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.
-
azure-cost-management-mcpgithub.com/bigonil/azure-cost-management-mcpupdated this year
MCP Server for Azure Cost Management - WAF Cost Optimization and CAF aligned. Compatible with GitHub Copilot Chat, Claude Desktop, Cursor, Windsurf.
-
agent-costcenter-mcpupdated this year
MCP server for per-agent cost attribution, budget management, and spend analytics across AI agent fleets
npm MIT -
cloudscope-mcpgithub.com/alexpota/cloudscope-mcpupdated this year
Multi-cloud cost management MCP server (Azure + GCP). Read-only access to spending, anomalies, forecasts, budgets, and guided FinOps workflows. Ask your AI about your cloud bill.
npm MIT ★ 1 -
azure-costmanagement-mcpupdated this year
MCP server for Azure Cost Management — query costs, forecasts, budgets, alerts, and more from your IDE
npm MIT -
Comprehensive MCP server for cloud services management. Supports AWS, Azure, and GCP with resource management, cost analysis, monitoring, and security features.
npm MIT -
AI agent (LangGraph + MCP) that finds idle Azure resources and writes a cost report. Azure Functions, Azure OpenAI, Managed Identity. Read-only.
-
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 -
Ephemeral environment manager in Go: on-demand, isolated test environments for humans and AI agents (via API or MCP), with quotas, cost budgets, priority preemption and automatic TTL cleanup.
-
MCP server for the Czech rental-management app — exposes property/contract/payment/cost-statement/reconciliation tools over stdio. Speaks to a rental-management REST backend.
npm MIT -
💰 Optimize Azure cloud costs effectively with a production-ready FinOps MCP server for enterprise-scale savings and management.
-
velosgithub.com/Dave93/velosupdated this year
High-performance AI-friendly process manager (PM2 alternative). Zig core + Rust shell. Native MCP server, algorithmic smart logs — zero LLM cost.
NOASSERTION ★ 2 -
@aaa-sentinel/mcp-serveractive
Read-only MCP server for AAA Sentinel: query cloud costs, savings, security posture, AI spend, uptime monitoring, the remediation agent and managed clients from an AI assistant
npm MIT -
exitlaunch-dealroom-mcpgithub.com/crawde/exitlaunch-dealroom-mcpupdated this year
MCP server for M&A deal management — due diligence checklist generation, LOI drafting, deal timeline planning, buyer qualification scoring, and closing cost estimation
npm MIT -
Comprehensive Red Hat Product Lifecycle Management MCP Server with advanced features for roadmap analysis, migration planning, compliance reporting, portfolio optimization, and cost analysis
npm MIT -
@om-surushe/efficient-ticktickgithub.com/om-surushe/efficient-ticktickupdated this year
Efficient TickTick MCP - LLM-optimized task management with intelligent time handling and 70% lower token costs
npm MIT -
MCP_CostMCPgithub.com/ar-codelabs/MCP_CostMCPupdated this year
AWS Billing and Cost Management MCP 서버
-
MeghIQgithub.com/Saby007/MeghIQupdated this year
MeghIQ MCP Server - Azure Cost Optimization Tools. A Model Context Protocol (MCP) server exposing 22 tools for Azure cost management, forecasting, budgets, alerts, recommendations, anomaly detection, utilization analysis, and personalized Azure Updates intelligence.
★ 1 -
Self-hosted apartment management: recurring maintenance, documentation, devices, defects, costs — with Home Assistant, Paperless-ngx and MCP integrations.
NOASSERTION -
productivity-mcpgithub.com/thomasgorisse/productivity-mcpupdated this year
MCP server for productivity & time management — Pomodoro planner, time blocking, Eisenhower matrix, meeting cost calculator, project estimator, habit tracker, and weekly review generator.
npm Apache-2.0 -
Comprehensive MCP (Model Context Protocol) server for cloud services management. Supports AWS, Azure, and GCP with resource management, cost analysis, monitoring, and security features.
MIT ★ 2 -
MCP server for Harness - Continuous delivery and cloud cost management
pypi ★ 2 -
LinkedIn Ads MCP server and CLI (read-only): LinkedIn Campaign Manager reporting for AI agents. Spend, CTR, CPC, cost per lead, demographics, creatives and targeting, run locally with your own token.
MIT -
@marginfront/mcpactive
MCP server for MarginFront. Lets AI agents (Claude, Cursor, Copilot) record usage events, create and look up agents + signals, query revenue / cost / MRR analytics, manage customers + subscriptions + pricing plans, set per-customer cost and revenue watch
npm MIT -
cloudability-mcp-servergithub.com/eelzinaty/cloudability-mcp-serverupdated this year
A comprehensive Model Context Protocol (MCP) server for the Cloudability API, providing advanced cost management, Kubernetes container analytics, and budget forecasting capabilities.
MIT ★ 4 -
anthropic-admin-mcpgithub.com/Trushtonfactory/anthropic-admin-mcpupdated this year
MCP server for the Anthropic Admin API — manage your Claude org from any MCP-compatible client. Full coverage of Usage/Cost API plus org/workspace/member/key management, with audit logging and safety scoping.
pypi MIT -
Conversational Infrastructure-as-Code platform powered by Agentic AI and Terraform. Features MCP protocol integration, natural language processing, secure credential management, and real-time cost estimation.
-
A Python-based server for managing and analyzing code context for AI-assisted development, without the monthly costs of a subscription API.
