Overview
Flomesh MCP Remote brings Zero Trust security and dynamic orchestration to AI agent-tool interaction using the Model Context Protocol (MCP). Unlike traditional platforms that rely on fixed infrastructure or SDKs, MCP Remote leverages ZTM Agents, lightweight mesh nodes deployed across desktops, servers, mobile, and IoT devices, to create a decentralized, secure runtime fabric for real-time MCP communication.
Much like Cloudflare Workers and Durable Objects form a programmable edge layer, ZTM acts as the orchestration backbone, handling mTLS-based authentication, routing, observability, and access control across all endpoints. Developers can interact with remote MCP tools via local RESTful APIs on localhost:7777, while agents tunnel encrypted traffic through NAT and firewalls without any special network configuration.
Key Features:
-
Zero Trust Mesh for MCP Enforces mTLS-based authentication and least-privilege access for all MCP interactions, no VPNs or static IPs required.
-
Distributed Orchestration with ZTM Agents ZTM Agents run on edge, user, mobile, and IoT devices to form a programmable mesh, similar in role to Cloudflare Workers.
-
Seamless Connectivity Across NAT/Firewalls Enables secure access to MCP servers across any network boundary without manual port forwarding or tunneling setup.
-
No SDK Required Connect to remote MCP tools or services without modifying or rebuilding them using any SDK.
-
Developer-Friendly Local API Access tools via RESTful API , ideal for rapid testing, IDE integration, and debugging.
-
Tool Poisoning & Threat Mitigation Built-in semantic validation, runtime monitoring, and strict access policies prevent tampering and misuse.
-
Cross-Platform & Lightweight Runs on Windows, macOS, Linux, iOS, Android, OpenWrt, and embedded Linux, making it ideal for hybrid cloud-edge use cases.
-
Full Auditability & Enterprise Compliance Logs every interaction with cryptographic guarantees to meet audit, security, and regulatory requirements.
Highlights
- - Zero Trust Security for AI and MCP Enforces mTLS, certificate-based identity, and least-privilege access to protect AI agents interacting with MCP tools and services.
- - Decentralized Mesh with ZTM Agents Deploy lightweight agents on edge, mobile, desktop, or IoT devices to securely connect to MCP servers across any network.
- - Developer-Friendly and SDK-Free Securely build and test AI-powered applications using a local RESTful API, no SDK or VPN required.
Details
Unlock automation with AI agent solutions

Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Cost/hour |
---|---|
t3.medium Recommended | $0.01 |
t3.micro AWS Free Tier | $0.01 |
t3.small | $0.01 |
Vendor refund policy
Follow AWS Refund policy
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
- Implement user and user group management
- Add system proxy switch, commercialize proxy rules, achieve user group granularity
- optimize chat display
- provide enterprise authentication
- optimize tunneling function
- configurable i18n
Additional details
Usage instructions
Launch Flomesh MCP Remote AMI
- Select the Flomesh MCP Remote listing in the AWS Marketplace and launch it.
- Configure the software with a 64-bit AMI, the latest version of Flomesh MCP Remote, and choose your desired region.
- Select your preferred instance type.
- Use the predefined access settings for ports and protocols in the security group.
- Choose a key pair for securely connecting to your instance (or create a new one if necessary).
- Launch your instance.
Connect to Your New AMI
After launching your new AMI, follow these steps to connect:
- SSH into the console using an SSH client software and the private key pair you used or created earlier.
- Use the instance username ubuntu.
- Connect with the following command: ssh -i /path/to/key-pair-name.pem ubuntu@instance-public-ipv4-address
Retrieve ZTM Root User Permit
Upon the first boot of your EC2 instance, a new permit file named ztm-permit.json will be generated and placed in the /root/.ztm directory.
Setting Up ZTM Endpoints
After setting up the ZTM hub server and obtaining the ztm-permit.json file, you are ready to install ZTM agent and set up the ZTM mesh on your own machines.
For detailed instructions on setting up ZTM endpoint on your personal machine, follow the Quick Start guide Setup Endpoints .
Resources
Vendor resources
Support
Vendor support
As a paid AMI, ZTM includes priority technical support from Flomesh. For assistance, contact us via Slack or email at  support@flomesh.io .
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.