Publishing agents as MCP tool providers

The global Bifrost MCP server exposes every tool the connecting user has access to. Sometimes you want the opposite: a focused, single-agent endpoint that an external chat service (Claude, Copilot, Cursor) can use as a tool. Bifrost supports this via per-agent MCP endpoints.

What this gives you

A per-agent MCP endpoint scopes tool visibility to exactly one agent’s tool list. From the client’s perspective, the endpoint is a single coherent capability — “Bifrost ticket-triage agent” — rather than the full platform surface.

Use it to:

• Publish a domain-specific agent (a billing assistant, a Microsoft 365 inspector, a runbook executor) as a callable tool inside Claude Desktop, Copilot, or Cursor.
• Hand a community user one URL that gives them exactly the tools you’ve curated, with no ability to enumerate the full platform.
• Compose Bifrost agents inside another organization’s MCP-enabled chat service via OAuth.

How agent-scoped endpoints work

The Bifrost MCP server intercepts requests to https://your-instance/mcp/{agent_id}. The middleware extracts the agent UUID from the path, scopes the tool list to that agent’s tools and system_tools, and rewrites the path to /mcp so the underlying server logic still runs.

OAuth discovery is served per-agent at /.well-known/oauth-authorization-server/mcp/{agent_id} and /.well-known/oauth-protected-resource/mcp/{agent_id} — clients that perform path-aware discovery (Claude, Cursor) will use the correct endpoints automatically.

Publish an agent as MCP

1. Confirm the global MCP server is enabled in Settings → MCP. Per-agent endpoints share the same OAuth provider as the root endpoint.

2. On the agent detail page, copy the agent’s UUID from the URL bar (/agents/{id}). This is the path component for the MCP URL.

3. Build the per-agent URL: https://your-instance.com/mcp/{agent_id}. Share it with whoever is configuring the external client.

Note

The agent’s Access Level still applies. If the agent is Role-based, the connecting user must have a matching role or they connect successfully but see an empty tool set.

Configure in Claude Desktop

1. Open Claude Desktop’s claude_desktop_config.json.

2. Add an mcpServers entry for the agent endpoint:

   {
     "mcpServers": {
       "bifrost-ticket-triage": {
         "url": "https://your-instance.com/mcp/aaaa1111-bbbb-2222-cccc-333344445555"
       }
     }
   }

3. Restart Claude. On first use, Claude opens the OAuth flow scoped to this agent. After login, only this agent’s tools appear in the tool tray.

Example: a triage agent inside Claude

Imagine you have ticket-triage-agent configured in Bifrost with three tools: lookup_customer, get_ticket, and update_ticket. Publishing it as MCP gives Claude exactly those three tools — not the full Bifrost surface.

A user in Claude can now say:

Look up customer alice@example.com and triage their open ticket.

Claude calls lookup_customer, then get_ticket, then update_ticket, all through the agent-scoped MCP endpoint. Each call is authenticated as the connecting user, runs through Bifrost’s normal permission checks, and is recorded as a regular tool execution in History.

Compose with other MCP servers

Because the per-agent endpoint is just another MCP server from the client’s perspective, it sits alongside any other MCP server the client uses. A Claude Desktop config might look like:

{
  "mcpServers": {
    "bifrost-platform": {
      "url": "https://your-instance.com/mcp"
    },
    "bifrost-ticket-triage": {
      "url": "https://your-instance.com/mcp/aaaa1111-bbbb-2222-cccc-333344445555"
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"]
    }
  }
}

Claude blends tools from all three. The agent-scoped endpoint keeps Bifrost’s surface narrow and predictable while the platform endpoint stays available for power users.

Next steps

• Configuring the MCP server
• Connecting Claude, Copilot, Cursor, and Open WebUI
• Agents and Chat — agent configuration including system_tools and Access Level