Upstream Servers

Configure and manage MCP servers

Ultra proxies requests to one or more upstream MCP servers. Servers can use stdio transport (local commands) or HTTP transport (remote URLs).

Only add MCP servers from official or trusted sources. Untrusted community servers can execute arbitrary code on your machine (stdio transport) or receive sensitive data from your AI agents (HTTP transport). Stick to servers from the official MCP Registry, verified publishers, or servers your organization has reviewed and approved.

Client

Add Servers Through Your AI Client

The simplest way to add MCP servers is to ask your AI client to do it for you. Since Ultra is already connected to your client, just tell it what services you want to connect:

• “Connect to the Notion MCP server”
• “Add the GitHub MCP server”
• “Set up the filesystem server so you can read my project files”
• “Add the Linear MCP server”

Your AI client will work with Ultra to search the registry, install the server, and configure any required authentication (API keys, OAuth, etc.).

After adding a server, restart your MCP client for the new server to become available.

Make sure your client installs the official MCP server for each service — not a random community fork. Look for servers published by the service provider (e.g., @notionhq/notion-mcp-server) or from the official MCP Registry. If you’re unsure, ask your client to confirm the publisher before installing.

You can also ask your client to list your current servers (“What MCP servers do I have connected?”) or remove ones you no longer need.

Popular Servers

Select a server to see setup instructions.

Notion

Ask your AI client: “Add the Notion MCP server”

Notion uses OAuth. You will be redirected to Notion in your browser to authorize access to your workspace. Tokens are stored and refreshed automatically.

You need to be a member of the Notion workspace you want to connect.

Slack

Ask your AI client: “Add the Slack MCP server”

Slack uses OAuth. You will be redirected to Slack in your browser to authorize.

Linear

Ask your AI client: “Add the Linear MCP server”

Linear uses OAuth. Authorize in your browser when prompted.

GitHub

Ask your AI client: “Add the GitHub MCP server”

You will be prompted for a Personal Access Token (PAT). Create one at github.com/settings/tokens with the scopes you need (typically repo and read:org).

Use a fine-grained PAT scoped to only the repositories you need for better security.

Figma

Ask your AI client: “Add the Figma MCP server”

Figma uses OAuth. You will be redirected to Figma in your browser to authorize access to your files and projects.

AWS

Ask your AI client: “Add the AWS MCP server”

You will need AWS credentials configured on your machine (via ~/.aws/credentials or environment variables).

Jira

Ask your AI client: “Add the Jira MCP server”

You will be prompted for your Jira instance URL and an API token. Create one at id.atlassian.com/manage-profile/security/api-tokens.

Mintlify

Ask your AI client: “Add the Mintlify MCP server”

You will need your Mintlify project subdomain or API key.

Salesforce

Ask your AI client: “Add the Salesforce MCP server”

Salesforce uses OAuth. You will be redirected to Salesforce in your browser to authorize access to your org.

Datadog

Ask your AI client: “Add the Datadog MCP server”

You will be prompted for your Datadog API key and application key. Find these in your Datadog org settings under API Keys.

PostgreSQL

Ask your AI client: “Add the PostgreSQL MCP server”

You will be prompted for your database connection string. Use a read-only database user when possible.

Vanta

Ask your AI client: “Add the Vanta MCP server”

Vanta uses OAuth. You will be redirected to Vanta in your browser to authorize. Once approved, the token is stored and refreshed automatically.

You need an active Vanta account with appropriate permissions. If you see an authentication error, check with your Vanta admin that your account has API access enabled.

Filesystem

Ask your AI client: “Add the filesystem server for my project files”

The filesystem server runs locally and does not require authentication. You will be asked which directories to allow access to.

Only grant access to directories you are comfortable sharing with your AI client. Never point it at your home directory or root.

Supported Clients

Ultra works with all major MCP-compatible AI clients:

Client	Type
Claude Desktop	Desktop app
Cursor	IDE
VS Code	IDE
GitHub Copilot	IDE (via VS Code)
Claude Code	CLI
Codex	CLI
Windsurf	IDE
Roo Code	VS Code extension
Goose	CLI
Gemini	Desktop app
LM Studio	Desktop app
Amazon Q Developer	CLI
Ona	Cloud dev environment
Hermes	Agent framework

Run ultra doctor to see which clients are detected on your machine, or ultra install to configure a specific client.

Terminal

Adding Servers from Registry

The easiest way to add servers is from the MCP registry:

# Search for servers
ultra search filesystem

# Add by name (searches registries)
ultra add filesystem

# Add by full package name
ultra add @modelcontextprotocol/server-filesystem

# Add with a custom name
ultra add @modelcontextprotocol/server-filesystem --name myfiles

When adding from the registry, Ultra automatically tests the connection, detects authentication requirements, and prompts for any required configuration (API keys, file paths, etc.).