MIT ★ 13 -
PCBWay MCP server for AI coding assistants — PCBWay API tools for instant PCB manufacturing quotes, SMT assembly pricing, order management, and shipping costs.
npm MIT ★ 1 -
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 -
Give AI agents full access to the Harness.io platform — manage pipelines, deployments, cloud costs, chaos engineering, feature flags, SEI, and 125+ resource types through 11 MCP tools
npm Apache-2.0 -
117 MCP tools for GPU infrastructure + Agent FinOps — deploy LLMs, manage VMs (Proxmox/XO/vSphere), track cost per agent, enforce budgets and model policies. Works with Claude, Cursor, n8n, LangChain
pypi MIT ★ 20 -
The Gatherings MCP Server provides an API that allows AI assistants to interact with the Gatherings application through the Machine Conversation Protocol. This enables AI systems to help users manage shared expenses for social events, outings, or any gathering where costs are split among participants.
Apache-2.0 -
terradev-mcpgithub.com/theoddden/terradev-mcpupdated this year
Complete Agentic GPU Infrastructure for Claude Code — 192 MCP tools: Full training lifecycle, inference deployment with cost guardrails, Ray cluster management (Wide-EP, disaggregated P/D, parallelism strategy), vLLM lifecycle (start/stop/sleep/wake/infer
npm MIT -
Fabrica Farm — printer management, agent-first. Every 3D printer (Bambu Lab, Prusa, OctoPrint, Klipper) on one dashboard, with cameras, history, costs, spaghetti detection and 47 MCP tools for AI agents. 100% local.
MIT -
Manage TrueNAS SCALE from an AI agent through 278 actions across 18 categories behind one hierarchical MCP tool — tool schemas cost ~200 tokens of context instead of ~28k, and destructive operations require explicit confirmation.
npm MIT ★ 8 -
MCP server for Business Central operational expense analysis, bank reconciliation, POS reconciliation, accounts receivable/payable, multi-payment draft visibility, payroll, inventory cost analysis, and manager reports - Full Queso franchise stores
npm MIT -
Agentic-first token counting and text chunking service for LLM context management. Count tokens, chunk text, truncate to limits, RAG-style splitting, estimate API costs. Plain text API, MCP-enabled, single Go binary, zero dependencies, no database.
-
databricks_candidates_analysisgithub.com/VenkatagiriRamesh/databricks_candidates_analysisupdated this year
End-to-end Databricks Free Edition project: PDF ingestion (data engineering), AI/BI dashboard + Genie (analytics), and 10 HR tools served via Managed MCP + a Mosaic AI Model Serving agent endpoint (agentic AI/LLM/MCP) -- built for optimized cost (serverless, scale-to-zero) and catalog-enforced governance.
MIT -
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 -
ecosgithub.com/ecos-labs/ecosupdated this year
ecos is an open FinOps data stack with a CLI and MCP server that turns raw cloud data into actionable insights.
Apache-2.0 ★ 24 -
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.
pypi Apache-2.0 ★ 20 -
MCP server that compares on-demand VM pricing across AWS, Azure, and GCP in real time
pypi MIT ★ 2 -
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 -
Azure ops MCP-style tools (kv_compare, ado_diagnose, cost_stub) — dry-run + audit
MIT -
MCP server for Azure cost analysis, budgets, forecasting & optimization — works with Claude, VS Code, and Cursor
pypi MIT -
kubecost-mcpstale
Model Context Protocol (MCP) server for Kubecost
npm MIT -
@openplan/mcpgithub.com/vncsleal/openplanupdated this year
Waze for AI agents — plan, track, and learn from software projects.
npm MIT -
Comprehensive Neon PostgreSQL MCP server with 145 tools for complete database management
npm MIT -
meetdrain-calculate-mcpgithub.com/crawde/mcp-meetdrain-calculateupdated this year
MCP server for meeting cost analysis — calculate real-time meeting expenses, compare sync vs async formats, check meeting ROI, estimate annual meeting budgets, and identify cost-saving opportunities
npm MIT -
AI-Powered Azure Infrastructure Optimization via Model Context Protocol
npm MIT -
MCP bridge for AI agents using Entroly Context Assurance: reduce avoidable AI token usage with evidence selection, receipts, exact recovery, and verification.
npm Apache-2.0 -
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 -
MCP server that ranks log patterns by volume and cost and plans compact, tier down or offload per pattern. Runs locally; no log data reaches log10x.
npm MIT ★ 1 -
Persistent multi-agent work graph and document-state machine for contracts, specs, slices, evidence, verification, handoffs, and cost-aware AI execution.
Apache-2.0 -
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 -
AIM — AI Maestro for the Harness platform. Your personal Harness Architect, powered by the Harness Adoption MCP server.
npm Apache-2.0 -
cache-manager-mcpgithub.com/datawithdanny/cache-manager-mcpupdated this year
Save tokens across AI agent chats with prompt TTL tracking, handoff memories, and cost insights — over MCP.
MIT -
gvnrgithub.com/mightbesaad/gvnrupdated this year
Budget & cost control for AI agents — hard per-agent spend caps, rate limits, idempotency, and human-in-the-loop approval, enforced before each LLM call (not after the invoice). One hosted MCP endpoint, no proxy or self-hosting. Settled via x402 (USDC on Base).
MIT -
Self-hosted AWS CloudOps control plane: incident cases, exact-action approvals, Cognito/JWKS, OPA/Rego, DynamoDB audit, Bedrock, Terraform, and GitHub Actions.
MIT ★ 1 -
cctxgithub.com/anil7948/cctxupdated this year
Reduce Claude Code token usage by 70-90% using a free local LLM (Ollama). MCP server + Stop hook with codebase indexing, tool output compression, and turn summarization.
npm MIT ★ 3