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.
-
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 -
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 -
llm-pricesgithub.com/benbencodes/llm-pricesupdated this year
Zero-dependency Python CLI + MCP server for comparing LLM API costs across 144 models and 22 providers (OpenAI, Anthropic, Google, Mistral, xAI, DeepSeek, Groq...)
MIT ★ 2 -
See what your LLM calls cost and how much you'd save by switching models — local MCP server, no API keys.
npm 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
MIT ★ 2 -
gcp-cost-mcp-servergithub.com/nozomi-koborinai/gcp-cost-mcp-serverupdated this year
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go
MIT ★ 23 -
Remote MCP server + REST API: US salary, 2026 tax & cost-of-living data (BLS/BEA/Census/IRS). Live at api.kultranz.com/mcp — free, no key.
MIT -
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 -
The headless FinOps intelligence layer: API-first, agent-first cost control for cloud + AI. Connect your cloud stack in Claude, Cursor, or the terminal, and gate what agents do to your infra before they act. Propose-only. Open source, local-first.
Apache-2.0 ★ 20 -
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 -
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 -
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 -
@deusflight/graziechef-mcpactive
MCP server for restaurant kitchens: food cost, menu price with VAT, recipe scaling with batch cost, and the EU 14 allergens matrix. Pure calculations, no API key.
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 -
ace-mcp-servergithub.com/rocky007cn/ace-memoryupdated this year
Ace MCP Server — Free AI memory that learns. Zero cloud, zero API keys, zero cost.
pypi BSL-1.1 -
ALPNAI tools for authorized AI agents: deterministic cost, latency and quality analysis, reproducible examples, API/MCP integration and report delivery.
NOASSERTION -
MCP server for AI economics: token cost, context windows, agent-hour cost, LLM energy, joules per verified task, Proof-Adjusted Autonomy, revocation exposure and more. Wraps the free piszczek.pl/tools API — no key required.
npm MIT -
MCP server for quelllm.fr — 250+ open-weights LLM catalog. Tools: list/compare/estimate VRAM/estimate cost API vs self-hosted.
MIT -
cloudcost-mcpgithub.com/marilynceo/cloudcost-mcpupdated this year
Cloud cost and usage intelligence for AI agents u2014 track cloud spending, detect anomalies, forecast costs, and optimize resource usage across AWS, GCP, and Azure. SQLite-backed with zero external API costs.
-
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.
MIT ★ 1 -
deep-research-hub-mcpgithub.com/thedapperdev/deep-research-hub-mcpupdated this year
Deep research MCP server for Claude — Perplexity & OpenAI APIs with cost tracking, batch queries, gap analysis, and prompt enrichment. Local self-hosted TypeScript research agent.
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 -
Real-time SAM.gov federal contract opportunity and RFP tender monitor. Zero-cost public API feed. MCP Server & Python SDK.
MIT -
Automate tweets, replies, likes, retweets, follows, and DMs with low-cost X/Twitter API calls via OpenClaw and Xquik integration.
-
llmabacus-mcpgithub.com/szp2005/llmabacus-mcpupdated this year
Official MCP server for LLM Abacus - live LLM API pricing lookup & cost estimation. Remote endpoint, no API key.
MIT -
An MCP Server that works with Roo Code/Cline.Bot/Claude Desktop to optimize costs by intelligently routing coding tasks between local LLMs free APIs and paid APIs.
★ 43 -
MCP Server for TRANSCEND Route Optimization API. Model Context Protocol tools for route optimization, toll costs, weather, POIs, traffic and fuel stations. Compatible with Claude Desktop, Cursor and any LLM supporting MCP.
MIT -
Lead Green: the energy and CO2e cost of LLM tokens, per model, GPU and country. Open data, JSON API and MCP server behind leadgreen.ai. A Katonic project.
Apache-2.0 -
arthur-mcpgithub.com/zachdelong/arthurupdated this year
Ground truth verification for AI-generated code plans. Catches hallucinated file paths, schema references, imports, env vars, types, API routes, Express/Fastify routes, and Supabase schema — deterministically, zero cost, no API key.
npm MIT -
Perplexity MCP server and CLI in Python: Agent, Search, Embeddings and Decisions APIs, model routing, local chat history, usage and cost tracking
MIT ★ 3 -
screenshot-mcpgithub.com/marilynceo/screenshot-mcpupdated this year
Web Page Capture and Visual Verification Assistant u2014 take, compare, annotate, and convert screenshots; generate PDFs from any URL. Playwright-powered, zero external API costs.
