Team MCP for the AI agent

Standard remote MCP contract Ticketping expects from your server — transport, auth, read-only tools, and how to connect.

Ticketping’s support AI can call your tools over the Model Context Protocol. We act as an MCP client. You host a normal remote MCP server; there is no Ticketping-specific RPC, SDK, or required tool names.

Teams that skip MCP can still use the agent with static knowledge in Settings → AI agent.

What to expose

Piece	Expectation
Transport	Streamable HTTP (preferred) or SSE-compatible responses on one HTTPS endpoint
Protocol	JSON-RPC 2.0: `initialize`, `notifications/initialized`, `tools/list`, `tools/call`
Auth	`Authorization: Bearer <token>` (optional custom headers also supported)
Customer-facing tools	Read-only lookups only (docs search, account status, order status, …)
Response shape	Prefer JSON with `title` + `url` (and a short snippet) so we can show citations

Writable actions (refunds, cancels, deletes) are blocked for the customer-facing agent today, even if the tool appears in tools/list.

Recommended tools (conventions)

Names are yours to choose. These shapes work well:

Docs search

json

{
  "name": "search_docs",
  "description": "Search the public help center and product docs",
  "inputSchema": {
    "type": "object",
    "properties": {
      "query": { "type": "string" }
    },
    "required": ["query"]
  }
}

Return something like:

json

{
  "results": [
    {
      "title": "How refunds work",
      "url": "https://docs.example.com/refunds",
      "snippet": "Refunds are available within 14 days…"
    }
  ]
}

Account / order lookup (read-only)

json

{
  "name": "get_account_status",
  "description": "Look up subscription status for a customer id or email",
  "inputSchema": {
    "type": "object",
    "properties": {
      "customer_id": { "type": "string" },
      "email": { "type": "string" }
    }
  },
  "annotations": { "readOnlyHint": true }
}

Mark read-only tools with annotations.readOnlyHint: true when you can. Tools whose names look mutating (refund, delete, cancel, …) are treated as writable and stay off the allowlist.

Connect in Ticketping

Open Settings → AI agent → MCP.
Paste your MCP URL and optional bearer token.
Turn Enabled on and click Test & sync tools.
Allowlist only the tools the customer-facing agent may call.
Optionally add Guidance (tone, when to escalate, which tool for which intent).
Use Preview to try the same runtime as the widget.

Limits we enforce: about 15s per tool call, a small number of tool rounds per turn, and truncated tool results so chats stay responsive.

Without MCP

If you do not run an MCP server yet:

Add articles under Settings → AI agent → Knowledge.
Turn on AI answers for your widget.
The agent answers only from that knowledge (or hands off to a human).

You can keep knowledge articles after you connect MCP — they act as short policy / tone context alongside live tools.

Migration and reuse

The same MCP server works with other MCP clients (Cursor, Claude, custom agents).
Later, Ticketping may offer first-party tools (help center search, public URL fetch). You can shrink or remove your server then; only the connection and allowlist change — not a new protocol.
No Ticketping SDK is required. A minimal Streamable HTTP MCP server in Node or Python is enough.

Minimal curl check

After initialize (and reading Mcp-Session-Id if the server returns one):

bash

curl -s -X POST 'https://mcp.example.com/mcp' \
  -H 'Authorization: Bearer YOUR_TOKEN' \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H 'MCP-Protocol-Version: 2025-03-26' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

You should get a JSON-RPC result with a tools array. If that works, Test & sync in the dashboard should too.

Start with one read-only `search_docs` tool. Allowlist it, preview a few questions, then add account lookups once answers look solid.