MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Measure what Chinese/Cantonese actually costs in tokens - and why. MCP server: cross-script comparison, per-token attribution, reproducible benchmark.
MIT -
token-proctorgithub.com/navintkr/token-proctorupdated this year
VS Code extension + MCP server that validates prompts, routes to the cheapest LLM, and projects token × turn cost before the call. Cuts Copilot premium-request burn on agent loops.
MIT ★ 3 -
Track MCP server token usage and costs for AI coding tools
MIT ★ 2 -
💎 Semantic Context Compressor, Live Token/USD Cost Calculator & Adaptive Model-Tier Router MCP Server — Cut LLM token bills by 85% across Claude Code, Cursor, VS Code, Codex & Antigravity.
MIT ★ 1 -
llm-cost-estimator-mcpgithub.com/waqarulwahab/llm-cost-estimatorupdated this year
MCP server for LLM token counting and multi-model cost estimation (GPT-4o, Claude, Gemini, and 25+ models). Local-first, no API key.
npm MIT -
MCP server for current LLM API prices, cost estimates, model comparisons and the language token tax (OpenAI, Anthropic, Google). Open data by AiGanak.
npm MIT -
mcp-cost-trackergithub.com/user/mcp-cost-trackerupdated this year
MCP server that automatically tracks LLM API call costs, token usage, and generates visual dashboards. Supports OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Mistral and more.
npm MIT -
token-optimizer-mcpgithub.com/tjpatel16/token-optimizer-mcpupdated this year
High-performance MCP server for minimizing LLM token usage and API costs via structural code analysis and precision chunking
pypi MIT -
Token counts and LLM cost checks for prompts in your repo: a CI linter, pull-request cost diffs, and an MCP server. Runs locally; prompts are never uploaded.
npm UNLICENSED -
io.github.rccola990-cloud/mcp-token-optimizergithub.com/rccola990-cloud/mcp-token-optimizerno update data
Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
npm -
ComparEdge LLM Costno update data
Token cost math for LLM API calls: current per-million-token rates for 69 models across 17 providers, verified and date-stamped. Estimates single calls, comparisons across models, and monthly budgets. Zero dependencies, no API key.
smithery -
visantchigithub.com/pedrojaques99/visantchi-cliupdated this year
Local observability CLI for LLM usage — token costs, mascote, MCP server. Offline-first.
npm MIT -
CLI and MCP server that verifies AI coding agent context-reduction proxies' token and cost savings claims
pypi Apache-2.0 -
codeledgergithub.com/bhvbhushan/codeledgerupdated this year
Token-level cost intelligence for Claude Code — per-project, per-agent, per-skill usage tracking with conversational MCP querying and local dashboard
npm MIT -
tokenmarkupdated this year
Drop-in observability and cost tracking for LLM API calls. Wrap your provider client, log every call with cost/tokens/latency to JSONL, query via CLI or MCP.
npm MIT -
promptthrift-mcpgithub.com/woling-dev/promptthrift-mcpupdated this year
Smart token compression MCP server for LLM apps. Gemma 4 local compression, multi-model cost tracking, intelligent model routing. Save 70-90% on API costs.
MIT ★ 1 -
tokensavergithub.com/pozii/tokensaverupdated this year
MCP server that cuts AI agent token costs by up to 97% — compression, caching, pruning, web extraction
Apache-2.0 ★ 1 -
@iflow-mcp/flightlesstux-prompt-caching-mcpgithub.com/flightlesstux/prompt-cachingupdated this year
Automatic prompt caching for Claude Code. Cuts token costs by up to 90%.
npm MIT -
tokenwise-mcpupdated this year
Library + MCP server for reducing LLM token costs via compression, summarization, chunking, and Anthropic prompt-cache breakpoint planning
npm SEE LICENSE IN LICENSE -
91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
npm MIT ★ 582 -
agent-cost-tracker-mcpgithub.com/rumblingb/agent-cost-tracker-mcpupdated this year
MCP server: Track AI agent token usage and API costs — npm wrapper
npm MIT -
See what your MCP servers cost you in tokens — and cut it. Records every MCP tool call, itemises the per-session tax each server charges, and tells your coding agent what to remove. All local, zero config.
npm MIT -
ai-cost-calculator-apigithub.com/lazymac2x/ai-cost-calculator-apiupdated this year
AI Cost Calculator API - calculate token costs for GPT-4, Claude, Gemini. REST + MCP.
