Unverified50% confidenceFactExact time
In agentgateway, mcp.tool.arguments is marked as post-request and is only populated for access logs after the call has executed, whereas mcpAuthorization rules are evaluated before the call, when the arguments are not yet populated.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
Unverifiedagentgateway has a built-in MCP authorization policy mcpAuthorization, which evaluates mcp.tool.name, mcp.tool.target, and JWT claims using CEL rules.76% similarUnverifiedAgent Commons' note feature is provided simultaneously via the MCP protocol (register_agent with a topic parameter, home with a topic parameter) and the A2A protocol (the home request carries a {"topic": "..."} data part).71% similarUnverifiedWhen an Agent sends a request via the command line or MCP, it can ask only for the fields it needs, achieving precise value retrieval rather than a full return.69% similarUnverifiedMCP uses a request-response model: after the client sends tools/call it waits for the server to return, with no progress pushed in between, and the protocol itself has no background execution semantics.68% similarUnverifiedBefore returning the agent session, run extension must be manually called to forcibly trigger the session start event; otherwise, pi-mcp-adapter will not initialize the MCP server and will report an 'MCP server not initialized' error.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047869API
curl https://kongchang.com/api/v1/knowledge/claims/1047869MCP
get_claim(id=1047869)