Ambient Code Platform MCP Server
Delegates expensive or long-running AI tasks to Kubernetes-hosted Claude agents running on OpenShift...
Open the FastMCP connection dialog
- Click the "Install Now" / connection button for the MCP and open the FastMCP connection interface where you can add environment variables (ENV key/value pairs).
Add the required bearer token ENV
- In the FastMCP interface add an ENV with key
ACP_TOKEN. - For the value, paste your ACP Bearer token (example value:
ya29.xxx...oreyJhbGci...). - Note: this token is required for the MCP to authenticate to the ACP public-api gateway.
- In the FastMCP interface add an ENV with key
(Optional) Add cluster-config path ENV if you use a local clusters.yaml
- If you prefer configuring clusters via a local file, add an ENV with key
ACP_CLUSTER_CONFIGand value set to the absolute path to the clusters.yaml on the MCP host (example:/home/ubuntu/.config/acp/clusters.yaml). - If you do this, the MCP will read cluster endpoints and per-cluster tokens from that file instead of the single
ACP_TOKENenv.
- If you prefer configuring clusters via a local file, add an ENV with key
Create the clusters.yaml file (if using file-based config)
- On the MCP host create
~/.config/acp/clusters.yamlwith contents like:clusters: my-cluster: server: https://public-api-ambient.apps.your-cluster.example.com token: your-bearer-token-here default_project: my-workspace default_cluster: my-cluster - Replace
server,token,default_project, anddefault_clusterwith your cluster values.
- On the MCP host create
Secure the clusters.yaml file
- Set strict permissions so the file is readable only by the MCP user:
chmod 700 ~/.config/acpchmod 600 ~/.config/acp/clusters.yaml
- Set strict permissions so the file is readable only by the MCP user:
How to obtain the Bearer token
- Primary option: Request the token from your ACP platform administrator (they can create/provide a bearer token).
- If you have access to the ACP gateway’s auth UI or endpoint, create or mint a token there (name it clearly, copy it immediately — tokens are often shown only once).
- If your org uses an automated identity system, follow the org’s process to generate a gateway bearer token and then copy it.
Paste the token into FastMCP and save
- After obtaining the token, paste it into the
ACP_TOKENENV value in the FastMCP interface (or ensure theACP_CLUSTER_CONFIGpath points to a clusters.yaml containing the token). - Save/apply the connection settings in the FastMCP dialog.
- After obtaining the token, paste it into the
Restart the MCP client (if required)
- Some MCP clients require a full restart for env changes to take effect. Quit and restart the client/service that runs the MCP server.
Verify the connection
- Use the MCP tool
acp_whoamior send a simple MCP request like “List my ACP sessions” to verify authentication and cluster access. - If you see authentication errors (401/403), confirm the token is correct and not expired, or verify the clusters.yaml content and file permissions.
- Use the MCP tool
If you need more details
- If your admin requires a specific gateway URL or token creation steps, follow your organization’s ACP gateway documentation or ask the ACP platform administrator for the exact token creation URL and permissions required.
Quick Start
Choose Connection Type for
Authentication Required
Please sign in to use FastMCP hosted connections
Run MCP servers without
local setup or downtime
Access to 1,000+ ready-to-use MCP servers
Skip installation, maintenance, and trial-and-error.
No local setup or infra
Run MCP servers without Docker, ports, or tunnels.
Always online
Your MCP keeps working even when your laptop is off.
One secure URL
Use the same MCP from any agent, anywhere.
Secure by default
Encrypted connections. Secrets never stored locally.
Configuration for
Environment Variables
Please provide values for the following environment variables:
HTTP Headers
Please provide values for the following HTTP headers:
started!
The MCP server should open in . If it doesn't open automatically, please check that you have the application installed.
Copy and run this command in your terminal:
Make sure Gemini CLI is installed:
Visit Gemini CLI documentation for installation instructions.
Make sure Claude Code is installed:
Visit Claude Code documentation for installation instructions.