Adding Remote Servers by URL

Add HTTP-based MCP servers directly by URL:

# Add a remote server
ultra add https://mcp.slack.com/mcp

# With a custom name
ultra add https://remote.example.com/mcp --name myserver

Ultra auto-detects transport type and authentication requirements. If the server requires OAuth, you’ll be prompted to authorize when it’s first used. For token-based auth, Ultra prompts for the token during setup.

Popular Servers

Select a server below for specific setup instructions.

Notion

ultra add notion

Notion uses OAuth. Ultra opens your browser for authorization. Tokens are stored and refreshed automatically.

You need to be a member of the Notion workspace you want to connect.

Slack

ultra add https://mcp.slack.com/mcp --name slack

Slack uses OAuth. Ultra opens your browser to authorize. Once approved, your AI client can send messages, search conversations, and interact with your workspace.

Linear

ultra add linear

Linear uses OAuth. Authorize in your browser when prompted. Your AI client can then read and manage issues, projects, and cycles.

GitHub

ultra add github

GitHub requires a Personal Access Token (PAT). Ultra prompts you to enter it during setup. Create one at github.com/settings/tokens with the scopes you need (typically repo and read:org).

Use a fine-grained PAT scoped to only the repositories you need for better security.

Figma

ultra add https://mcp.figma.com/mcp --name figma

Figma uses OAuth. Ultra opens your browser for authorization. Tokens are stored and refreshed automatically.

AWS

ultra add aws

The AWS server uses your local AWS credentials (~/.aws/credentials or environment variables). Make sure aws configure is set up before adding.

Jira

ultra add jira

Jira requires your instance URL and an API token. Create one at id.atlassian.com/manage-profile/security/api-tokens. Ultra prompts for both during setup.

Mintlify

ultra add mintlify

When prompted, enter your Mintlify project subdomain or API key.

Salesforce

ultra add salesforce

Salesforce uses OAuth. Ultra opens your browser for authorization. Tokens are stored and refreshed automatically.

Datadog

ultra add datadog

Datadog requires an API key and application key. Find these in your Datadog org settings under API Keys. Ultra prompts for both during setup.

PostgreSQL

ultra add postgres

When prompted, enter your PostgreSQL connection string (e.g., postgresql://user:pass@host:5432/dbname). Use a read-only database user when possible.

Vanta

ultra add https://mcp.vanta.com/mcp --name vanta

Vanta uses OAuth. Ultra detects this automatically and opens your browser to authorize. Once approved, tokens are stored and refreshed automatically.

You need an active Vanta account with appropriate permissions. If you see an authentication error, check with your Vanta admin that your account has API access enabled.

Filesystem

ultra add filesystem

The filesystem server runs locally (stdio transport) and does not require authentication. When prompted, specify the directory paths you want to allow access to.

Only grant access to directories you are comfortable sharing with your AI client. Never point it at your home directory or root.

Adding Servers Manually

Use ultra servers add for full control:

# Stdio transport (local command)
ultra servers add filesystem \
  --command npx \
  --args "-y @modelcontextprotocol/server-filesystem /tmp"

# HTTP transport (remote URL)
ultra servers add remote-api --url https://mcp.example.com/sse

# With environment variables
ultra servers add github \
  --command npx \
  --args "-y @modelcontextprotocol/server-github" \
  --env "GITHUB_TOKEN=ghp_xxx"

# Add in disabled state
ultra servers add test-server --command ./test-server --disabled

Managing Servers

# List all servers
ultra servers

# Enable/disable
ultra servers enable filesystem
ultra servers disable filesystem

# Remove
ultra servers remove filesystem
ultra servers remove filesystem --force  # Skip confirmation

Stdio vs HTTP Transport

Stdio Transport

For servers that run as local processes. Ultra spawns the process and communicates over stdin/stdout.

upstream:
  filesystem:
    command: npx
    args: ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
    env:
      NODE_ENV: production
    enabled: true

HTTP Transport

For remote servers. Ultra connects over HTTP/SSE.

upstream:
  notion:
    url: "https://mcp.notion.so"
    headers:
      Authorization: "Bearer secret_xxx"
    enabled: true

Authentication

Token-Based Auth

Set auth tokens for HTTP servers:

# Set during add (interactive)
ultra add https://mcp.example.com/sse

# Set after adding
ultra config set-token my-server YOUR_TOKEN

# Set a custom header
ultra config set-header my-server X-API-Key YOUR_KEY

Tokens are stored as Authorization: Bearer {token} headers in the config file.

OAuth2

Ultra supports OAuth2 authentication for upstream servers that require it. The OAuth flow is handled automatically at runtime — when a server requires authorization, Ultra opens a browser for you to complete the flow and stores the tokens for future requests.

Environment Variables

For stdio servers, pass secrets via environment variables instead of hardcoding them in args:

upstream:
  github:
    command: npx
    args: ["-y", "@modelcontextprotocol/server-github"]
    env:
      GITHUB_TOKEN: "ghp_xxxxxxxxxxxx"
    enabled: true