Fourth Feed is an MCP server published by com.fourthfeed, hosted at fourthfeed.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 9 tools, including search_tools, get_tool, list_categories, list_new_tools, compare_tools.
Search AI video tools: prices, free credits, traffic and agent-readiness.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| q | string | Words to look for, e.g. "lip sync". |
| limit | integer | |
| offset | integer | |
| category | string | Category id from list_categories. |
| agent_ready | boolean |
None yet. Changes appear after a server's second daily check.
{
"name": "search_tools",
"title": "Search AI video tools",
"description": "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.",
"inputSchema": {
"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"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| domain * | string | Domain from search_tools, e.g. "example.ai". |
{
"name": "get_tool",
"title": "Get a tool",
"description": "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 $/s, pass rate, script scores), agent-readiness (llms.txt, MCP registry id, public API), traffic and revenue with source and date, our referral code if we have one, and a link to its page.",
"inputSchema": {
"type": "object",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"maxLength": 120,
"description": "Domain from search_tools, e.g. \"example.ai\"."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}The categories used to sort tools, with how many tools each has.
No parameters.
{
"name": "list_categories",
"title": "List categories",
"description": "The categories used to sort tools, with how many tools each has.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Tools by the date Fourth Feed first saw them, newest first. Pass since (YYYY-MM-DD) to get only those first seen on or after that day.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| since | string |
{
"name": "list_new_tools",
"title": "List newly added tools",
"description": "Tools by the date Fourth Feed first saw them, newest first. Pass since (YYYY-MM-DD) to get only those first seen on or after that day.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}The same facts as get_tool for 2 to 5 tools side by side.
| Parameter | Type | Description |
|---|---|---|
| domains * | array |
{
"name": "compare_tools",
"title": "Compare tools",
"description": "The same facts as get_tool for 2 to 5 tools side by side.",
"inputSchema": {
"type": "object",
"required": [
"domains"
],
"properties": {
"domains": {
"type": "array",
"items": {
"type": "string",
"maxLength": 120
},
"maxItems": 5,
"minItems": 2
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}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.
No parameters.
{
"name": "list_benchmarks",
"title": "List quantitative video benchmarks",
"description": "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 $/s leaders.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Get one standardized AI video benchmark suite by suite_id: frozen R2 input URLs and sha256 hashes, automated pass gates, and the full leaderboard ranked by cases passed and effective cost per usable second ($/s).
| Parameter | Type | Description |
|---|---|---|
| suite_id * | string | Suite id from list_benchmarks, e.g. "product-i2v-v1". |
{
"name": "get_benchmark",
"title": "Get a benchmark suite and leaderboard",
"description": "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).",
"inputSchema": {
"type": "object",
"required": [
"suite_id"
],
"properties": {
"suite_id": {
"type": "string",
"maxLength": 80,
"description": "Suite id from list_benchmarks, e.g. \"product-i2v-v1\"."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| category | string | Category id from list_categories. |
{
"name": "list_referrals",
"title": "List referral codes",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {
"category": {
"type": "string",
"maxLength": 60,
"description": "Category id from list_categories."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| url * | string | The tool’s URL or domain, e.g. "https://example.ai". |
| name | string | |
| note | string | What the tool does, in your own words. Stored for the maintainer; not published as is. |
| category | string | Category id from list_categories, if you know it. |
{
"name": "submit_tool",
"title": "Submit a tool",
"description": "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.",
"inputSchema": {
"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."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true
}
}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; "from_the_site" fields are the tool’s own words.
Names, descriptions and schemas were written by the server and are shown as data.