MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Tokmeter — AI Agent Usage & Cost is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
178
downloads a day
local
runs on your machine
791
downloads in 30d
What it does
Tokens and cost for Claude Code, Codex and 14 more AI coding agents, from local session files.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user tokmeter-ai-agent-usage-cost-mcp '--' npx -y @sriinnu/tokmeter-mcp serve
# 2 — ask your agent for something these tools do
# tokmeter_pulse, tokmeter_models, tokmeter_providers and 21 more
Tokmeter — AI Agent Usage & Cost costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Tokmeter — AI Agent Usage & Cost as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user tokmeter-ai-agent-usage-cost-mcp '--' npx -y @sriinnu/tokmeter-mcp serveReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
24 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Get a quick pulse-check snapshot of token usage — total cost, tokens, active models, projects, and providers.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
Detailed per-model cost and token breakdown with visual bar charts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
| limit | number | no | Max models to show (default: 20) |
Compare token usage across providers (Claude Code, Cursor, Codex, Gemini, etc.).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
Show per-project token usage breakdown — cost, tokens, active days, models used, and date range.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
| limit | number | no | Max projects to show (default: 20) |
Show a day-by-day timeline of token usage with sparkline trends and daily cost/token breakdowns.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
| limit | number | no | Max days to show (default: 30, most recent first) |
Project future AI token costs based on historical burn rates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
Flexible search across all token usage records with filtering by model, provider, project, date range, and cost thresholds.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
| model | string | no | Filter by model name substring |
| min_cost | number | no | Minimum cost per record (USD) |
| max_cost | number | no | Maximum cost per record (USD) |
| since | string | no | Start date (YYYY-MM-DD) for custom date range |
| until | string | no | End date (YYYY-MM-DD) for custom date range |
| sort_by | string | no | Sort by cost (desc), tokens (desc), or time (desc). Default: time |
| limit | number | no | Max records to return (default: 25) |
Compare two or more models or providers side-by-side on cost, tokens, efficiency, and usage metrics.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| compare_type | string | yes | What to compare: models, providers, or projects |
| names | array | no | Specific names to compare (if omitted, compares top entries) |
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
Export token usage data as JSON, CSV, or Markdown.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| format | string | yes | Export format: json, csv, or markdown |
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
| data | string | no | Which data to export (default: all) |
Monitor spending against a budget with visual progress bars and alerts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| daily_budget | number | no | Daily budget in USD |
| weekly_budget | number | no | Weekly budget in USD |
| monthly_budget | number | no | Monthly budget in USD |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
Visualize activity patterns as a heatmap — see which hours of the day and days of the week have the heaviest usage.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
| metric | string | no | Heatmap metric: cost, tokens, or records (default: cost) |
Detect unusual spending patterns and anomalies in token usage.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
| sensitivity | string | no | Anomaly detection sensitivity (default: medium) |
Analyze cache hit rates, reasoning token ratios, input/output efficiency, and cost-per-token metrics.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
Rank models and providers by various metrics: total cost, cost-efficiency (cost per 1M tokens),
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rank_by | string | no | Ranking metric (default: cost) |
| entity | string | no | Rank models or providers (default: models) |
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| limit | number | no | Top N to show (default: 10) |
Generate a concise natural language summary of token usage — like a daily/weekly briefing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
Analyze your AI coding habits — active day streaks, weekend vs weekday usage, session frequency,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
Analyze cache hit/miss patterns across sessions. Shows overall cache hit rate, dollar savings from caching,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| period | string | no | Time period to analyze: today, week, or month |
| provider | string | no | Filter to a specific provider |
| project | string | no | Filter by project name/path substring |
Compare what you actually spent vs what cheaper models would have cost.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| period | string | no | Time period to analyze: today, week, or month |
| project | string | no | Filter by project name/path substring |
Proactive budget monitoring with configurable daily/weekly/monthly thresholds.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| daily_budget | number | yes | Daily budget in USD |
| weekly_budget | number | no | Weekly budget in USD |
| monthly_budget | number | no | Monthly budget in USD |
Analyze usage patterns and provide actionable cost optimization recommendations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| period | string | no | Time period to analyze: today, week, or month |
Preview what session data would be deleted for the given filters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
| since | string | no | Start date (YYYY-MM-DD) for custom date range |
| until | string | no | End date (YYYY-MM-DD) for custom date range |
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
DESTRUCTIVE: Permanently delete session data matching the given filters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Filter by project name/path substring |
| providers | array | no | Filter to specific providers (e.g. ['claude-code','cursor']) |
| since | string | no | Start date (YYYY-MM-DD) for custom date range |
| until | string | no | End date (YYYY-MM-DD) for custom date range |
| scope | string | no | Time scope: today, week (last 7d), month (calendar month), or all (default) |
| backup | boolean | no | Accepted for compatibility only: over MCP a tar.gz backup is always created before deleting, even when false |
| confirm | string | yes | Must be exactly 'DELETE' to proceed with deletion |
List available cleanup backups with metadata (date, size, providers, projects).
No parameter schema on file.
Restore session data from a cleanup backup. Requires confirm='RESTORE' as a safety guard.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| backup_id | string | yes | Backup ID to restore (from tokmeter_backups) |
| confirm | string | yes | Must be exactly 'RESTORE' to proceed |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under AGPL-3.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Tokmeter — AI Agent Usage & Cost or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 1.15.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings5 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest22a3dcfc7398022eeba0d46ed915dbf80b81ce4b050b460b7ed4fe858cab220b
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (24 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| tokmeter_pulse | no tags | |
| tokmeter_models | no tags | |
| tokmeter_providers | no tags | |
| tokmeter_projects | no tags | |
| tokmeter_timeline | no tags | |
| tokmeter_forecast | no tags | |
| tokmeter_search | no tags | |
| tokmeter_compare | no tags | |
| tokmeter_export | external-sink | external-sink: keyword "export_to" |
| tokmeter_budget | no tags | |
| tokmeter_heatmap | no tags | |
| tokmeter_anomaly | no tags | |
| tokmeter_efficiency | no tags | |
| tokmeter_leaderboard | no tags | |
| tokmeter_digest | no tags | |
| tokmeter_streaks | no tags | |
| tokmeter_cache_efficiency | no tags | |
| tokmeter_model_advisor | no tags | |
| tokmeter_budget_alert | no tags | |
| tokmeter_cost_optimization_tips | no tags | |
| tokmeter_cleanup_preview | no tags | |
| tokmeter_cleanup_execute | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| tokmeter_backups | no tags | |
| tokmeter_restore | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest22a3dcfc7398022e
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.15.0. Pin a release below and the command asks for exactly that one.
1.15.0
12 Oct 2026
latestNo release note was published with this version.
1.14.1
5 Oct 2026
No release note was published with this version.
1.14.0
3 Oct 2026
No release note was published with this version.
1.13.0
23 Sep 2026
No release note was published with this version.
1.12.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Tokmeter — AI Agent Usage & Cost can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.