-
mcp-cost-trackergithub.com/cc-fuyu/mcp-cost-trackerupdated this year
MCP server that automatically tracks LLM API call costs, token usage, and generates visual dashboards. Supports 50+ models across OpenAI, Anthropic, Google, DeepSeek, Mistral and more.
MIT ★ 1 -
context-analyzergithub.com/manavgup/context-analyzerupdated this year
See where your Claude Code tokens go — cost per call scales 4.3x with context size. Hooks + SQLite + dashboard + MCP server for context window forensics.
pypi MIT ★ 21 -
skillfm-claude-code-token-usage-mcpgithub.com/ericm1018/skillfm-claude-code-token-usage-mcpupdated this year
SkillFM gateway MCP for Claude Code token usage and cost visibility.
npm MIT -
Cut 79-91% of the input tokens your logs and command output cost. MCP server or drop-in proxy: park bytes outside the conversation, fetch exact slices, draw a slice as dense PNG pages when that is cheaper - and it says when plain text is cheaper instead.
npm PolyForm-Noncommercial-1.0.0 -
What your coding-agent seats and tokens buy, from your own machine: Claude Code and Codex tokens and API-equivalent cost by day, project and model, burn toward your own limits, and a flag when the rate changes. Local, no account.
MIT -
Local-only MCP server for Claude Code usage: tokens, equivalent API cost, 5-hour blocks and context size, read from your own transcripts on disk. No API key, no network calls, nothing leaves the machine.
npm MIT -
tokenslimgithub.com/himanshudhawale/tokenslimupdated this year
Shrink the token cost of context you feed to LLMs — count tokens, estimate cost across models, and slim files (with a CI budget guard) before you send them.
MIT -
Zero-dependency CLI and MCP server for LLM token cost estimation, context budget enforcement, and prompt secret scrubbing.
MIT -
llm-cost-mcpgithub.com/comparedge/llm-cost-mcpupdated this year
MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge
npm MIT ★ 2 -
LLM cost calculator, token counter, latency benchmark, CI guardrail, MCP server, and VS Code/Cursor extension.
npm MIT ★ 1 -
An MCP server that predicts AI development duration and cost using diff tokens and regeneration rates instead of human-time.
GPL-3.0 -
LLM-COST-TRACKER-MCP-Server-NPM-Package-github.com/dominiquekossi/LLM-COST-TRACKER-MCP-Server-NPM-Package-updated this year
LLM Cost Tracker is a complete, production-ready NPM package that provides accurate token-based cost tracking for Large Language Models (LLMs). It includes a built-in MCP Server, a flexible budget manager, multi-provider support, usage analytics, cost simulation, and an extensible architecture for storage and pricing.
MIT -
Token and context budget for AI agents. Tracks spend, estimates the cost of reads, and tells an agent the cheaper path before it burns its budget.
npm MIT -
skillfm-mcpgithub.com/ericm1018/skillfm-mcpupdated this year
SkillFM Beacon MCP: AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits.
npm MIT -
claude-conduitgithub.com/Labontese/claude-conduitupdated this year
Token and agent optimization MCP server for Claude: smaller inputs, higher cache hit rates, per-session cost reports.
MIT -
MCP server: what a tokenized stock on Solana really costs against the real share
npm MIT -
seatledgergithub.com/agentwares/seatledgerno update data
Local ledger of Claude Code and Codex tokens, API-equivalent cost, limits and token-rate changes.
npm -
Local cost analyzer for AI coding agents: see where tokens and AI Credits go in Claude Code, GitHub Copilot Chat, pi and mitmproxy sessions. Turn-by-turn cost, prompt caching explained, cost by repository and project, replay on another model, tool-call audit, MCP server with interactive views. Also a VS Code extension: AI Credits Analyzer.
