Read, replay and fork recorded coding-agent runs.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
orca_list_runsList every agent run recorded in this project, newest first, with the run it was forkedList every agent run recorded in this project, newest first, with the run it was forked
No input schema was published for this tool.
orca_show_runThe full timeline of one run: every model turn with its token counts and stop reason,The full timeline of one run: every model turn with its token counts and stop reason,
No input schema was published for this tool.
orca_checkpointsThe points in a run a fork can start from — where the conversation prefix is complete andThe points in a run a fork can start from — where the conversation prefix is complete and
No input schema was published for this tool.
orca_graphWhat caused what in a run, as a list of edges. Each edge says which event produced which,What caused what in a run, as a list of edges. Each edge says which event produced which,
No input schema was published for this tool.
orca_replayRe-run a recording exactly, with the network blocked and no tokens spent, and report whatRe-run a recording exactly, with the network blocked and no tokens spent, and report what
No input schema was published for this tool.
orca_compareFork one recorded run onto several models from the same checkpoint — same files, sameFork one recorded run onto several models from the same checkpoint — same files, same
No input schema was published for this tool.
6 of 6 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Read, replay and fork recorded coding-agent runs.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.