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.
-
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 -
Local-first Claude Code cost analyzer. Parses JSONL session logs to surface per-tool spend, daily trends, and optimization hints.
npm MIT -
@vk0/agent-cost-mcpgithub.com/vk0dev/agent-cost-mcpupdated this year
Local-first MCP server for Claude Code cost analysis, budgets, forecasts, anomalies, and subagent-aware optimization from local JSONL session logs.
npm MIT -
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 -
LLM cost calculator, token counter, latency benchmark, CI guardrail, MCP server, and VS Code/Cursor extension.
MIT ★ 1 -
agent-cost-mcpgithub.com/vanthienha199/agent-cost-mcpupdated this year
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. Stop overspending on AI APIs.MCP server that tracks AI agent spending in real time. Visual dashboard, budget alerts, 15+ models. Works with Claude Code, Cursor, Windsurf.
MIT ★ 1 -
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 -
tokenscopegithub.com/wartzar-bee/tokenscopeupdated this year
See what your AI-coding session actually cost — and what is eating your context. Local, read-only CLI for Claude Code.
MIT ★ 4 -
Audit your repos and cloud providers for CI and infrastructure cost leaks. CLI + MCP server for AI coding agents (Claude Code, Codex, any MCP host).
MIT ★ 2 -
Track what every AI coding agent costs and see the limit coming. Per-session, per-model cost for Claude Code, Codex, Cursor and 37 more tools from your provider's own token counts, plus limit gauges, a dangerous-command guard and dashboard terminals. Free, Apache-2.0, runs on your machine.
NOASSERTION ★ 60 -
prompt-squeezegithub.com/joshua-burnell-1/prompt-squeezeupdated this year
Builds prompt-cost discipline into Claude Code: measure every prompt, surface avoidable spend, report org-wide. Skill + UserPromptSubmit hook + MCP rollup with cited dollar/Wh/CO2e receipts.
Apache-2.0 ★ 1 -
💎 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 -
claude-code-minimaxgithub.com/slantidawg/claude-code-minimaxupdated this year
Claude Code plugin: delegate scoped coding tasks to MiniMax-M2.7-highspeed via Anthropic-compatible endpoint, with Sonnet/Haiku fallback. Bundles MCP server, orchestration-discipline skill, and cost-summary slash command.
MIT -
preflightgithub.com/preflight-dev/preflightupdated this year
✈️ 24-tool MCP server for Claude Code: preflight checks for your prompts, cross-service context, session history search with LanceDB vectors, correction pattern learning, cost estimation
MIT ★ 13 -
Claude Code plugin marketplace: 6 local-first MCP servers for safer AI coding — MCP security, Postgres migrations, OpenAPI breaking changes, npm deps, LLM costs, SEO.
MIT -
Local-first MCP server that reports real token usage and cost across coding agents (Claude Code, OpenCode, Codex CLI). Nothing leaves your machine.
npm MIT -
Dead man's switch, cost cap and outcome check for unattended AI agents (Claude Code, OpenClaw, n8n, cron)
MIT -
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's own records, budget caps, OpenTelemetry gen_ai spans, Langfuse traces, and a live web dashboard + MCP server.
npm MIT ★ 2 -
Observability for AI coding assistants — cost tracking, efficiency scoring, and anti-pattern detection for Claude Code, Cursor, Copilot, and more. Local-first; New Relic optional.
npm Apache-2.0 ★ 67 -
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
pypi MIT ★ 129 -
Cost-aware, local-first skill routing for AI agents. MCP server + CLI + Claude Code hook. Tested on 141 real skills.
MIT ★ 1 -
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. CLI, Browser UI and MCP server.
MIT ★ 5 -
Local, read-only web explorer for your ~/.claude folder — Claude Code sessions, estimated cost, context-window usage, and a workflow view by skill, ticket & branch. Ships an MCP server.
MIT ★ 1 -
Free construction MCP server for Claude, Cursor and AI assistants: cost codes, CPM critical path, pay applications, change orders, earned value, quantity calculators. Offline, no dependencies.
NOASSERTION ★ 3 -
claude-model-routergithub.com/korelex/claude-model-routerupdated this year
Routes each task to the cheapest Claude model that still clears the quality bar — a Claude Code skill + MCP server that optimizes total cost to an acceptable answer, not sticker price.
MIT ★ 3 -
aws-calculator-mcpgithub.com/Musheer360/aws-calculator-mcpupdated this year
MCP server for AWS Pricing Calculator — create estimates, get actual costs, shareable links. All 436 services, Savings Plans, Reserved Instances. Works with Claude, Kiro, Cursor, VS Code.
npm MIT ★ 8 -
Multi-LLM MCP server for Claude Code & Codex — route AI agent work across 20+ low-cost provider buckets with round-robin dispatch and quota-aware fallback.
npm MIT -
MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers per task, cost receipt on every call. Zero dependencies.
npm MIT ★ 50 -
Cut Claude Code costs: Claude stays the brain while its subagents run on cheaper models (OpenRouter, DeepSeek, Qwen, GLM, Kimi). Rust CLI, local proxy and MCP server with secret/PII redaction, budgets and savings reports.
