Unverified50% confidenceFactExact time
Plugins and MCP address the problem of enabling models to call external tools and actually get things done, as the model itself can only generate text.
1
Sources
50%
Confidence
Long-term
Relevance
9/27/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn MCP, Tools are invoked at the model's discretion, Prompts are triggered by the user, and Resources are controlled by the application.77% similarVerifiedBefore MCP emerged, major model vendors each implemented tool calling in their own way, forcing developers to rewrite all tool-calling code whenever the underlying model was changed.77% similarUnverifiedWrapping with MCP allows existing business logic to be reused without rewriting, simply by encapsulating legacy systems as MCP tools for large models to call.76% similarUnverifiedMCP Server Instructions are injected into the model's context when Codex connects to an MCP server, guiding the model on how to correctly invoke tools76% similarVerifiedBefore MCP emerged, the integration of large language models with external tools was highly fragmented, with OpenAI's Function Calling, LangChain's Tool framework, and various vendor plugin mechanisms being mutually incompatible.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/954387API
curl https://kongchang.com/api/v1/knowledge/claims/954387MCP
get_claim(id=954387)