
zhouzhou MCP server
Which MCP servers are zhouzhou'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 2026-10-27
- Registry namedev.deskfeed/deskfeed-apiverified in the MCP registry
The registry name sits under deskfeed.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools6
- Server calls itselfdeskfeed
- Server version0.6.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 92 ms.
- Its tools do none of the product's use cases we checked: verify and roll back failed steps in multi-agent pipelines; run a software delivery process as a multi-agent pipeline.
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 score68 of 100answers 100 · does the job 0 · definitions 83 · context 100 · connects 100
- What an agent can do with it0 of 2 use cases
- Answered100% of days8 of 8 daily checks
- Median first answer304 ms
- Space in an agent's context≈ 1,211 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 6 of 6
What an agent can do with it
- cannot · verify and roll back failed steps in multi-agent pipelines
- cannot · run a software delivery process as a multi-agent pipeline
- not sure · sell market data to other agents per call in USDC
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 →
market_stateMulti-timeframe market state for BTCUSDT, ETHUSDT, SOLUSDT, XRPUSDT & DOGEUSDT USD-M perpetual futures in one call: mark & index price, funding rate, open interest change, taker buy share, per-timeframe (4h/1h/15m) EMA-20/50, RSI-14, ATR…
event_factsVerified market-moving events for crypto agents: headlines categorized (liquidations, macro, regulation and more) and tagged to BTC/ETH, each with source, publisher, timestamp, original link, and a trust tier distinguishing primary…
bsc_alertsVolume-anomaly observations across newly created BSC pools, from a 15-minute monitoring sweep: pools whose hourly volume spiked vs the prior hour (floor $1,000 and 100x), with pool name, hourly volume, spike ratio, price move and source…
bsc_verdictBSC token risk verdict in one call: send a BSC token address, get a 0-100 score, A-F grade, a plain-language take, key risk facts (honeypot, taxes, liquidity, holder concentration, mint/ownership flags) and a shareable card link. Security…
bsc_pool_autopsyBSC pool autopsy in one call: pool age, liquidity, 1h/24h volume and transaction spike ratios, buy/sell pressure, holder concentration, LP lock, honeypot/tax/mint/ownership flags, and a 0-100 risk verdict with grade. Built from…
pingHealth check (free).
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"deskfeed-api": {
"type": "http",
"url": "https://deskfeed.dev/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http deskfeed https://deskfeed.dev/mcpclaude.ai, ChatGPT and other clients: add https://deskfeed.dev/mcp as a custom connector in the settings.
OpenAPI spec
5 paths, read 2026-10-27. Open the spec ↗
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.
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.