MIT ★ 1 -
costapi-mcpgithub.com/aethar-dev/costapi-mcpupdated this year
MCP server for CostAPI — Cost of living, CPI, PPP data for 190+ countries. Connect Claude, Cursor, or VS Code to cost-of-living data.
MIT -
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 ★ 581 -
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 -
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.
Apache-2.0 -
MCP server for Zentria Flow: US tariff layers by HTS code and origin, origin comparison, HTSUS search and landed cost. Planning estimates, not customs rulings.
NOASSERTION -
agent-tts-free-mcpactive
Zero-cost, unlimited neural voice generator & MCP server for AI coding agents and autonomous content pipelines. Powered by Edge neural speech.
npm MIT -
MCP server for US import duty research — HTS codes, Chapter 99 duties (Section 301 / IEEPA), MPF/HMF fees, and landed-cost math from official USITC data.
MIT ★ 3 -
Local MCP server that gives coding agents a verifiable project memory, trims what enters their context, and masks secrets — with honest accounting of what it saves and costs.
npm MIT -
Model Context Protocol (MCP) server for an equipment maintenance log and schedule: service entries, costs, and what is due or overdue. Equipment maintenance log: assets, service entries with costs, and a due report computed from stored dates. Works with Claude Desktop, Claude Code and Cursor.
MIT -
Cost-optimized MCP coding executor for Claude Code and Codex
npm MIT -
See what each AI agent, client and job costs, in dollars at list price, and give any job a spend ceiling: preflight answers approved: false past it, and your code decides. An SDK and an HTTP API, not a proxy.
MIT ★ 7 -
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
npm MIT -
@iflow-mcp/howardpen9-kimi-code-mcpgithub.com/howardpen9/kimi-code-mcpupdated this year
MCP server for Claude Code × Kimi K2.5 (256K context) — delegate bulk codebase analysis to Kimi, save 90% on token costs
npm MIT -
Cerver for Claude Code: an AI backend for your app, with cost and caps for each customer
MIT -
@kevinrabun/judgesgithub.com/kevinrabun/judgesupdated this year
45 specialized judges that evaluate AI-generated code for security, cost, and quality.
npm MIT -
Precise Symbol-Level Code Retrieval MCP Server: Cut AI Token Costs 95% in 2026
-
intent-codegithub.com/harsharahul/intent-codeupdated this year
Intent-aware code-knowledge index for LLM agents, built on intent-db: index a repo once, query it by intent, cut the token cost of re-reading files.
pypi MIT -
@nomadop/session-watchergithub.com/nomadop/session-watcherupdated this year
Local Claude Code context-cost monitor, transcript replay, buckets, and handoff
npm MIT -
@iflow-mcp/kevinrabun-judgesgithub.com/kevinrabun/judgesupdated this year
45 specialized judges that evaluate AI-generated code for security, cost, and quality.
npm MIT -
hivecodegithub.com/JasonDiazTTB/hivecodeupdated this year
Real-time analytics dashboard for Claude Code — track sessions, tools, files, and costs via MCP
MIT ★ 1 -
Top Token-Saving AI Coding Tools 2026: Local Memory MCP Cuts Costs 90%
★ 1 -
judgesgithub.com/KevinRabun/judgesupdated this year
MCP server with specialized judges to evaluate AI-generated code for security, cost, scalability, cloud readiness, and best practices.
npm MIT ★ 7 -
locus-memorygithub.com/magnifico4625/locusupdated this year
Persistent project-aware memory for AI coding tools. Built on MCP. Knows your project, remembers your decisions, costs almost nothing.
npm MIT -
MCP server that lets Claude Code hand bounded coding tasks to cheap models, behind tests, a second-model review and cost caps.
-
Best Token-Efficient AI Coding Tools 2026 – Reduce Costs 90% with Local Memory & MCP
★ 1 -
A fact base and lenses for any codebase. Zero-LLM-cost indexing, MCP server for coding agents, BYOK.
MIT -
An evaluation infrastructure layer for autonomous coding agents. Measure true FinOps costs, cache economics, and risk-aware routing for Claude Code.
-
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 -
@rulecatch/ai-poolergithub.com/thedecipherist/rulecatch-sdkupdated this year
Monitor and track AI coding activity in Claude Code — real-time analytics, token usage, cost tracking, rule enforcement. Zero overhead.
npm MIT -
mcpgithub.com/supermodeltools/mcpupdated this year
Save up to 40% on agent token costs with code graphs: call graphs, dependency graphs, dead code detection, and blast radius analysis.
MIT ★ 17 -
Building permit requirements, code references, OSHA compliance, and cost estimation
npm MIT