Unverified50% confidenceFactExact time
A complete Agent typically consists of multiple components including prompts, MCP Server configurations, Skills, and policies, making it a composite entity rather than a single weight file.
1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAgentOS 包含多个分工明确的专精智能体（规划智能体、资深开发、审查协调员等），每个都有专属prompt、技能集、MCP连接和知识库78% similarVerifiedDuring the reasoning process, an MCP Agent autonomously decides whether to call a tool, which tool to call, and what parameters to pass in through its Function Calling capability, and the entire process is multi-turn and iterative.76% similarUnverifiedThe progressive disclosure mechanism means that even if an Agent is equipped with hundreds of skills, the actual context usage during runtime may be equivalent to only that of an MCP solution using 3–5 tools.75% similarUnverifiedIn the agent domain, an "expert" is essentially a combination of pre-configured system prompts and specific tool permissions, while a "skill" is closer to the concept of an MCP or traditional API plugin.74% similarVerifiedThe generated Agent configuration includes tool permission settings that specify which tools the Agent can use, and supports manual adjustment afterward.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958540API
curl https://kongchang.com/api/v1/knowledge/claims/958540MCP
get_claim(id=958540)