
Buildfeed MCP server
Which MCP servers are Buildfeed's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry nametech.buildfeed/buildfeedverified in the MCP registry
The registry name sits under buildfeed.tech. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools10
- Server calls itselfbuildfeed
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 154 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- Parameters are untyped or undescribed in 3 of 10 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score93 of 100answers 100 · definitions 78 · context 100 · connects 100
- Answered100% of days9 of 9 daily checks
- Median first answer259 ms
- Space in an agent's context≈ 1,945 tokensthe definitions of all its tools (10), which an agent carries on every turn
- Tool definitionsB · 78 of 100
- Typed results0 of 10 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 3 of 10
- Not saying whether it only reads or can destroy: 10 of 10
What an agent can do with it
- not sure · Browse daily picks on AI and startup topics
- not sure · Catch up on product and design talks
- cannot · Watch podcast interviews with AI and startup leaders
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_videosFull-text search over BuildFeed's curated AI/startup/VC YouTube video library. Scores videos by keyword match across title, topics, TLDR summary, channel name, and key takeaways, ranked by relevance (then recency). Use this when the user…
search_transcript_passagesSearch inside transcript passages, returning the most relevant timestamped excerpts across multiple videos. Use this for evidence, quotations, implementation details, or questions whose answer may not appear in a title or summary.
get_transcriptGet a bounded transcript window for one video. Prefer search_transcript_passages for discovery; use this tool to inspect surrounding context after selecting a video.
list_videosList curated BuildFeed videos, optionally filtered by category and sorted by recency, views, likes, or quality score. Returns compact video records (title, channel, categories, view/like counts, quality score) without transcript or…
get_videoGet full detail for a single BuildFeed video — description, channel info, stats, categories, topics, TLDR, and key takeaways (the raw transcript text itself is excluded). Accepts either an 11-character YouTube video ID or a BuildFeed…
list_channelsList YouTube channels tracked by BuildFeed, with per-channel video counts and categories, sorted by video count descending. Use this to discover which creators BuildFeed covers, optionally filtered to a category.
list_categoriesList all of BuildFeed's video categories (AI, VC, Startup, Product, Design, Tools) with the number of videos in each. Use this to understand the taxonomy before filtering search_videos/list_videos/list_channels by category.
list_topicsList canonical topic clusters from the full BuildFeed archive, grouped into stable families such as AI & Models, Building, Product, Startups, and Industry. Returns video counts, aliases, content-type distribution, and audience labels.
get_statsGet aggregate statistics for the entire BuildFeed corpus: total videos, channels, categories, topics, and views; the published-date range; and transcript/TLDR enrichment coverage. Use this for high-level "how much data / how fresh"…
get_weekly_roundupGet BuildFeed's weekly roundup content. Without a date, returns the index of available weekly roundups (most recent first) — useful for discovering which weeks exist. With a date (YYYY-MM-DD week key), returns that week's full roundup…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"buildfeed": {
"type": "http",
"url": "https://buildfeed.tech/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http buildfeed https://buildfeed.tech/api/mcpclaude.ai, ChatGPT and other clients: add https://buildfeed.tech/api/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.