Cost of 13 back-office tasks per unit: person vs software, US, Greece, Ukraine. Sources cited.
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.
list_work_tasksList every task in the Cost of Work Index — the task id, what one unit is, and which AI employee performs it. Call this first when you do not already know the task id you need.List every task in the Cost of Work Index — the task id, what one unit is, and which AI employee performs it. Call this first when you do not already know the task id you need.
No input schema was published for this tool.
get_task_costWhat one unit of a given task costs in a given market — the human cost per unit, the AI cost per unit, and the ratio between them, with the source behind every figure. Markets: `us` (United States), `gr` (Greece), `ua` (Ukraine). Note that `uk` means Ukraine in this dataset, not the United Kingdom.What one unit of a given task costs in a given market — the human cost per unit, the AI cost per unit, and the ratio between them, with the source behind every figure. Markets: `us` (United States), `gr` (Greece), `ua` (Ukraine). Note that `uk` means Ukraine in this dataset, not the United Kingdom.
No input schema was published for this tool.
estimate_annual_costTurn a monthly volume of a task into monthly and annual cost, for a person and for the AI employee, in one market. Use this when someone asks what a workload costs them per year, or what they would save.Turn a monthly volume of a task into monthly and annual cost, for a person and for the AI employee, in one market. Use this when someone asks what a workload costs them per year, or what they would save.
No input schema was published for this tool.
list_sourcesThe official statistics behind the human-cost side of the Index — publisher, exact release title, resolvable URL, reference period, and how the published figure became the number used here. Call this when you need to cite or verify a figure.The official statistics behind the human-cost side of the Index — publisher, exact release title, resolvable URL, reference period, and how the published figure became the number used here. Call this when you need to cite or verify a figure.
No input schema was published for this tool.
get_cost_of_work_indexThe complete Cost of Work Index as JSON — every task, every market, every source, plus the caveats. Use this when you need the dataset itself rather than one answer; prefer `get_task_cost` for a single figure.The complete Cost of Work Index as JSON — every task, every market, every source, plus the caveats. Use this when you need the dataset itself rather than one answer; prefer `get_task_cost` for a single figure.
No input schema was published for this tool.
5 of 5 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.
Cost of 13 back-office tasks per unit: person vs software, US, Greece, Ukraine. Sources cited.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the depth-4 limit. Anything below that level was never resolved.
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)
54 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+42 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.