MIT ★ 1 -
Open-source Kubernetes FinOps operator: cost per namespace, team, GPU and LLM token, schedules that scale idle environments and cloud databases to zero, budgets, chargeback and right-sizing with a rollback guard. Helm chart, dashboard, REST API, MCP server.
Apache-2.0 ★ 7 -
MCP server for AI agent token-cost telemetry + quota-window awareness across Anthropic, OpenAI, Gemini, Ollama, AWS Bedrock. Per-agent + per-provider attribution, spend-spike anomaly detection, cheaper-model routing, monthly forecast, and 429-prediction tools that read rate-limit headers to project quota exhaustion before it happens. Reads cost-log JSONL with the standard schema.
pypi MIT License -
FastAPI service that routes each LLM request to a provider by prompt complexity and logs tokens and cost to Supabase, with a semantic cache and an MCP server.
MIT -
awesome-confluence-mcpgithub.com/mazhar480/awesome-confluence-mcpupdated this year
🚀 Token-efficient MCP server for Confluence. Reduces LLM costs by 76% via Markdown conversion. Supports listing, searching, and fetching pages.
MIT ★ 3 -
mcptokensgithub.com/dondai1234/mcptokensupdated this year
375 tokens in your agent's harness. One MCP tool that counts the tool-definition cost of any other MCP server.
pypi MIT -
claude-shrinkgithub.com/aghori3004/claude-shrinkupdated this year
Cuts Claude Code's file-reading token cost by ~46%. One MCP tool, 60-second install.
MIT -
Language server + MCP server behind the TokenBurn Zed extension: AI token and cost usage from local logs (pi, Zed, Claude Code, Codex, …)
cargo MIT -
Local-first MCP tools and dashboard for investigating Codex token usage, credits, costs, caching, and thread patterns.
pypi MIT ★ 196 -
astrag-mcpgithub.com/dong7812/ast-rag-mcpupdated this year
MCP server that reduces web page token cost by 90%+ via DOM AST extraction — no API key required
npm MIT -
MCP server for AI economics — 12 calculators for token cost, LLM energy, agent-hour, Proof-Adjusted Autonomy, revocation exposure. Free API, no key. By Michał Piszczek.
npm MIT ★ 1 -
Time estimation MCP server for AI agents: PERT, COCOMO II, Monte Carlo, sprint forecasting, token-to-time mapping, cost estimation, and schedule risk tools.
npm Apache-2.0 ★ 8 -
shared-context-cache-mcp-servergithub.com/AiAgentKarl/shared-context-cache-mcp-serverupdated this year
MCP server for shared context caching — AI agents share computed results to reduce token cost and latency
pypi MIT ★ 1 -
Ask DarkRoute what a token costs to trade, and whether it has a way out, from any MCP client.
npm MIT -
Task tracker for AI agents. You accept the result. Open-source and self-hosted, with tokens, cost and human review over MCP.
Apache-2.0 -
Azure FinOps playbook as code: 10 cost optimization patterns, AI FinOps (token attribution, routing, caching, PTU, ROI, eval gate) and an approval-gated FinOps agent over MCP. Offline, synthetic data, list-price snapshot.
MIT -
MCP server for forensic analysis of Claude Code sessions: where your tokens went, what it cost, and where to compact. No API keys, read-only, offline.
MIT -
Zero-cost token optimization engine for AI coding assistants (Claude Code, Cursor, Antigravity, Windsurf). Saves 70-95% tokens via AST skeletons, differential cache, and line slicing.
NOASSERTION ★ 6 -
MCP server and costfluent command line tool that let AI assistants such as Claude Code and Cursor, and your scripts and CI jobs, read your Costfluent cloud costs, saved cost reports, budgets and anomalies, and change them where an Owner allows it. They run on your machine with the API token you give them and never delete anything.
mcpb Apache-2.0 -
An MCP server and CLI to track model prices, detect volatility, and optimize token costs on OpenRouter.io for AI Agents such as Hermes or OpenClaw.
MIT ★ 2