-
gsa-perdiem-mcpgithub.com/1102tools/federal-contracting-mcpsupdated this year
MCP server for GSA Per Diem Rates API. Federal travel lodging and M&IE rates for IGCEs and travel cost estimation.
pypi MIT -
npubmailno update data
Your agent's own email inbox, owned by a Nostr key. No signup, no password, no API key. Receive verification codes, read replies, send mail. Receiving is free; mailing someone new costs a few sats over Lightning.
smithery -
cronmaster-mcpgithub.com/marilynceo/cronmaster-mcpupdated this year
Job scheduling and workflow orchestration for AI agents u2014 schedule, monitor, and orchestrate recurring jobs with dependencies, retries, logging, and alerting. SQLite-backed with zero external API costs.
-
MCP server for CostBench — verified software pricing, hidden costs, negotiation data, price history & TCO for 3,290+ products. Read-only, no API key.
MIT -
- A Vibe Coded Project - Connect Claude Code to local LLMs through LM Studio APIs via MCP bridge. Multi-model support, hot reload, dynamic MCP discovery. Access filesystem, database, web, git, and more. Zero API costs, full privacy, test coverage. Inspired by infinitimeless/LMStudio-MCP.
MIT ★ 3 -
print-advisor-mcpgithub.com/vandurmedries/print-advisor-mcpupdated this year
MCP server that calculates 3D printing cost, time, material and build-plate fit from plain dimensions — no file upload, no API key.
-
Lulu Printno update data
Integrate print-on-demand services with your applications by managing print jobs, validating files, calculating costs, and handling shipping through Lulu Print API. Streamline book printing workflows and track order statuses seamlessly. Enable webhook subscriptions for real-time print job updates.
smithery -
perplexity-mcpgithub.com/teoobarca/perplexity-mcpupdated this year
Free Perplexity AI MCP server with multi-account pooling, React admin dashboard, zero-cost health monitoring, and Telegram alerts. No API keys needed.
MIT ★ 14 -
pricewatch-mcpgithub.com/marilynceo/pricewatch-mcpupdated this year
Competitive price monitoring for AI agents u2014 track competitor pricing, detect price changes, and optimize pricing strategy. Monitor any product across the web from your AI agent. SQLite-backed with zero external API costs.
-
MCP server for the Yandex Delivery (Dostavka) B2B API: calculate cost, create and track courier, pickup point and parcel locker shipments from an AI app
MIT -
job-search-assistantgithub.com/MezaGabriel/job-search-assistantupdated this year
AI job-search copilot for Claude Desktop — MCP server that sources, scores, tailors CVs/covers, and preps interviews. Runs on your own Claude subscription, no API costs.
-
Compares perp funding, fees and slippage across Strike, Hyperliquid and OKX to show where Strike has the edge, after costs. Web dashboard, JSON API, MCP server for AI agents, and historical report. Built for the Strike Finance hackathon.
MIT -
A guard-first MCP server for the EODHD market-data API: catches silent failures (frozen codes, NA quotes, empty answers), says raw vs adjusted, and counts every call's cost.
MIT ★ 1 -
Badgr — GPU Compute, AI Model Deployment & Agent Executionno update data
**Run GPU workloads, deploy AI models, access inference APIs, and execute AI agents using Badgr's MCP server.** Badgr is an AI compute and workload execution platform for developers, coding agents, and AI assistants. Run workloads on cloud GPUs or compatible customer-owned GPUs (BYO GPU), with cost controls, execution logs, and verified results. **What can Badgr do?** - **GPU Compute / AI Workloads:** Run Python scripts, machine learning jobs, batch inference, and supported ComfyUI workflows. - **AI Model Deployment:** Deploy and serve LLMs using compatible runtimes such as vLLM and SGLang. Get a verified, OpenAI-compatible inference endpoint. - **AI API / LLM Inference:** Make AI API requests with response validation, supported fallback routing, and bounded execution. - **AI Agent Execution:** Launch coding and testing agents, run tasks, check acceptance criteria, and retrieve execution receipts. **Key features:** Cloud GPU execution, BYO GPU support, model serving, AI agent jobs, workload verification, execution logs, cost limits, and deployment management. Connect Badgr to your MCP-compatible AI assistant to execute real workloads instead of just generating instructions. Get started: https://aibadgr.com **Requires a Badgr API key. GPU workloads and other paid execution may incur usage charges.**
smithery -
longform-memory-mcpgithub.com/emberspun/longform-memory-mcpupdated this year
MCP server giving your AI writing assistant a constant-size memory of a long document. Chapter 1000 costs the same tokens as chapter 10. Local-only: no account, no API key, no network.
