Gorgias MCP

Live

OAUTH 2.1

SUPPORT TICKETS

Customer Support

Gorgias MCP gives agents authenticated access to your support tickets: search conversations, reply and close, snooze, tag, and manage macros and help center content.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Gorgias MCP
agent · Acme Q3
Run
Find tickets mentioning a defective hinge and reply to the newest one.
S
gorgiasmcp_search_tickets
104ms
Gorgias agent
3 tickets matched. Replied to #48211 with a replacement offer and closed it.
Sources: 3 tickets, 1 closed
gorgiasmcp
3 tickets
18:29
Message Claude...

Tools your support agent reaches for on Gorgias, scoped per user.

CALL ANY TOOL
Search, reply, and manage support tickets end to end, scoped to each user's own Gorgias access.
gorgiasmcp_search_tickets
Search tickets
Full-text search across ticket subjects, messages, and customer fields. Results are ordered by relevance.
Parameters
Name
Type
Required
Description
query
string
Required
The text to search for across ticket subjects, messages, and customer fields.
filters
string
Optional
Optional Gorgias view-DSL filter expression, e.g. ticket.status=='open'.
limit
integer
Optional
Max tickets to return (1-100, default 30).
gorgiasmcp_get_ticket
Get ticket
gorgiasmcp_reply_and_close
Reply and close
gorgiasmcp_snooze_ticket
Snooze ticket
gorgiasmcp_add_internal_note
Add internal note
gorgiasmcp_update_tone_of_voice
Update tone of voice
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Gorgias tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gorgiasmcp"], toolNames: [
    "gorgiasmcp_search_tickets",
    "gorgiasmcp_get_ticket",
    "gorgiasmcp_reply_and_close"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Reply to the newest hinge complaint and close it" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gorgiasmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Reply to the newest hinge complaint and close it" }],
  tools,
});

// Execute the tool call with the user's vaulted gorgiasmcp credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gorgiasmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Reply to the newest hinge complaint and close it" }],
  tools,
});

// Tool call runs with the user's vaulted gorgiasmcp credential
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gorgiasmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "gorgiasmcp_agent",
  model: "gemini-2.5-pro",
  instruction: "Gorgias tools scoped to this user",
  tools,
});

await agent.run("Reply to the newest hinge complaint and close it");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Gorgias MCP tool. Click to copy, paste into your agent, done.
Ticket triage
Copy the prompt
Copied
Find tickets mentioning a defective hinge from the last week.
Copy the prompt
Copied
Get ticket 48211 with its full message thread.
Copy the prompt
Copied
Search open tickets tagged 'refund' by priority.
Resolve and close
Copy the prompt
Copied
Reply to ticket 48211 with a replacement offer and close it.
Copy the prompt
Copied
Snooze ticket 50210 until Monday 9am with a note.
Copy the prompt
Copied
Add tags 'shipping-delay' to ticket 49102.
Help center and tone
Copy the prompt
Copied
Update the AI Agent tone of voice for artemisathletix to Friendly.
Copy the prompt
Copied
Publish the draft help center article about return policy.
Copy the prompt
Copied
Apply macro 812 to ticket 48901.
SEE HOW AUTH WORKS
Your users connect once. Their Gorgias MCP credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Gorgias MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Gorgias MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Gorgias MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Gorgias MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other support connectors.
SUPPORT
Support triage agent
Read Zendesk tickets, fetch runbooks from Notion, and route to the right Slack channel with a drafted response.
SUPPORT
Support ticket automation (Google ADK)
Google ADK agent that classifies Zendesk tickets, pulls Notion context, and posts to Slack. End-to-end ticket handoff.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with identity, scope enforcement, and audit. Connectors follow.
01.
Shared tokens break per-user analytics
A shared Gorgias MCP token looks fine in a demo. In production every ticket reply looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Gorgias MCP today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Gorgias MCP as the user or through a shared key?
As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every Gorgias MCP action in your audit trail is attributed to a real user, not a shared service account.
Where is the Gorgias MCP token stored?
In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, refresh automatically, and can be revoked from one dashboard.
Can I limit what the agent does in Gorgias MCP?
Yes. Filter by tool name in listScopedTools to expose only what you want. Scalekit also enforces scope checks before every API call.
What happens when a user revokes access?
The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.
Can the agent post replies without my review?
Only if you scope reply_and_close into the tool set you expose. Keep it out of listScopedTools to require a human to send the final reply while still letting the agent search, tag, and draft internal notes.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""gorgiasmcp"": {
""url"": ""https://mcp.scalekit.com/gorgiasmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.gorgiasmcp]
url = ""https://mcp.scalekit.com/gorgiasmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""gorgiasmcp"": {
""url"": ""https://mcp.scalekit.com/gorgiasmcp"",
""type"": ""http""
}
}
}