Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Fourth Feed

REMOTE · FOURTHFEED.COM

Search AI video tools: prices, free credits, traffic and agent-readiness.

Available components

+4 this week 66 Trust /100

Last scanned (17 hours ago)

Scores higher than 51% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Design and Media

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 937 tokens (~104/item across 9 items; 9 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage84
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 53% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_tool” rewrote its description, which is the text the model reads security
    • Schema quality: 751 → 937 ▼ functional
    • New tool “get_benchmark” functional
    • New tool “list_benchmarks” functional
  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 13 Nov 26 61

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://fourthfeed.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=fourthfeed.com CN=WE1,O=Google Trust Services,C=US 25 Sept 2026 24 Dec 2026 ECDSA 256 ECDSA-SHA256 a088db3924a34e6c138c67b41bd0f98d
SANs: fourthfeed.com, *.fourthfeed.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of fourthfeed.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
fourthfeed.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://fourthfeed.com/mcp Verified 200
http (plaintext) http://fourthfeed.com/mcp HTTPS enforced 301 https://fourthfeed.com/mcp
MCP tools · 9 exposed · ~794 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
compare_tools ~32

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

NameTypeReqDescription
domainsarrayyes–

No output schema declared.

No examples provided.

get_benchmark ~78

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).

NameTypeReqDescription
suite_idstringyesSuite id from list_benchmarks, e.g. "product-i2v-v1".

No output schema declared.

No examples provided.

get_tool ~114

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.

NameTypeReqDescription
domainstringyesDomain from search_tools, e.g. "example.ai".

No output schema declared.

No examples provided.

list_benchmarks ~57

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_categories ~22

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_new_tools ~55

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.

NameTypeReqDescription
limitinteger––
sincestring––

No output schema declared.

No examples provided.

list_referrals ~89

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.

NameTypeReqDescription
categorystring–Category id from list_categories.

No output schema declared.

No examples provided.

search_tools ~146

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.

NameTypeReqDescription
agent_readyboolean––
categorystring–Category id from list_categories.
limitinteger––
offsetinteger––
qstring–Words to look for, e.g. "lip sync".

No output schema declared.

No examples provided.

submit_tool ~201

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.

NameTypeReqDescription
categorystring–Category id from list_categories, if you know it.
namestring––
notestring–What the tool does, in your own words. Stored for the maintainer; not published as is.
urlstringyesThe tool’s URL or domain, e.g. "https://example.ai".

No output schema declared.

No examples provided.

Install

How do I install the Fourth Feed MCP server?

Fourth Feed is a hosted endpoint at https://fourthfeed.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · fourthfeed.com

# add to Claude Code
claude mcp add --transport http com-fourthfeed-fourthfeed 'https://fourthfeed.com/mcp'
Common questions

What is the Fourth Feed MCP server?

Fourth Feed is an MCP server listed in the public MCP registry as com.fourthfeed/fourthfeed. Search AI video tools: prices, free credits, traffic and agent-readiness. This page covers its hosted endpoint (https://fourthfeed.com/mcp).

Is the Fourth Feed MCP server safe to use?

Fourth Feed scores 66 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Fourth Feed MCP server expose?

Fourth Feed exposes 9 tools: search_tools, get_tool, list_categories, list_new_tools, compare_tools, and 4 more. Their descriptions and schemas cost roughly 794 tokens of context every time the server is loaded.

Does the Fourth Feed MCP server require authentication?

No. We connected to Fourth Feed without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Fourth Feed MCP server still maintained?

Fourth Feed is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Fourth Feed MCP server?

VerifyMCP ran 12 checks on Fourth Feed, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Fourth Feed: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.