Bench Agent Discovery
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
Open the source (opens github.com) https://github.com/virajmishra1/bench
Before you use it
- Runs on someone else's server: what you send it leaves your machine.
What it is
MCP servers from io.github.VirajMishra1.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
Remote endpoint (streamable-http)
https://bench.virajmishratakehome.workers.dev/mcp
From the server's entry in the official MCP Registry
Related
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
plzebo
MCP serversCost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts.
plzebo@0.2.0 -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Eclipse Proving MCP
MCP serversGoverned bench access for agents — signed mandates, pinned artifacts, evidence for every session.
-
blender-optics-simulator
MCP serversBuild, align & render a real optical bench in Blender; drivable by an AI agent over MCP.
blender-optics-mcp@0.24.4 -
super-log
MCP serversQuery your local super-log bench from an AI agent - read-only log tools over the hub.
@super-log/mcp@0.4.1