Unverified50% confidenceFactExact time
The agents in the project access supplier websites via crawlers or APIs to scrape quote information, forming a chain of "running inside the sandbox → MCP gateway reading ERP → crawler fetching quotes → multi-model collaboration → ASGI streaming return".
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedThe intelligent procurement assistant accesses supplier websites via skills or web crawlers to scrape publicly available information such as pricing pages.72% similarUnverifiedProductBridge's AI agent can call users' APIs through tools, workflows, and MCP.72% similarUnverifiedThe technology stack of the explored project is: a React-based console for the frontend, HTTP for the communication layer, FastAPI for the backend, and Agent Service (including a control plane module and Agent Runtime) for the service layer.71% similarUnverifiedTool calls in AI Agent endpoints pass tenant context from the HTTP request all the way to the tool execution context, and agentRunner.ts explicitly extracts the tenantId and passes it into the tool execution context.69% similarUnverified科研自动化 Agent 通常基于 LLM 的工具调用与任务规划能力，结合代码执行沙箱、文件系统访问、学术检索及 GitHub/Hugging Face API 等外部工具，形成感知-规划-执行-反馈的闭环69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1051364API
curl https://kongchang.com/api/v1/knowledge/claims/1051364MCP
get_claim(id=1051364)