Bench Agent DiscoveryVerifiedπ‘ No advisories
Provenancewhere it came from, and what was verified
Published to the official MCP registry by github.com/virajmishra1, which proved it owns this namespace.
π‘ Permissions & trustwhat this server can touch before you run it
About
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
Packages & transports
Computed from the server's own data, not a hidden formula. This measures how much you can depend on it, not how popular it is. Stars are shown separately, on purpose. How it's scored β
βΈsearch_agents83B
βΈget_agent100A
βΈlist_benchmarks100A
Structural, not an LLM's opinion: each check is a fact about the tool's schema, so it's reproducible. One weak tool drags the score (60% average, 40% worst). How it's scored β
Raise this grade
up to +9 on qualityOwn this server? Here's exactly what to change, biggest wins first. Every number below is a fixed point value, so you can see what each edit is worth before you make it.
With no reviews this sits at a neutral 11. Reviews reporting it works push it toward the full 20.
- 5 of 12 params have no description: `sort`, `limit`, `model`, `category`, +1 more. Describe each one.
- No `required` array. Declare which params are mandatory so an agent knows what it must provide.
Already earned (5) βΎAlready earned (5) β΄
These are structural checks, so the fixes are exact. See the full formula β
Add a badge to your README
[](https://socketcat.com/servers/io.github.VirajMishra1/bench)Shows your live quality grade and links back here. It updates itself as the grade changes.
Reviews
Sign in to leave a reviewNo reviews yet. Be the first to say whether it worked.
{
"mcpServers": {
"bench": {
"command": "npx",
"args": [
"-y",
"bench"
]
}
}
}βΆ Try itlive against bench.virajmishratakehome.workers.dev
This server has a hosted endpoint, so we can connect and list its actual tools right here. Nothing runs on your machine.