Ambient Code Platform MCP Server
Delegates expensive or long-running AI tasks to Kubernetes-hosted Claude agents running on OpenShift. Enables creating, managing, and monitoring remote agentic sessions for complex work like codebase analysis and security audits.
README
Ambient Code Platform MCP Server
Delegate work to Kubernetes-hosted Claude agents running on OpenShift.
What It Does
Offload expensive or long-running AI tasks to the cluster. Example workflow:
- Create session: "Analyze this 50k line codebase for security vulnerabilities"
- Session runs on ACP (Kubernetes pod with Claude)
- Check status periodically
- Fetch results when done
- Stop session to free resources
Tools
| Tool | Description |
|---|---|
acp_whoami |
Check OpenShift auth status |
acp_list_projects |
List available projects/namespaces |
acp_list_sessions |
List agentic sessions in a project |
acp_get_session |
Get session details and status |
acp_get_events |
Get session status snapshot |
acp_create_session |
Create a new agentic session with a prompt |
acp_send_message |
Send follow-up message to a session |
acp_stop_session |
Stop a running session |
Quickstart
1. Clone
git clone https://github.com/ambient-code/mcp.git
cd mcp
2. Install dependencies
bun install
3. Login to OpenShift
oc login --token=<your-token> --server=<your-openshift-api-server>
# Verify
oc whoami
4. Configure your MCP client
OpenCode
Add to ~/.config/opencode/opencode.json:
{
"mcp": {
"ambient-code": {
"type": "local",
"command": ["bun", "run", "/path/to/mcp/src/index.ts"],
"environment": {
"ACP_BASE_URL": "https://<your-acp-route>"
}
}
}
}
Claude Desktop, Claude Code CLI, OpenAI Codex CLI
These clients use the standard MCP config format. Add to:
| Client | Config file | Docs |
|---|---|---|
| Claude Desktop (macOS) | ~/Library/Application Support/Claude/claude_desktop_config.json |
docs |
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
docs |
| Claude Code CLI | ~/.claude/settings.json |
docs |
| OpenAI Codex CLI | ~/.codex/config.json |
docs |
{
"mcpServers": {
"ambient-code": {
"command": "bun",
"args": ["run", "/path/to/mcp/src/index.ts"],
"env": {
"ACP_BASE_URL": "https://<your-acp-route>"
}
}
}
}
5. Restart your client
The tools will be available after restart.
Usage
Just talk to your AI assistant naturally. It will use the tools automatically.
You say:
"Am I logged in to OpenShift?"
"What projects do I have access to?"
"Show me the running sessions in my workspace"
"Create a new session called 'Security Audit' and have it analyze this repo for SQL injection vulnerabilities"
"Tell that session to also check for XSS issues"
"Stop that session when it's done"
Testing
# Set the required environment variable
export ACP_BASE_URL="https://<your-acp-route>"
# Test tools/list
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | bun run src/index.ts
# Test whoami
echo '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"acp_whoami","arguments":{}}}' | bun run src/index.ts
# Test list projects
echo '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"acp_list_projects","arguments":{}}}' | bun run src/index.ts
Environment Variables
| Variable | Required | Description |
|---|---|---|
ACP_BASE_URL |
Yes | Ambient Code Platform API URL (e.g., https://acp.example.com) |
How Authentication Works
The MCP server uses oc whoami -t to get your current OpenShift token. This means:
- You must be logged in via
oc loginbefore using the tools - Tokens expire - re-login if you get auth errors
- Both
Authorization: BearerandX-Forwarded-Access-Tokenheaders are sent (ACP requirement)
License
Apache-2.0
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.