean",
          "title": "Subtitles",
          "default": true
        }
      }
    }
    arguments 38 lines
  • request_capability sends messages unknown never probed

    Tell this server what you needed and could not get. Free — no payment required. Your input goes to the operator's queue and to a public board of unmet agent demand (contact details are never shared; entries are reviewed before publishing). Include what you would pay if you know.

    mcp-tool

    {
      "type": "object",
      "title": "request_capabilityArguments",
      "required": [
        "need"
      ],
      "properties": {
        "need": {
          "type": "string",
          "title": "Need"
        },
        "tried": {
          "type": "string",
          "title": "Tried",
          "default": ""
        },
        "contact": {
          "type": "string",
          "title": "Contact",
          "default": ""
        },
        "would_pay_usd": {
          "type": "number",
          "title": "Would Pay Usd",
          "default": 0
        }
      }
    }
    arguments 28 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 542a8eb1c99b6272.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/542a8eb1c99b6272/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/542a8eb1c99b6272/badge.svg)](https://brick.blue/agent/542a8eb1c99b6272?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.

_ also on autosophia.io 2 entries

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.