Unverified50% confidenceFactExact time
MCP servers usually provide a pagination mechanism (such as cursor-based pagination), returning partial results and a continuation token in the response, so the client must make multiple requests to obtain all the data.
1
Sources
50%
Confidence
Long-term
Relevance
10/25/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe Sampling mechanism in MCP allows a Server to request model inference from the client, making it a reverse invocation mechanism.79% similarVerifiedMCP supports progress notification and log feedback mechanisms, allowing an MCP Server to proactively return execution progress and real-time logs to the client during tool execution.79% similarUnverifiedMCP tool calls trigger real operations (writing to databases, sending emails, etc.), so permission control and audit logging are especially important at the MCP server layer, which differs from API integrations that are primarily read-only queries.76% similarUnverifiedMCP servers influence model behavior at two moments—through tool description text and through call return values—and both become attack surfaces.75% similarUnverifiedAudit logs for an MCP server should live on the server side; only server-side logs reflect what actually happened in the system, while client-side logs only reflect what the model requested.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1096091API
curl https://kongchang.com/api/v1/knowledge/claims/1096091MCP
get_claim(id=1096091)