Sold by: A2AGateway
Deployed on AWS
Free Trial
Self-hosted Model Context Protocol gateway that connects Claude, Cursor, and any MCP client to your internal systems, Jira, Slack, Salesforce, or any proprietary API. Runs entirely in your AWS account.
Overview
MCPCloud is an open-source, self-hosted MCP (Model Context Protocol) gateway that turns any Python function into a tool callable by Claude Desktop, Cursor, the Claude API, or any MCP-compatible AI client. Write a function, deploy it, and your AI assistant calls it as a native tool. No copy-paste, no tab switching, no custom integrations required. Built for enterprise teams. MCPCloud bridges the gap between AI clients and your existing systems. Connect to Jira, Slack, Salesforce, ServiceNow, or any internal API including proprietary systems that will never have a vendor-built MCP server. A single Python file wraps any REST endpoint in minutes. One Claude prompt can open a Jira ticket, post a Slack alert, and update your dashboard simultaneously. MCPCloud deploys on your AWS account using ECS Fargate, Redis, and an Application Load Balancer, provisioned automatically via CloudFormation. Credentials are stored in AWS Secrets Manager. All data stays within your VPC. A built-in tool browser lets every team member discover and test registered skills without requiring an AI client setup.
Highlights
- Connect AI to any system. Jira, Slack, Salesforce, ServiceNow, or any internal API your team uses. Write a Python function, deploy it, and Claude can call it as a native tool. No vendor support required, no waiting for official integrations.
- Runs entirely in your AWS account. Nothing routes through third-party infrastructure. Meets data residency and compliance requirements out of the box.
- Ship a new AI tool in an afternoon. Drop a .py file into skills/, restart, and it's live. No SDK, no framework, no deployment pipeline. Built-in tool browser lets every teammate discover and test skills without AI client setup.
Details
Sold by
Delivery method
Supported services
Delivery option
Amazon ECS Fargate
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 7 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/unit/hour |
|---|---|---|
Hours | Container Hours | $0.20 |
Dimensions summary
This product uses one usage-based pricing dimension: Container Hours. You pay for each hour the gateway container runs, billed by the unit UnitHrs. There are no tiers or fixed plans. Your cost scales directly with how long you keep the container running. The software deploys into your own AWS account, so you run it as long as you need and pay by actual runtime.
Top-of-mind questions for buyers
One Container Hour is one hour that the gateway container runs in your AWS account. The software deploys on serverless containers alongside an in-memory cache and a load balancer. Billing counts the running time of the gateway container, not the number of tool calls or connected clients.
The software charge meters running container time. When you stop the container, software hours stop accruing. Underlying AWS resources, such as the load balancer, cache, or stored secrets, may still carry their own AWS fees separate from this listing's Container Hours charge.
No. Cost scales only with how many hours the container runs. You can add Python skills through files or the browser editor, and connect many clients, without changing the Container Hours rate. More skills or clients do not add separate charges.
mcpcloud.dev
Helpful?
Vendor refund policy
All fees are non-refundable. A 7-day free trial is available before any charges apply, allowing buyers to fully evaluate the product before purchase. For billing questions, contact help@mcpcloud.dev .
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon ECS Fargate
Supported services: Learn more
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
The audit log now records exactly which skill implementation (filesystem-loaded or dashboard-saved) handled every tool call, giving you a clear, verifiable trail of what ran and when.
Additional details
Usage instructions
- Subscribe and accept the terms.
- Choose region and software version, then click "Continue to Launch".
- Click the "MCPCloud ECS Fargate CloudFormation Template" link above it opens CloudFormation with the template pre-loaded.
- Fill in your VPC ID, subnet IDs, and integration credentials (Jira, Slack, etc.).
- Click "Create stack". The MCP endpoint URL appears in CloudFormation Outputs after ~10 minutes.
Requirements: an existing VPC with at least one public subnet (for the load balancer) and one private subnet (for ECS tasks and Redis).
Support
Vendor support
GitHub Issues: https://github.com/carsor007/mcpcloud/issues Email: help@mcpcloud.dev Documentation: https://github.com/carsor007/mcpcloud#readme
Community support is provided via GitHub Issues. Email support available at help@mcpcloud.dev . Response within 48 hours on business days.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Self-hosted API and AI gateway for platform engineers managing microservices, LLM traffic, and multi-cloud architectures on AWS EC2.
Synch is a secure, cloud-based platform offering task force management and collaboration with real-time voice, video, chat, and location-based services, designed to enhance communication and operations for first-line workers
The Wiz Model Context Protocol (MCP) Server acts as an MCP-compatible service that translates plain-language queries into Wiz-specific operations, like querying resources, or assessing risks.
falcon-mcp enables seamless communication between AI agents and the CrowdStrike Falcon platform. Deployable directly onto Amazon Bedrock AgentCore, it provides programmatic access to Falcon data for agentic workflows and accelerating AI-native security automation.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.