Skip to main content
DocumentationAPI ReferenceVideo Tutorials

MCP Servers

MCP — the Model Context Protocol — is an open standard that lets AI assistants discover and call external tools. If you run an MCP-compatible server (your own, or one of the many community servers), you can plug it into Hanc.AI and your agents will get the server's tools at the moment a call begins.

Once connected, the agent can call those tools mid-conversation — pulling live data, running calculations, kicking off backend workflows — exactly like the built-in Calendar, HubSpot, or API Tool integrations.

Available on every plan

MCP servers are available on all plans including Free. There's no per-server fee — you only pay for the call minutes your agent uses when invoking the tools.

When to Use MCP​

ScenarioWhy MCP Fits
You already run an internal tool serverOne connection, all your tools available to every agent
You want to share tools across agentsConnect once, attach to as many agents as you like
You use community MCP serversPlug in popular open-source MCP servers without writing custom code
Your tool surface changes frequentlyThe agent re-discovers tools at each call — add/remove tools server-side without touching the dashboard

If you have a single one-off endpoint, the API Tool is simpler. If you have a set of related tools, or you already maintain an MCP server, this is the right integration.

Connecting an MCP Server​

1. Open the Integrations page​

In the dashboard sidebar, go to Integration. Scroll to the MCP servers section.

2. Click "Connect MCP server"​

A modal opens. Fill in:

FieldDescription
LabelA short name for this connection (e.g. "Sales Tools", "Internal CRM"). The label is shown in the agent tool picker and prefixes the tool names presented to the AI, so keep it short and meaningful.
URLThe HTTPS URL of your MCP server. Must be a publicly reachable address — http:// and private/internal addresses are rejected.
AuthenticationNone if your server is open, or Bearer token if it expects an Authorization: Bearer … header.
Token(Bearer only) Your auth token. Stored encrypted — only your platform account can decrypt it for use.

Click Save. Hanc.AI verifies the URL format and stores the connection. The connection is now available to every agent in your workspace.

Labels matter

Tool names from each MCP server are prefixed with the connection label, so an MCP server with a lookup_order tool connected as "Shop API" will appear to the agent as Shop_API_lookup_order. This prevents collisions when you connect multiple MCP servers that happen to have similarly-named tools.

3. Edit, disable, or delete​

The MCP servers list shows the label, URL, auth type, and status of every connection you've added. Use the row actions to:

  • Edit — change label, URL, auth type, or token
  • Delete — remove the connection entirely

Removing a connection deactivates it for every agent that had it attached — those agents simply lose access to its tools on the next call.

Attaching MCP Tools to an Agent​

A connection in your workspace is available to your agents — but each agent decides individually which of your connections to expose. This means you can have separate Sales and Support agents that pull from different MCP servers.

1. Open the agent's Actions tab​

Pick the agent. Open the Actions tab. Click Add Action.

2. Choose "MCP servers" from the Live-call group​

The dropdown shows three groups: Pre fetch, Live call, Post call. Look in the Live-call group — that's where MCP servers belongs, because the agent invokes MCP tools during the conversation, not before or after.

3. Toggle which connections to enable​

The modal lists every MCP connection in your workspace, each with an on/off toggle. Switch on the ones this agent should use. You can also write a short instruction in the "When to use it" field — this is what the agent reads to decide when to reach for these tools during a conversation.

Click Save. The agent now has access to the tools from every enabled MCP connection.

Mix and match

You can have one MCP connection enabled on five agents and another enabled on only one — each agent has its own MCP servers tool with its own set of toggles.

How It Works at Call Time​

When a call starts, the agent connects to each of its enabled MCP servers and asks "what tools do you offer?" Whatever the server returns is exposed to the AI as a tool it can call during the conversation.

A few things to know:

  • Tools are discovered at call start. If you add or remove tools on your MCP server, the change shows up on the very next call — no need to update anything in Hanc.AI.
  • Tool names are prefixed with the connection label (so "Shop API" + tool search_products → Shop_API_search_products). Built-in agent tools and other MCP tools won't clash.
  • Tool descriptions and parameter schemas come from your MCP server. Write good descriptions there — that's what the AI uses to decide when and how to call the tool.
  • Errors are reported back to the agent. If a tool call fails, the agent sees the error message and can decide to retry, apologise, or try a different tool.

Requirements for Your MCP Server​

To work with Hanc.AI, your server needs to:

RequirementDetail
HTTPSPlain http:// is not accepted. Use a real TLS certificate.
Public URLThe URL must resolve to a public address — Hanc.AI can't reach servers on a private network or localhost.
MCP Streamable HTTP transportThe current MCP HTTP transport over a single endpoint. SSE-only and stdio transports are not supported in this integration.
Bearer auth (optional)If your server requires authentication, it must accept a standard Authorization: Bearer <token> header.

If you're hosting your own server behind a firewall, expose it via a tunnel or reverse proxy with a public HTTPS endpoint.

Security and Privacy​

Your bearer tokens are stored encrypted at rest. Only Hanc.AI's call infrastructure can decrypt them, and only at the moment a call starts and the agent needs to connect to your server.

Tool calls flow agent → Hanc.AI → your MCP server → back. We don't log tool call payloads. Your server logs whatever you choose to log on your end.

If you change or rotate your token, edit the connection in the dashboard — the new value takes effect on the next call.

Plan Availability​

PlanMCP Servers
FreeAvailable
Starter / Pro / Business / EnterpriseAvailable

There is no per-connection charge — you only pay for the call minutes during which the agent invokes the tools.

Troubleshooting​

"Connection won't save"​

  • Make sure the URL begins with https:// and not http://.
  • Make sure the host is publicly reachable — localhost, 127.0.0.1, and internal addresses are blocked by design.
  • Re-check the bearer token if you set one — extra whitespace or quotes will break the save.

"Agent doesn't see the tools"​

  • Check that the MCP server entry on the agent's Actions tab has at least one connection toggled on and the entry is saved.
  • Make sure your MCP server is responding to a tools/list request and not requiring an interactive auth flow.
  • Look in the agent's call log for messages from the MCP connection right at the start of the call.

"Tool fails mid-call"​

  • The agent will see whatever error your server returns. Check your server logs.
  • Long-running tools may time out — keep MCP tool execution under a few seconds per call so the visitor doesn't sit in silence.

"I changed tools on my server but the agent still uses old ones"​

  • Tools are re-discovered at the start of each call, not cached across calls. The very next new call sees the updated tool set. Ongoing calls keep the tools they were given at start.