MCP Client

An MCP client that brings external AI tools into your workspace

Connect external MCP servers to your Runwork workspace and your AI assistant gains their capabilities. Connect a weather service, a code analysis tool, a knowledge base, anything with an MCP server. External tools appear alongside your apps and can be loaded as skills in any channel.

External MCP Servers

Company Knowledge Base docs.internal.acme.com/mcp

Connected

search_docs get_article 2 tools

Code Analysis code-review.tools.dev/mcp

Connected

analyze_code find_vulnerabilities suggest_refactors check_dependencies lint_project 5 tools

Weather API weather.api.tools/mcp

Connected

get_weather get_forecast get_alerts 3 tools

Allowed Domains

docs.internal.acme.com code-review.tools.dev weather.api.tools

10 external tools available

Capabilities

Connect Any MCP Server

Add external MCP server URLs in workspace settings. Your AI assistant immediately discovers and can use their tools. No code, no configuration beyond the URL.

Auto-Discovery

When you connect an MCP server, Runwork automatically discovers available tools, resources, and prompts. They appear in your workspace ready to use.

Unified Tool Set

External MCP tools work alongside your native workspace tools. Your AI can query your CRM (native) and check the weather (external MCP) in the same conversation.

External Tools as Skills

Connected MCP tools automatically generate skill descriptions. Browse them with slash commands, pin them to channels, use them like any other skill.

Domain Allowlisting

Security first. Approve which external domains your AI can call. Manage the allowlist from workspace settings. Rate limiting built in.

HTTP Request Tool

Skills that reference external APIs get a secure HTTP request tool. The AI can call approved endpoints directly, with full request and response handling.

Use Cases

External knowledge bases Weather and location data Code analysis tools Third-party AI services Company documentation Market data feeds

Why It Matters

Extend your workspace with any MCP-compatible service
External tools feel native: same slash commands, same skill system
Secure by default with domain allowlisting and rate limiting
The AI ecosystem flows both ways: out via MCP Servers, in via MCP Client

How It Works

The MCP Client is the other half of Runwork's AI ecosystem. While MCP Servers let external tools access your workspace, the MCP Client lets you bring external tools in. Connect any MCP server URL and your workspace AI gains new capabilities instantly.

Adding an external MCP server is simple: paste the server URL in your workspace settings and Runwork connects, authenticates, and discovers all available tools, resources, and prompts. These show up alongside your native workspace tools. Your Work Assistant can use them in any conversation without you having to switch contexts or tools.

External MCP tools automatically become skills. This means you can browse them with slash commands, pin them to channels, and load them into conversations just like your vibe-app skills. Your AI can orchestrate across native apps and external services in the same conversation.

Security is built in. Every external domain must be explicitly approved in your workspace allowlist before the AI can make calls. Rate limiting prevents abuse. You manage the allowlist from workspace settings, and it applies to both MCP connections and direct HTTP requests from skills.

The MCP Client also enables a powerful pattern: connect your company's internal MCP servers to centralize knowledge. A documentation server, a metrics server, an HR system. Your workspace AI becomes the single point that can access and orchestrate across all of them, combined with your vibe-coded apps, integrations, and workflows.

Frequently Asked Questions

What can I connect as an MCP client?

Any service that exposes an MCP server. This includes company knowledge bases, documentation systems, weather APIs, code analysis tools, market data feeds, HR systems, and more. The MCP ecosystem is growing rapidly. If a service has an MCP server, Runwork can connect to it.

How do external MCP tools appear in my workspace?

When you add an MCP server URL, Runwork auto-discovers its tools, resources, and prompts. External tools appear alongside your native workspace tools. They also automatically generate skill descriptions, so you can browse them via slash commands, pin them to channels, and load them into conversations.

Is it secure to connect external MCP servers?

Yes. Security is built in at multiple levels. Every external domain must be explicitly added to your workspace allowlist. Rate limiting prevents excessive calls. Authentication credentials are stored securely. You control exactly which external services your workspace AI can access.

Can I use external MCP tools in channel conversations?

Absolutely. External MCP tools become skills that you can load via slash commands or pin to channels. Ask a question in #sales and the AI can query your CRM (native app), check a lead enrichment service (external MCP), and draft a follow-up email, all in the same conversation.

What is the difference between MCP Server and MCP Client?

MCP Server exposes your Runwork workspace to external AI tools (outbound). MCP Client brings external services into your workspace (inbound). Together, they create a two-way bridge: your workspace is part of the broader AI ecosystem, and the broader ecosystem is part of your workspace.

Related Features

MCP Servers Skills Integrations

See How Teams Use MCP Client

AI Ecosystem CTOs AI-Powered Apps

Ready to try MCP Client?

Start vibe-coding with Runwork today.

Get Started Explore More Features