Records your screen and voice, returns one annotated screenshot and finding per mark.
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.
markdownDefault Markdown format — AI-ready, llms.txt-inspired structured documentDefault Markdown format — AI-ready, llms.txt-inspired structured document
No input schema was published for this tool.
jsonStructured JSON output for programmatic consumptionStructured JSON output for programmatic consumption
No input schema was published for this tool.
github-issueGitHub-flavored Markdown optimized for issue bodies with task lists and collapsible detailsGitHub-flavored Markdown optimized for issue bodies with task lists and collapsible details
No input schema was published for this tool.
linearLinear-compatible Markdown for issue descriptionsLinear-compatible Markdown for issue descriptions
No input schema was published for this tool.
jiraJira wiki markup with panels, tables, and {code} blocksJira wiki markup with panels, tables, and {code} blocks
No input schema was published for this tool.
capture_screenshotReturns a saved PNG path, markdown image reference, and captured cursor/window context for the current screen.Returns a saved PNG path, markdown image reference, and captured cursor/window context for the current screen.
No input schema was published for this tool.
capture_with_voiceReturns a structured report path plus transcript, extracted-frame, and processing counts from a timed screen-and-voice capture.Returns a structured report path plus transcript, extracted-frame, and processing counts from a timed screen-and-voice capture.
No input schema was published for this tool.
analyze_videoReturns a structured report path plus transcript, extracted-frame, and processing counts for an existing video file.Returns a structured report path plus transcript, extracted-frame, and processing counts for an existing video file.
No input schema was published for this tool.
analyze_screenshotReturns the captured screen as image data with its MIME type so a vision-capable agent can inspect it directly.Returns the captured screen as image data with its MIME type so a vision-capable agent can inspect it directly.
No input schema was published for this tool.
start_recordingReturns a session ID and recording status for a new long-form screen-and-voice session.Returns a session ID and recording status for a new long-form screen-and-voice session.
No input schema was published for this tool.
stop_recordingReturns the completed report path plus transcript, frame, and processing counts for the active recording session.Returns the completed report path plus transcript, frame, and processing counts for the active recording session.
No input schema was published for this tool.
push_to_linearReturns created Linear issue identifiers and URLs, or a dry-run preview, with one issue per report finding.Returns created Linear issue identifiers and URLs, or a dry-run preview, with one issue per report finding.
No input schema was published for this tool.
push_to_githubReturns created GitHub issue URLs and numbers, or a dry-run preview, with one issue per report finding.Returns created GitHub issue URLs and numbers, or a dry-run preview, with one issue per report finding.
No input schema was published for this tool.
describe_screenReturns a structured visual description of a fresh screen capture or supplied image, including UI, text, layout, and notable issues.Returns a structured visual description of a fresh screen capture or supplied image, including UI, text, layout, and notable issues.
No input schema was published for this tool.
14 of 14 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.
Records your screen and voice, returns one annotated screenshot and finding per mark.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
84 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+72 more not listed. The counts by reason above cover all of them.
Not followed: optionalDependencies, peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.