MCP Environment Proxy
Allows dynamic switching between multiple Kubernetes clusters (EKS) by managing environment variables for different AWS accounts and regions.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Environment Proxy Switch to the production EKS cluster"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Environment Proxy
A dynamic MCP (Model Context Protocol) proxy that allows switching environment variables on-the-fly. Instead of configuring multiple MCP servers for different AWS accounts/regions, use a single proxy that can switch contexts dynamically.
Problem
When working with multiple AWS accounts or Kubernetes clusters, you typically need one MCP server per environment:
{
"mcpServers": {
"eks-production": { "env": { "AWS_PROFILE": "prod" } },
"eks-staging": { "env": { "AWS_PROFILE": "staging" } },
"eks-dev": { "env": { "AWS_PROFILE": "dev" } }
}
}This consumes context and requires restarting Claude to switch environments.
Related MCP server: MCP Manager
Solution
MCP Environment Proxy provides a single MCP server that can switch between contexts on-demand:
{
"mcpServers": {
"mcp-env-proxy": {
"command": "uvx",
"args": ["mcp-env-proxy@latest", "-c", "~/.config/mcp-env-proxy/contexts.yaml"]
}
}
}Then dynamically switch contexts:
> switch_context("eks-production")
> list_k8s_resources(...)
> switch_context("eks-staging")
> list_k8s_resources(...)Installation
# With uvx (recommended)
uvx mcp-env-proxy@latest
# With pip
pip install mcp-env-proxy
# From source
git clone https://github.com/KamorionLabs/mcp-env-proxy.git
cd mcp-env-proxy
pip install -e .Configuration
Create a contexts.yaml file:
# Default environment variables for all contexts
defaults:
FASTMCP_LOG_LEVEL: ERROR
# Define MCP server types
servers:
eks:
command: uvx
args: ["awslabs.eks-mcp-server@latest"]
ecs:
command: uvx
args: ["awslabs.ecs-mcp-server@latest"]
# Named contexts
contexts:
production:
server: eks
env:
AWS_PROFILE: WordPress-Production/AWSAdministratorAccess
AWS_REGION: eu-west-3
staging:
server: eks
env:
AWS_PROFILE: WordPress-Staging/AWSAdministratorAccess
AWS_REGION: eu-west-3
homebox-prod:
server: ecs
env:
AWS_PROFILE: homebox-production/AdministratorAccess
AWS_REGION: eu-west-3
# Default context on startup
current_context: productionConfig file locations (in order of precedence):
MCP_ENV_PROXY_CONFIGenvironment variable./contexts.yaml(current directory)~/.config/mcp-env-proxy/contexts.yaml
Available Tools
list_contexts
List all available contexts with their configuration.
switch_context(context_name)
Switch to a different context. This loads the MCP server with the specified environment variables.
get_current_context
Get information about the currently active context.
list_proxied_tools
List all tools available from the current context's MCP server.
proxy_tool(tool_name, arguments)
Call a tool on the proxied MCP server.
Process Pool
The proxy maintains a pool of MCP server processes (default: 5). When you switch contexts:
If the context was previously loaded, it reuses the existing process (fast)
If it's a new context, it spawns a new process
If the pool is full, it evicts the oldest unused process
This provides fast context switching while limiting memory usage.
Usage with Claude Code
Add to your Claude Code MCP configuration:
claude mcp add mcp-env-proxy -- uvx mcp-env-proxy@latest -c ~/.config/mcp-env-proxy/contexts.yamlThen in conversation:
User: Switch to the production EKS cluster
Claude: [calls switch_context("production")]
User: List the pods in the wordpress namespace
Claude: [calls proxy_tool("list_k8s_resources", {"resource_type": "pods", "namespace": "wordpress"})]Development
# Clone the repository
git clone https://github.com/KamorionLabs/mcp-env-proxy.git
cd mcp-env-proxy
# Create virtual environment
python -m venv .venv
source .venv/bin/activate
# Install in development mode
pip install -e ".[dev]"
# Run tests
pytest
# Run locally
python -m mcp_env_proxy -c config/contexts.example.yaml -vLicense
MIT License - see LICENSE for details.
Contributing
Contributions welcome! Please open an issue or PR on GitHub.
Available Tools
5 toolsget_current_contextA
Get information about the current context.
Returns: Current context info including available tools
Inputs: no named parameters. Returns: object
list_contextsA
List all available contexts.
Returns a list of contexts with their configuration, showing which is currently active and which have cached tools.
Inputs: no named parameters. Returns: result
list_proxied_toolsA
List tools available from the current context's MCP server.
Returns: List of tools with their names and descriptions
Inputs: no named parameters. Returns: result
proxy_toolA
Call a tool on the current context's MCP server.
This forwards the tool call to the underlying MCP server (EKS, ECS, CloudWatch, etc.) with the current context's environment variables.
Args: tool_name: Name of the tool to call on the proxied server arguments: Arguments to pass to the tool
Returns: Result from the proxied tool
Inputs: tool_name (required), arguments.
switch_contextA
Switch to a different context.
This changes the active MCP server connection to use different environment variables (AWS_PROFILE, AWS_REGION, etc.).
Args: context_name: Name of the context to switch to
Returns: Information about the new active context including available tools
Inputs: context_name (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a distinct and clear purpose: getting current context, listing contexts, listing proxied tools, calling a proxied tool, and switching contexts. There is no overlap.
All tool names use a consistent verb_noun pattern in snake_case (e.g., get_current_context, list_contexts), with clear and predictable naming.
Five tools is appropriate for a proxy server that manages contexts and proxies tool calls; each tool serves a necessary role without redundancy.
The tool set covers the full lifecycle: switching contexts, viewing context info, listing available tools, and executing proxied calls. There are no obvious gaps for the stated domain.
Maintenance
Related MCP Connectors
Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.
One MCP endpoint for your company's tools, with per-person sign-in, policy and audit.
Remote MCP for Copilot CLI switch gate MCP, structured receipts, audit logs, and reviewer-ready evid
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA dynamic proxy server that enables users to manage and access multiple MCP backend servers through a single, unified interface. It supports both static and runtime server configuration with persistent storage and works with HTTP and SSE transports.MIT
- AlicenseNot gradedqualityDmaintenanceSelf-hosted MCP proxy and aggregation platform. Register multiple upstream MCP servers and expose them through a single unified endpoint with namespace routing, multi-transport support (HTTP/SSE, stdio, OpenAPI→MCP), per-tool overrides, and a web admin UI.18MIT
- AlicenseNot gradedqualityCmaintenanceLocal-first CLI + proxy that curates your MCP servers per client from one canonical config, cutting tool-schema tokens ~80% and resolving secret references instead of hardcoding keys.MIT
- AlicenseNot gradedqualityBmaintenanceA local MCP auth wrapper and credential broker for multi-account workflows, enabling profile switching, secret injection, and policy enforcement for upstream MCP servers.9 npm5MIT