Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

Rubricv1.0
AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Glossary
Agents and protocols

MCP

Model Context Protocol

An open protocol that lets a model call external tools and read external data through a standard interface.

Before MCP, every integration between a model and an outside system was bespoke. MCP standardises the handshake: a server advertises the tools it offers and the resources it can read, and any client that speaks the protocol can use them without knowing anything about that particular server.

The consequence is that an MCP server is a piece of software you install and grant access to, in much the same way as a browser extension. That framing is the useful one, and it is the reason the security questions on this site look the way they do.

Why it matters

It is the reason a market for third party agent tooling exists at all. A standard interface is what makes a marketplace possible.

The mistake everyone makes

Treating an MCP server as a library rather than as software with privileges. A library runs where you put it. A server describes its own capabilities to a model that will then decide when to use them.

Related terms

MCP server
A program that exposes tools and data to a model through the Model Context Protocol.
Tool poisoning
Hiding instructions inside a tool description so the model reads them as commands.
Capability manifest
The declared list of tools a listing exposes, scopes it needs and hosts it may contact.
Previous
Lifecycle script
Next
MCP server

See MCP on a real listing

Every term here shows up in the catalogue next to a real result, with the findings published and the limits stated. Free to browse, no account needed.

Open the catalogue