Installation Steps:
Configuration
Installation Failed
More for Cloud Platforms
View All →Salesforce
Unlock powerful Salesforce org management with the Salesforce DX MCP Server, designed for seamless interaction between large language models and Salesforce environments. This developer preview offers secure, direct access to Salesforce resources without exposing secrets, using TypeScript libraries and granular org allowlisting. Its modular toolsets cover org administration, data queries, user permissions, metadata deployment, and testing. Easily extendable and compatible with various clients like VS Code, Cursor, and more, it empowers developers to perform complex tasks with natural language commands while maintaining robust security. The MCP Server streamlines Salesforce DX workflows through an efficient, secure, and flexible protocol.
Hostinger API
Integrates with Hostinger's hosting platform to enable domain registration and DNS management, VPS creation and configuration, firewall setup, backup operations, and billing subscription handling through over 100 specialized tools organized by service category.
Netlify
Control your Netlify projects effortlessly using natural language through AI agents with Netlify MCP Server. This server follows the Model Context Protocol to enable code agents to create, deploy, and manage sites, configure access controls, handle environment variables, and more—all via simple prompts. It acts as a bridge between AI clients and Netlify’s API and CLI, empowering seamless automation and resource management. Whether retrieving team data or managing forms and extensions, Netlify MCP Server streamlines your workflow by integrating powerful AI-driven project control in an accessible, standardized way.
Azure All
Supercharge AI agents with seamless access to Azure services using Azure MCP Server. This project enables powerful automation and management of Azure resources with tools for databases, storage, monitoring, security, and best practices. Easily interact with services like Cosmos DB, SQL, Key Vault, Service Bus, and more—all within compatible AI platforms. Azure MCP Server is in Public Preview and rapidly evolving, making it a versatile solution for both developers and enterprise environments looking to integrate Azure functionality.
Tencent EdgeOne Pages
Effortlessly publish HTML, folders, or zip files with instant public URLs using EdgeOne Pages MCP. This service streamlines rapid deployment of your static content via EdgeOne Pages, leveraging serverless edge functions and key-value storage for fast, reliable delivery. Users can quickly deploy content and receive shareable links, making it ideal for web developers and teams needing easy, scalable web hosting.
More for Developer Tools
View All →
GitHub
Extend your developer tools with the GitHub MCP Server—a powerful Model Context Protocol server enhancing automation and AI interactions with GitHub APIs. It supports diverse functionalities like managing workflows, issues, pull requests, repositories, and security alerts. Customize available toolsets to fit your needs, enable dynamic tool discovery to streamline tool usage, and run the server locally or remotely. With read-only mode and support for GitHub Enterprise, this server integrates deeply into your GitHub ecosystem, empowering data extraction and intelligent operations for developers and AI applications. Licensed under MIT, it fosters flexible and advanced GitHub automation.
Desktop Commander
Desktop Commander MCP transforms Claude Desktop into a powerful AI assistant for managing files, running terminal commands, and editing code with precision across your entire system. It supports in-memory code execution, interactive process control, advanced search and replace, plus comprehensive filesystem operations including reading from URLs and negative offset file reads. With detailed audit and fuzzy search logging, it enables efficient automation, data analysis, and multi-project workflows—all without extra API costs. Designed for developers seeking smarter automation, it enhances productivity by integrating all essential development tools into a single, intelligent chat interface.
Chrome DevTools
Provides direct Chrome browser control through DevTools for web automation, debugging, and performance analysis using accessibility tree snapshots for reliable element targeting, automatic page event handling, and integrated performance tracing with actionable insights.
FreeCAD
Enables AI-driven CAD modeling by providing a remote procedure call (RPC) server that allows programmatic control of FreeCAD, supporting operations like creating documents, inserting parts, editing objects, and executing Python code for generative design workflows.
Similar MCP Servers
Amicus MCP Server
A state persistence layer that enables seamless handoffs between different AI coding assistants by maintaining a shared context bus. It provides tools for tracking summaries, next steps, and active files to ensure continuity across development sessions.
DollhouseMCP
A comprehensive Model Context Protocol (MCP) server that enables dynamic AI persona management with an integrated GitHub-powered marketplace, allowing Claude and other compatible AI assistants to activate different behavioral personas.
astro-airflow-mcp
An MCP server that enables AI assistants to interact with Apache Airflow's REST API for DAG management, task monitoring, and system diagnostics. It provides comprehensive tools for triggering workflows, retrieving logs, and inspecting system health across Airflow 2.x and 3.x versions.