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.
-
cloud-cost-mcpgithub.com/jasonwilbur/cloud-cost-mcpupdated this year
Multi-cloud pricing comparison MCP server for AWS, Azure, GCP, and OCI
npm Apache-2.0 -
—
-
cloud-cost-mcpgithub.com/jasonwilbur/cloud-cost-mcpupdated this year
Model Context Protocol server for Cloud Infrastructure pricing information
Apache-2.0 ★ 4 -
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 -
Multi-cloud cost, inventory and waste analysis over MCP — what you spend by service, region and account, and what is idle, oversized, previous-generation, unattached or a commitment you are not consuming. AWS, GCP, Cloudflare and OVH, each behind that clo
npm Apache-2.0 -
MCP server for FinOps cloud cost analysis using FOCUS billing data. Query AWS, Azure & GCP costs with AI assistants like Claude.
Apache-2.0 ★ 12 -
cloudscope-mcpgithub.com/alexpota/cloudscope-mcpupdated this year
Multi-cloud cost management MCP server (Azure + GCP): spending, forecasts, anomalies, budgets, idle resources, tags.
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.
MIT ★ 1 -
cloud-migration-mcpgithub.com/chrishorne74/cloud-migration-mcpupdated this year
MCP server for cloud migration: 7Rs strategy, guardrails, candidate scoring, wave planning, cost estimation, and draw.io diagrams
-
Hosted streamable HTTP MCP server for Cloud World Model: simulate cloud infrastructure and estimate cost, latency and resilience before deploying or changing infrastructure. Multi-cloud world model for AWS, GCP, Azure, OCI and DigitalOcean; MCP and REST, with x402 payment on eligible requests.
-
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 -
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 -
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 -
AI model router for agents. Checks whether a local model can handle the task before calling cloud inference. LOCAL/CLOUD verdict saves cost on every call.
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 -
An MCP (Model Context Protocol) server that brings powerful AWS FinOps capabilities directly into your AI assistant. Analyze cloud costs, audit for waste, and get budget insights using natural language, all while keeping your credentials secure on your local machine.
MIT ★ 184 -
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 -
monitorgithub.com/1037630579/monitorupdated this year
AI-powered multi-cloud governance tool for Alibaba Cloud, Huawei Cloud & AWS. Natural language queries, idle resource detection, and cost optimization.
MIT ★ 1 -
MCP server for Cursor Cloud Agents (background agents): launch, follow up, supervise and cost Cursor agents from Claude Code, Codex CLI or OpenCode
pypi MIT -
cloudbillgithub.com/cognis-digital/cloudbillupdated this year
Multi-cloud cost report, anomaly detection, and FOCUS export
NOASSERTION -
MCP server for Cursor Cloud Agents (background agents): launch, follow up, supervise and track the cost of Cursor agents from Claude Code, Codex CLI or OpenCode.
MIT ★ 1 -
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.
-
Design-time sustainability co-pilot (MCP server): greener, cheaper cloud infrastructure decisions with carbon + cost + latency tradeoffs.
pypi MIT -
Cloud-hosted MCP server for Alibaba's Qwen models - specializing in Chinese language, coding, and cost-effective AI inference on Apify platform
-
Cloud-hosted MCP server providing AI agents access to Deepseek's cost-effective LLMs (R1 & V3) with 60-90% cost savings vs OpenAI/Claude
-
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 -
Decoupled local-SLM pre-processing and routing layer for MCP and cloud LLMs. Intercepts, distills, and routes prompts locally with Ollama to cut token costs and protect monthly quota.
npm MIT ★ 3 -
smritigithub.com/moltizmo/smritiupdated this year
Local-first persistent memory for AI agents via MCP. Sanskrit for memory (स्मृति). Zero cloud. Zero cost.
MIT ★ 1 -
mychatarchivegithub.com/1ch1n/mychatarchiveupdated this year
Local-first AI memory archive. Import ChatGPT, Claude, and Grok exports, generate semantic embeddings, and search via MCP server. Zero cloud, zero cost.
NOASSERTION ★ 72 -
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 -
Hardware-adaptive local LLM & cloud cascading gateway. Sub-5ms intelligent routing, 3-token lookahead failover, asymmetric verification, 1-click IDE config, and MCP for $0 token cost.
MIT ★ 4 -
Standalone cloud-deployable Remote Model Context Protocol (MCP) servers built with FastMCP (SSE/HTTP transport) providing global intelligence: real-time forex currency conversion, cryptocurrency valuations, live weather telemetry, and city living cost indicators.
MIT -
An agentic AI–powered IaC scanner that evaluates cloud infrastructure against security and compliance benchmarks. It also delivers cost analysis and AWS Well-Architected recommendations, with support for custom policies, checks, and configurable exceptions.
Apache-2.0 ★ 4 -
A decoupled local-SLM pre-processing and routing layer for MCP and cloud LLMs. Intercepts, distills, and routes prompts locally with Ollama to cut token costs and protect monthly quota.
npm MIT -
Self-hosted Google Ads MCP server for Claude & AI agents. Deploys the official googleads/google-ads-mcp on your VPS with CapRover/Docker: HTTPS, Google OAuth, encrypted tokens, zero Google Cloud cost. Prebuilt image on GHCR. Docs in EN and PT-BR.
