Skip to main content
The MCP client integration lets you connect remote MCP servers to your Relevance AI agents. This gives your agents access to tools hosted on external platforms — so you can pull in capabilities from other services without rebuilding them in Relevance AI.
This page is about connecting external MCP servers to Relevance AI agents. If you want to use Relevance AI from an AI client like Claude or Cursor, see Programmatic GTM.

​
Setting up an MCP connection for Agents

Agents can connect to and run tools from remote MCP servers.
  1. Open the Agent you want to connect
  2. Navigate to the Tools tab in the agent builder
  3. Click Add MCP
  4. Click Connect my own
  5. Add the URL of the remote hosted MCP server
  6. Label your MCP Server connection
  7. Add any authentication details required for the MCP server
The connection label you provide will appear in tool descriptions as (MCP: connection-name). This helps agents distinguish between tools from different connections, especially when using multiple instances of the same MCP server.
Once connected, the agent will automatically fetch and display the available tools from the remote MCP server. These tools can be referenced in the agent’s core instructions and will appear in the conversation task view. When a tool is run, the agent communicates with the remote MCP server and returns the result directly in the conversation.
Local MCP server support (e.g. JSON configuration) is not available.

​
Connecting multiple instances of the same MCP server

You can connect the same MCP server URL multiple times within a project. Each connection operates independently with its own authentication credentials, label, and configuration. Tools from each connection display (MCP: connection-name) in their descriptions so agents can distinguish which connection a tool belongs to. This is useful when you need different authentication contexts (e.g. separate user credentials for different data access), environment separation (staging vs production), or multi-tenant setups where each connection uses different tenant credentials.

​
Best practices

Choose labels that clearly indicate the purpose or context of each connection, such as github-prod, github-staging, or linear-team-a, linear-team-b.
When building agents that use multiple instances of the same server, include guidance in the agent’s core instructions about when to use tools from each connection.

​
Troubleshooting

  • Verify the MCP server URL is correct and the server is online
  • Check that any required authentication credentials are entered correctly
  • Ensure the external MCP server supports the Streamable HTTP transport
  • Confirm the tools are listed in the agent’s Tools tab after connecting
  • Check that the external MCP server has not revoked access or changed credentials
  • Try disconnecting and reconnecting the MCP server in the agent builder
  • The external MCP server may be temporarily unavailable — try again later
  • Check that the server URL does not require VPN or network access that Relevance AI cannot reach
  • Contact the MCP server provider if the issue persists

​
Frequently asked questions (FAQs)

You can connect any remote MCP server that supports the Streamable HTTP transport. This includes servers from services like Linear, Notion, GitHub, and any custom MCP servers you host.
Yes. You can add multiple MCP server connections to a single agent, giving it access to tools from several external services at once.You can also connect the same MCP server URL multiple times with different labels and credentials. This is useful for environment separation (staging vs production), different authentication contexts, or multi-tenant setups. See connecting multiple instances for details.
No. Relevance AI only supports remote MCP servers accessible via a public URL. Local MCP servers running on your machine (e.g. via JSON configuration) are not supported.