MIT ★ 1 -
Scrapogithub.com/vikast908/Scrapoupdated this year
AI-native, agent-first web scraping for Python. Cost-aware tiered fetching (HTTP, browser, stealth, agent), model-agnostic LLM extraction with self-healing selector caches, API-first resolution, deterministic replay and field-level diff, and an MCP server.
MIT ★ 4 -
longform-memory-mcpgithub.com/emberspun/longform-memory-mcpupdated this year
MCP server that gives your AI writing assistant a constant-size memory of a long document. Chapter 1000 costs the same tokens as chapter 10. Local-only: no account, no API key, no network.
npm MIT -
Two MCP tools instead of an API catalog: search finds endpoints, run executes model-written Python in a sandbox with memory and allowlisted HTTP. 217 tokens for the whole toolset; 1272 GitHub endpoints cost 79,525 tokens as plain tools.
npm MIT -
给中文网文作者的本地写作工作台(22 个工具):动笔前取齐上一章承接口/大纲/人物卡/待回收伏笔/用语规范;写完后按六维文笔基线对照原著波动带自检,排出带原句行号的改稿待办;跨章查伏笔埋设跨度、人物连续缺席与大纲偏离;出错时可生成只含元数据、可安全分享的诊断报告。24MB 中文模型随包本地推理,零 token、正文不出本机。Local novel-writing workbench for DSH: 22 tools, on-device model, zero API cost.
npm MIT ★ 29 -
Free offline scan of your AI agent: what loads on every message, heartbeat costs, plaintext API keys and planted or bloated memory. CLI, agent skill and MCP server. Runs locally, sends nothing. MIT-0.
MIT-0 -
Drive the Unity Editor from any MCP client - built for low token cost: selectable tool groups (52 tools, load only what you need), incremental console reads, isolated object screenshots. One C# file + Node. No Python, no account, no API key.
MIT ★ 1 -
The Brave Search API as a CLI and local MCP server — ranked web results, page text pre-extracted to a token budget for grounding a model, and cited answers from one search or a multi-step research run. Every result prints its cost; nothing is cached (Brave ToS)
MIT -
Your AI assistant, but it can phone a friend — an MCP server that consults a council of other AI CLIs. Ban-safe (no API keys, no token extraction), local cost cap, and it ships the eval that tests its own claim.
Apache-2.0 ★ 2 -
OCDgithub.com/Riko5652/OCDactive
OCD (Omni Coder Dashboard) v5.6.0 — AI memory engine with real semantic embeddings, 25 MCP tools, session guard, trace-to-evidence audit bot, Antigravity intelligence, cost visibility, smart routing, and proactive IDE interception. 100% local, zero API keys.
NOASSERTION ★ 3 -
GunsNPricesno update data
US gun and ammo shopping helper from GunsNPrices (gunsnprices.com), a price comparison site that tracks 40+ US gun and ammo stores. Parses product titles into brand, model, caliber, magazine capacity and barrel length; identifies firearm models (50 brands, Glock part numbers decoded); looks up calibers; computes ammo cost per round; and returns GunsNPrices pages that compare current prices. Runs locally, no API key.
smithery -
Local-first MCP server for the Higgsfield AI API: 85 typed image & video models (Seedance 2.5, Kling 3.0, Wan 3, Genjutsu, Soul, Cinema Studio), webhooks, cost estimates, Soul ID training. Opt-in web backend for Sora 2, Veo 3, Nano Banana.
MIT ★ 105 -
Agent Personas as MCP Server — 16 tools, 13 personas (8 free: CEO, CFO, CTO, CMO, PM, Analyst, Support, Creative Director + 5 Pro specialists), 3 multi-persona workflows plus councils + ensembles. Zero LLM API cost (BYO-LLM). Free tier. OAuth 2.1. Hosted at crew.studiomeyer.io
MIT ★ 4 -
A modular platform integrating SQLite, Filesystem, AWS IAM, and Gmail (via SMTP) services through a master MCP server, powered by a custom Claude UI built with Streamlit. Optimized for the Claude API for cost-effective AI interactions, it also supports Claude desktop. Extendable to Grok or OpenAI models with code modifications in client code
★ 1 -
Session continuity for AI coding agents — your agent picks up where it left off. Persistent memory for Claude Code, OpenAI Codex CLI & Google Gemini CLI, sharing one local db: auto context injection, compaction handover, semantic search (KO/EN/JA), error→solution recall. 100% local, zero config, zero API cost.
MIT ★ 7