- Conduid
- Marketplace
- #token-usage
MCP servers tagged token-usage
50 live MCP servers tagged "token-usage", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with token-usage.
Codeprism
An experimental, 100% AI-generated, high-performance code intelligence server providing AI assistants with a graph-based understanding of codebases.
Codeburn
Free, local tool to track AI coding token usage and cost across 31 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
Casbin Gateway
See what every AI coding agent on your machine is doing, and whether the API behind it is the one you paid for. Claude Code, Codex, Cursor, Gemini CLI and more: one endpoint for 4…
Agentacct
See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Cl…
Tura
Build agent that uses 80% less token and delivers better results.
Squadra
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall less…
Codex Hygiene
Codex skill for auditing and tuning Codex Desktop context/tool surfaces
Codex Usage Tracker
Local dashboard for understanding where your Codex tokens and usage credits are going.
Lemoncrow
Faster runtime for coding agents. Make coding agents 25% faster and 30% cheaper on average while keeping the quality same or more. Same Task, Same Quality, Faster and Cheaper.
Gantry
A native macOS dashboard for Claude Code, Codex & other AI coding tools. Inspect quota, context & MCP; preview fixes and undo. Free for personal use. Closed-source.
Beezi Claude Plugin
Official Beezi plugins for Claude. Track what AI-assisted work costs per session in Claude Code, get a personal usage summary on demand, and draft tickets from claude.ai — all u…
EzCoworker
A multi-user Claude Code CLI based Coworker with Multi Agent Orchestrator, Multi model support including Ollama models, Advanced Functional skills, Channel integration for Chat an…
AgentHarbor
🚢 One native app for all your AI coding agents - live rate limits, session usage, deep analysis of your & monthly spend for Claude Code, Cursor, Codex, Gemini etc plus one-click M…
8v
8v is one binary that reads, writes, searches, checks, builds, tests, and formats code, using fewer input and output tokens than the agent's native tools.
Opencode Lazy Loading
Opencode lazy load plugin Saves 85%+ on tools and MCP servers tokens per request. The LLM loads tool instructions on-demand instead of receiving thousands of tokens of schemas it…
Agent Connector
SDK/runtime for branded MCP packages: declare your server + hooks once, install across the current AI-agent coverage matrix, and collect local-first token telemetry.
Agent Context Cost
Claude Code context window and token usage audit: see what your skills, subagents, plugins, CLAUDE.md and MCP servers cost before you type, ranked, with duplicates flagged and rem…
Tallybook
Prices your Claude Code and Codex sessions from the transcripts on disk, shows what each agent cost over any period, and tells you in plain English what would have been cheaper. C…
CodePrism
Standalone Python package + MCP server that builds and maintains a persistent knowledge graph of any codebase, exposing precise, token-efficient context to AI coding agents.
Fleetdiff
See what changed in your agent app's token usage, from summary files instead of raw traces.
Context Tax
What Claude Code sends on every turn before you type a word: what it costs, which of it you never used, and which of your skills never reached the agent.
Fapony
Token usage across Claude Code, OpenCode, Codex & ZCode on one yardstick — plus a project memory and convention-debt tracker agents can query via MCP. No server, your data stays l…
Agentic Coding Harness
Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI. Normalized events, cache-aware token usage, cost accounting verified against each agent'…
Context Tax
What your coding agent's context costs you every turn, and which of it you never used.
SpikeBridge
Local-first MCP multi-agent workbench: dual Codex accounts, web quota cards, Experience Memory, token analytics, remote Mac worker and Safe-Boot.
Agentobs
Stop your AI coding agent before it overspends. Budget limits, guardrails and cost tracking for Claude Code - local-first, no account.
AI Harness Character Creator
AgentDeck: one local GUI to configure every AI coding agent. Tune behavior, permissions, token usage and cost, skills, subagents, MCP servers and hooks for Claude Code, Codex CLI,…
Agentlens
Local-first AI agent debugger: trace waterfalls, LLM cost & token analysis, MCP inspection, retry/loop detection. English / 中文. 开源 AI 智能体调试与可观测性工具。
AgentGuard
Protect AI agents by detecting and blocking prompt, command injection, Unicode bypass, and social engineering attacks with customizable security controls.
Glm Coding Plan Statusline
GLM Coding Plan 智能状态栏 - 帮助用户实时掌握套餐使用情况
Claude Code Lens
Local monitor for Claude Code API traffic, logs, prompts, and tools
Tokenscope
See what your AI-coding session actually cost — and what is eating your context. Local, read-only CLI for Claude Code.
foldwork-dev/mcp-injector
89% on real codebases (verified across Django, Tokio, Gin, and more). Single Go binary, zero config. Free for codebases under 100K lines.
Kyber Weave
Kyber-Weave is a DocGraph CLI, library, and MCP server that increases documentation and code quality while reducing agent token spend through an opinionated ontology and ranked, c…
Agent Cost MCP
MCP server for tracking AI agent costs in real time. Per-message spending, budget alerts, visual dashboard. Works with Claude Code, Cursor, Windsurf, Codex, Gemini CLI, OpenClaw.…
AI Runtime Meter
AI Runtime Meter gives developers a live token, cache & cost meter for Claude Code. Shows tokens, cache, model, source , cost and session totals per request. Run from any terminal…
ClaudeCode Token Universe
Local, single-file HTML dashboard for Claude Code usage and estimated USD cost — token totals across all classes (input/output/cache), per-model spend at list API prices, live cur…
Agent Budget
Budget enforcement and spend tracking for autonomous agents — per-agent limits, threshold alerts, cost analysis. MCP server.
AI Insights
Understand and improve how you use AI coding tools. A local web app that turns raw usage data into a live dashboard — token counts, costs, session history, and configuration healt…
Chaukas SDK
One line to instrument your agent and capture every event in an immutable, queryable audit trail.
Meterly
Where your Claude Code spend actually goes — per project, model, MCP server, MCP tool, session and branch. Budgets that warn before you overrun. Local-first, zero deps, no API key.
Claude Contextlens
See where your coding agent's tokens actually go. Local usage analytics and setup audit for Claude Code: cost, prompt-cache economics, context growth, 5-hour billing windows, and…
Agentxray
X-ray for your AI agents - see where your agent burns time, tokens and money
Tokenarchive
Daily snapshots of your AI coding usage, kept forever: local dashboard, optional Cloudflare Worker backup, MCP servers over both.
Agent Harbor Observatory
AI Agent Cost Control & Usage Analytics Dashboard 2026: Monitor Claude, Cursor & Codex Spend
Pi Meter
Cross-session LLM spend tracking, budget alerts, and auto-downshift for AI coding agents (CLI + MCP + Claude/Cursor skill + pi extension).
Claude Quota Planner
Claude Code quota planner: a status line for your 5h/7d windows — or your USD budget on pay-per-token auth — plus an MCP server that says whether a task fits before you start it.
AI Agent Bridge
AI Agent Bridge for VS Code — local models, DeepSeek, Codex, and Claude with native tools, memory, context control, and diagnostics.
Shuttle Stack
Local-inference layer for coding agents: your files are read by llama.cpp on your machine, not by your agent's context. MCP, rootless Podman, no egress, cited answers, measured.
Tokendog
Watchdog for Claude Code token spend: prices every turn from authoritative usage and tells you which sessions to close. Local-only, nothing leaves your machine.