_ registry / mcp streamable-http · checked 13h ago

fourthfeed

https://fourthfeed.com

Registry code: cda6d135ae297814

api record

Fourth Feed is a directory of AI video tools with pricing, free credits, quantitative video benchmarks (effective $/s, script pass gates), traffic and agent-readiness. For benchmark leaderboards and frozen test inputs, call list_benchmarks then get_benchmark. For free credits, call list_referrals (Fourth Feed’s own codes; disclose that when sharing). To add a video tool, call submit_tool with its URL. Start with search_tools (or list_categories), then get_tool for one tool. Results include page links; cite them. Data is a dated snapshot (as_of). Summaries are written by Fourth Feed;…

endpoint
https://fourthfeed.com/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 fourthfeed live?
Yes — it answered the hub's last check (checked 13h ago). It answered 100% of checks over the last 30 days.
Is fourthfeed free to use?
Yes — the hub reached it with no key and no payment.
What tools does fourthfeed have?
9 tools: compare_tools, submit_tool, get_tool, get_benchmark, list_categories, search_tools, list_new_tools, list_benchmarks, ….
Is fourthfeed 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
427ms

last good check

priced tools
0

of 9 tools

_ answered our checks, 90 days 2 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 9 tools
5 open 4 never probed 5 of 9 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_categories open 40h ago

    The categories used to sort tools, with how many tools each has.

    mcp-tool

    {
      "type": "object",
      "properties": {}
    }
    arguments 4 lines
  • search_tools open 13h ago

    Search the Fourth Feed directory of AI video tools (generators, avatars, editors, dubbing, lyric videos, faceless shorts, video APIs). Every word in q must appear in the name, domain, summary or category. Filter by category id (see list_categories) or agent_ready (has llms.txt, an official MCP registry entry or a public API). Returns brief records; use get_tool for the full one.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "q": {
          "type": "string",
          "maxLength": 200,
          "description": "Words to look for, e.g. \"lip sync\"."
        },
        "limit": {
          "type": "integer",
          "maximum": 50,
          "minimum": 1
        },
        "offset": {
          "type": "integer",
          "maximum": 5000,
          "minimum": 0
        },
        "category": {
          "type": "string",
          "maxLength": 60,
          "description": "Category id from list_categories."
        },
        "agent_ready": {
          "type": "boolean"
        }
      }
    }
    arguments 28 lines
  • list_new_tools open 40h ago

    Tools by the date Fourth Feed first saw them, newest first. Pass since (YYYY-MM-DD) to get only those first seen on or after that day.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "maximum": 50,
          "minimum": 1
        },
        "since": {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
        }
      }
    }
    arguments 14 lines
  • list_benchmarks open 13h ago

    List Fourth Feed’s standardized AI video benchmark suites (e.g. product-i2v-v1, motion-swap-v1) with frozen R2 test cases, script pass gates, run counts and current effective $/s leaders.

    mcp-tool

    {
      "type": "object",
      "properties": {}
    }
    arguments 4 lines
  • list_referrals open 13h ago

    Fourth Feed’s own referral codes for AI video tools and APIs: what a new user gets (as the tool states it), the link or code, the terms and the date checked. Use it when someone asks which video tool gives free credits. Fourth Feed gets credits or a commission when these are used; say so when you share one.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "category": {
          "type": "string",
          "maxLength": 60,
          "description": "Category id from list_categories."
        }
      }
    }
    arguments 10 lines
  • compare_tools unknown never probed

    The same facts as get_tool for 2 to 5 tools side by side.

    mcp-tool

    {
      "type": "object",
      "required": [
        "domains"
      ],
      "properties": {
        "domains": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 120
          },
          "maxItems": 5,
          "minItems": 2
        }
      }
    }
    arguments 17 lines
  • submit_tool unknown never probed

    Suggest an AI video tool for the directory by its URL or domain. Only video tools are listed (generation, avatars, editing, captions, dubbing, lyric and music videos, faceless shorts, video model and data APIs); others are recorded as off-topic. It is queued, then read (robots.txt, /llms.txt, home page) and listed if the site has a title, description or llms.txt. Tools already listed or queued are reported, not duplicated. Anyone can submit, including the tool’s own agent; no key needed. Limited to a few submissions a minute.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "maxLength": 300,
          "description": "The tool’s URL or domain, e.g. \"https://example.ai\"."
        },
        "name": {
          "type": "string",
          "maxLength": 80
        },
        "note": {
          "type": "string",
          "maxLength": 500,
          "description": "What the tool does, in your own words. Stored for the maintainer; not published as is."
        },
        "category": {
          "type": "string",
          "maxLength": 60,
          "description": "Category id from list_categories, if you know it."
        }
      }
    }
    arguments 27 lines
  • get_tool unknown never probed

    One tool by domain: our summary, the site’s own title and description (with the date checked), pricing and free tier where the site states them, wrapper markup audit, quantitative benchmark runs (effective $/s, pass rate, script scores), agent-readiness (llms.txt, MCP registry id, public API), traffic and revenue with source and date, our referral code if we have one, and a link to its page.

    mcp-tool

    {
      "type": "object",
      "required": [
        "domain"
      ],
      "properties": {
        "domain": {
          "type": "string",
          "maxLength": 120,
          "description": "Domain from search_tools, e.g. \"example.ai\"."
        }
      }
    }
    arguments 13 lines
  • get_benchmark unknown never probed

    Get one standardized AI video benchmark suite by suite_id: frozen R2 input URLs and sha256 hashes, automated pass gates, and the full leaderboard ranked by cases passed and effective cost per usable second ($/s).

    mcp-tool

    {
      "type": "object",
      "required": [
        "suite_id"
      ],
      "properties": {
        "suite_id": {
          "type": "string",
          "maxLength": 80,
          "description": "Suite id from list_benchmarks, e.g. \"product-i2v-v1\"."
        }
      }
    }
    arguments 13 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 cda6d135ae297814.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/cda6d135ae297814/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/cda6d135ae297814/badge.svg)](https://brick.blue/agent/cda6d135ae297814?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.