Apache-2.0 ★ 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 -
YouTube Download to Cloud Storage — FlashDatano update data
# YouTube Download to Cloud Storage — FlashData Deliver YouTube video, audio or clips to your own S3 or other supported cloud storage. Track asynchronous delivery and its output manifest. Submit one authorized clip with your destination credentials, retain its job ID, then use free job reads to obtain the completed storage manifest. [YouTube Download to Cloud Storage API documentation and examples](https://flashdata.dev/docs/sources/youtube_download?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_download-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Download to Cloud Storage listing](https://smithery.ai/servers/flashdata/youtube-download) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_download`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the per-TB rate. Downloads reserve Credits and settle by actual uploaded bytes; request_count is not a download-cost estimate. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_download` without submitting a data query. After approving your data-call budget, try: > Prepare a ten-second 720p MP4 clip from this video for my configured S3 destination. Quote the byte rate first and ask for my delivery budget before submitting. This server exposes `youtube_download`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call video_id and storage are required. Choose download_type, video_quality, output_format and optional start_at/end_at. Only async is supported. Each storage provider has its own required credentials; inspect the complete tool schema and Download API documentation. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_download", "arguments": { "video_id": "jNQXAC9IVRw", "mode": "async", "download_type": "audio_video", "video_quality": "<=720", "output_format": "mp4", "start_at": "00:00:00", "end_at": "00:00:10", "storage": { "storage_type": "s3", "storage_url": "your-media-bucket", "access_key": "YOUR_ACCESS_KEY", "secret_key": "YOUR_SECRET_KEY", "region": "us-east-1", "object_prefix": "flashdata-clips" } } } ``` ## Work with the output Submit once, save the returned id, and call get_job with job_id until job.status is completed. Read output.results[0] for file_url, file_size, downloaded_bytes and output_format. Pending or processing is not completed delivery. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "job": { "id": "job_EXAMPLE", "source": "youtube_download", "status": "completed" }, "output": { "results": [ { "file_url": "s3://customer-bucket/clip.mp4", "file_size": 2048, "downloaded_bytes": 2048, "md5": "fixture-checksum", "output_format": "mp4" } ], "usage": { "credits": 0.001 } }, "http_status": 200, "request_id": "fixture-request" } ``` For example, after receiving the real id, call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Poll only the read, not the original download submission. Storage credentials travel to FlashData to perform the upload and may be retained by your MCP client in tool history; use narrowly scoped credentials and your client's protected configuration. ## Limits and result handling Only asynchronous delivery is supported. Supply your own destination and credentials; media access and retention follow your storage settings. Private object URLs are not public download links. Charges reserve Credits and settle by uploaded bytes. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
cost-audit-agentgithub.com/alex-jb/cost-audit-agentupdated this year
Monthly cloud bill auditor. 6 providers (Vercel, Anthropic, OpenPanel, HyperDX, Supabase, GH Actions). Dollar-tagged waste findings. pip · MCP · MIT.
MIT ★ 1 -
Cross-cloud FinOps server that brings visibility and control to AWS, GCP, and Azure in one place
MIT ★ 2 -
Open-source, read-only AWS security scanner. 110 checks across 25 services, 31 attack-chain rules, 64 IAM escalation methods (incl. lateral AssumeRole graph), Proof Mode exploitability verification, data perimeter and Bedrock AgentCore checks, Blast Radius CLI, Threat Feed, What-If simulator, AI-SPM, 6 compliance frameworks, breach-cost estimation, MCP server. CLI + Terraform remediation on every finding.
pypi MIT -
focus-mcpgithub.com/glassity/focus-mcpupdated this year
MCP server for querying FOCUS cloud billing data with DuckDB
pypi Apache-2.0 -
Read-only AWS waste scanner: NAT endpoint tax, infinite logs, zombie EBS/EIPs: USD/mo + Terraform fix
npm MIT -
Ask Claude about your cloud and AI bill. Brand alias for finops-mcp.
pypi Apache-2.0 -
An MCP server for AWS FinOps to analyze costs and audit for savings.
pypi MIT -
unofficial-gmi-cloud-cligithub.com/yannan000/unofficial-gmi-cloud-cliupdated this year
Your terminal is now a film studio. Unofficial CLI + MCP server for GMI Studio's 300+ models — uploads, formats, polling, downloads, and cost pre-flight handled.
MIT ★ 2 -
k8scostgithub.com/cognis-digital/k8scostupdated this year
Kubernetes cost and rightsizing advisor with no Prometheus dependency
NOASSERTION -
Read-only BigQuery MCP server for Claude, Cursor, Windsurf, Copilot and other MCP clients. Auto-LIMIT, dry-run cost guard, Application Default Credentials. Run with uvx.
MIT ★ 1 -
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 -
GNAWS MCP server — expose AWS resource scanning and unused resource detection to AI agents
npm AGPL-3.0-only -
Read-only AWS waste scanner: NAT endpoint tax, infinite logs, zombie EBS/EIPs: USD/mo + Terraform fix
npm MIT -
meetingcostgithub.com/cognis-digital/meetingcostupdated this year
Compute the dollar cost of meetings from your calendar (.ics)
NOASSERTION -
Train-in-Silencegithub.com/hlpun/Train-in-Silenceupdated this year
The first Task-Aware MCP server and automated VRAM calculator for LLM fine-tuning. Instantly snipe the cheapest, fastest GPUs across 10+ cloud providers.
MIT ★ 104 -
Let any AI assistant work a Slurm cluster, safely: MCP server + CLI in one Go binary. Typed, audited, read-mostly access to jobs, diagnosis, costs and modules for Claude, Codex, Gemini, Hermes, OpenCode.
MIT