@rajatpal96/tokentrail-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 0 of 1 tool tried
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y -p @rajatpal96/tokentrail-mcp@1.0.8 tokentrail-mcp
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
1 tool that takes no input and looks read-only was called once with nothing. 0 returned a result.
budget_status | No usable answer tools/call timed out after 15000 ms |
During the calls (not necessarily because of them) it first contacted: api.tokentrail.xyz.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
usage_today organizationId
Get today's total AI agent token consumption, request count, and estimated cost across the organization.
usage_this_week organizationId
Get this week's AI agent token consumption, cost breakdown, and top agents.
usage_this_month organizationId
Get this month's AI agent token metrics and cost summary.
usage_current_session sessionId
Get real-time token consumption, latency, and cost for a specific active coding session.
usage_by_agent range
Break down AI consumption across agents (Claude Code, GitHub Copilot, Gemini/Antigravity, Codex, Grok).
7 more tools
usage_by_model range
Break down AI consumption and cost by model (Claude 3.7 Sonnet, GPT-4o, Gemini 2.5 Pro, etc.).
usage_by_project range
Break down AI spend and token usage by repository or project name.
cost_today
Get today's total estimated spend in USD across all AI coding assistants.
cost_this_month
Get this month's estimated USD spend vs budget allocation.
budget_status
Check organization monthly budget limit, current spend, and remaining allocation percentage.
top_expensive_sessions limit
List the most expensive AI coding sessions with agent names, token counts, and USD cost.
track_usage_event agent, model, promptTokens, completionTokens, sessionId, projectId
Directly record a token consumption or execution event from Antigravity/IDE into central AgentMeter.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | not stated |
| Source | not stated |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-pCjxqLZSZrlhwvWiWWaTfc+eB6nVzXaaOyUBqt/29+H6KgfFw76nxcwDFO1Jz0v0ZTkOePnAjEdQXUD2iTGtjQ== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40rajatpal96/tokentrail-mcp)
New version out? Ask for a fresh report.