MCP
The Model Context Protocol (MCP) is an open protocol for connecting AI applications to external tools, data and prompts through a standard client–server interface, built on JSON-RPC.
Servers expose tools, resources and prompts; clients such as chat apps and coding agents discover and call them. The specification covers transports (stdio and streamable HTTP) and OAuth-based authorisation; the current revision is dated 2026-07-28.
Kojen runs an MCP server so agents can drive its full train, evaluate and deploy loop.
Learn more on Kojen
Related terms
- OpenAI-compatible APIAn OpenAI-compatible API accepts the same request and response format as OpenAI's Chat Completions endpoint, so existing SDKs and tools work with it by changing only the base URL and key..
- Context engineeringContext engineering is designing everything that goes into a model's context window, instructions, tools, retrieved documents, memory and history, so an agent has the information it needs and little else..
- Prompt injectionPrompt injection is an attack in which text supplied to a language model overrides or subverts its intended instructions, for example "ignore previous instructions and…"..
Sources
- Model Context Protocol. Model Context Protocol Specification, revision 2026-07-28
- Kojen. Kojen developer docs: REST API, MCP server and endpoints
Put the definitions to work.
Kojen evaluates, tunes and red-teams your agents with these methods built in: Wilson intervals, pass^k, LLM judges with visible components. Free to start.
Start training free