registry / record
{"command":"npx","args":["-y","https://mcp.vespper.com/mcp"]}
Does {"command":"npx","args":["-y","https://mcp.vespper.com/mcp"]} MCP work in Claude Code and Cursor? Throne executed {"command":"npx","args":["-y","https://mcp.vespper.com/mcp"]} mcp in a single-use Firecracker microVM and replayed both recorded client behaviours. Compatibility verdict: inconclusive. Is {"command":"npx","args":["-y","https://mcp.vespper.com/mcp"]} mcp safe? Static security scan: not run (the server did not launch far enough to scan). The full per-step results, security findings, scan date, and evidence hash are below.
> throne registry {"command":"npx","args":["-y","https://mcp.vespper.com/mcp"]}
sealed
- scan id
- 6c3fb8c66692427eb02ac148005407bb
- target
- {"command":"npx","args":["-y","https://mcp.vespper.com/mcp"]}
- sealed at
- 2026-07-19 10:42:04Z
- evidence hash
- sha256:8f835e54a7d5fd63dde80318aebb3c204291d6aae6f8b548d9be72c0a175ae4d
RuntimeError: connect failed: McpError: Connection closed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
RuntimeError: connect failed: McpError: Connection closed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
not run, connect failed
- target
- {"command":"npx","args":["-y","https://mcp.vespper.com/mcp"]} config
- engine
- sandboxed
- claude code
- calibration: partial recorded=9,spec=0,assumed=9
- cursor
- calibration: partial recorded=11,spec=0,assumed=7
- chatgpt desktop
- calibration: unavailable recorded=0,spec=2,assumed=16
- steps exercised
- 18 of 18
- test suite
- v1.0.0
- security ruleset
- v1.0.0
- sealed at
- 2026-07-19 10:42:04Z
- evidence hash
- sha256:8f835e54a7d5fd63dde80318aebb3c204291d6aae6f8b548d9be72c0a175ae4d
- valid until
- 2026-10-17
maintainer of this server? challenge this record: hello@usethrone.dev. tell us what we got wrong and we re-run it in the open.
this page renders the stored record of a real run. nothing on it is asserted without the execution that proved it.