
Mcp MCP server
Which servers in the official MCP registry are Mcp's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-19
- Registry namemarket.mcp/gatewayverified in the MCP registry
The registry name sits under mcp.market. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-19
- Tools4
- Server calls itselfmcp.market
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 296 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- Parameters are untyped or undescribed in 2 of 4 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 score92 of 100answers 100 · definitions 75 · context 100
- Answered100% of days8 of 8 daily checks
- Median first answer365 ms
- Space in an agent's context≈ 570 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsB · 75 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 4
- Not saying whether it only reads or can destroy: 4 of 4
What an agent can do with it
- not sure · compare MCP servers using user reviews and scan grades
- not sure · check a server's safety scan before installing it
- not sure · find a server for a specific job, such as scraping pages
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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →
searchFind MCP servers for a job in plain words. Results are ranked by user rating first, then adoption. Each hit carries its rating, safety grade and adoption score. D and F grades are hidden unless min_grade says otherwise.
describeFull detail for one server: user rating and what reviewers said, safety grade and scan summary, adoption, price, and every tool with its input schema and whether it performs write actions.
callRun one tool on a listed server. The gateway meters the call, enforces your spend caps, and logs reliability data. F-graded servers are blocked.
balancePrepaid balance, today's spend, and this key's caps.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"gateway": {
"type": "http",
"url": "https://gw.mcp.market/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http mcp https://gw.mcp.market/mcpclaude.ai, ChatGPT and other clients: add https://gw.mcp.market/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.