Gladly MCP connector
The Gladly connector brings your customers, conversations, tasks, agents, teams, and inboxes into Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent, so each person can look up a customer, read a thread, or create a follow-up task inside their own Gladly access, with every call logged.
- Connects with an API key
- Free 14-day trial
- No credit card
Summarize open Gladly tasks assigned to the support team.
Working in Gladly with Elaichi
-
List all Gladly agents
-
Get single Gladly agent by ID
-
List all Gladly customers
How to connect Gladly to Claude, ChatGPT, Cursor or Microsoft Copilot
Step by step, for each AI app
Gladly MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Gladly MCP connector for Claude Code
-
1
In a terminal, run
claude mcp addwith the endpoint.https://api.elaichi.ai/mcp -
2
Start Claude Code and run
/mcp. -
3
Pick elaichi, then sign in and approve in the browser.
Terminal
$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
Use --scope project instead to share it with the repository through .mcp.json.
Gladly MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web. The plugin directory lives at chatgpt.com/plugins.
Gladly MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Gladly MCP connector for Microsoft Copilot
-
1
In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
-
2
Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
https://api.elaichi.ai/mcp -
3
Create a new connection, sign in and approve, then press Add to agent.
-
4
Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.
- Server URL
- https://api.elaichi.ai/mcp
- Authentication
- OAuth 2.0
- Type
- Dynamic discovery
Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.
Connect Gladly to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
What teams do with Gladly through Elaichi
Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in Gladly is logged.
-
Support
Catch up on a customer before replying
Ask for a customer by name or email and get their Gladly profile plus every past conversation across email, chat, SMS, and voice in one view. No more scrolling through the timeline while the customer waits.
-
Support
Turn a promise into a Gladly task
When you tell a customer you will check on a refund or a reshipment, ask the agent to create the task in Gladly, assign it, and add a comment once it is done.
-
Customer experience
Summarize a long conversation thread
Pull every message and internal note from a Gladly conversation and get a short summary of what the customer asked, what was promised, and what is still open.
-
Support leadership
See who is handling what today
List Gladly agents, teams, and inboxes, then ask which tasks are open and who owns them, without opening a dozen tabs.
-
Quality
Pull conversations for coaching reviews
Fetch the recent conversations handled by a specific Gladly agent and review tone, accuracy, and follow-through before a one-to-one.
-
Operations
Correct customer records after checkout errors
Find the Gladly customer whose email or phone was entered wrong, update the details, or create a new customer record from an order that never matched.
Try asking
- “Summarize open Gladly tasks assigned to the support team.”
- “Which Gladly agents closed the most tasks last week?”
- “Show recent comments on Gladly tasks for this customer.”
What connecting Gladly gets you
6 screens from Elaichi, each doing one job for your Gladly account.
Ask Elaichi to work across your apps.
Summarize open Gladly tasks assigned to the support team.
Which Gladly agents closed the most tasks last week?
Show recent comments on Gladly tasks for this customer.
Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot
The agent
Ask about Gladly customers, get real answers.
Plain language questions run against live Gladly customers, tasks and agents.
Copy the endpoint
AI apps
Claude, ChatGPT, Cursor and Microsoft Copilot reach Gladly.
One org MCP endpoint over OAuth, no SDK and no shared API key.
Tool catalog
64 Gladly tools ready without custom code.
Browse Gladly agents, customers, tasks and comments with methods already wired.
Toolboxes
Every team gets its own Gladly toolbox.
Toolboxes scope Gladly tools to Support, Success, Quality and Operations separately.
Shared connections
Teammates use Gladly without seeing a credential.
Each Gladly connection shows who connected it and which teams and members share it.
Audit log
Answer who touched which Gladly customer.
Append-only log records when, who, what happened, type and Gladly resource.
From answering questions to doing the work
A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations, collections and live dashboards come with the Black plan.
Gladly digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch customers
Gladly
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Jake Morgan
Approve Deny -
Post the digest
Gladly
Queued
Automations
A schedule drafts your Gladly task digest.
Six steps fetch and group Gladly tasks, draft a digest, await approval, post back.
Gladly health
Refreshed 4 minutes ago · every 15 minutes · from the customers collection
Customers
1,284 ↓ 12%
Tasks
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Customers created
Last 14 days
By team
Share of activity
Support EMEA 34%
Support US 27%
Customer success 21%
Quality assurance 18%
Collections and dashboards
Gladly numbers arrive before anyone asks.
Four metrics, 14 days of Gladly customers created, split by team, refreshed on schedule.
For IT and engineering
Elaichi vs Zapier MCP vs Composio for Gladly
All three can connect Gladly to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Gladly tools | Allow or restrict single Gladly tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Gladly call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
Gladly tools for your AI agents
64 tools are ready to call through Elaichi's MCP endpoint the moment you connect Gladly, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
Questions, answered
How do I connect Gladly to Claude?
Connecting Gladly to Claude takes two steps. First, connect Gladly in Elaichi by pasting a Gladly API key, which you copy from the API tokens area of your Gladly settings; there is no client ID or secret to generate and no OAuth application to register. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude will ask you to sign in to Elaichi as yourself, and Gladly is ready to use.
Does Gladly work with ChatGPT and Cursor as well as Claude?
Yes. Once Gladly is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client, and the Elaichi Agent. You connect Gladly once and every client you use picks it up.
What can an AI agent actually do with my Gladly data?
With Gladly connected, an AI agent can look up a customer and read their full conversation history, pull the messages and internal notes from a single conversation, and summarize what happened. It can create and update Gladly customers, create and update tasks, add comments to tasks, and list your agents, teams, and inboxes. Because Gladly exposes a lot of actions, short concrete asks such as "find the customer with this email" work better than one long paragraph.
Does connecting Gladly give the AI access to every customer and conversation?
No. The AI acts inside the access of the person who signed in, so it sees the Gladly customers, conversations, and inboxes that person can already see. Elaichi can narrow that further, for example read-only on customers, but it can never widen what Gladly itself allows for that person.
Can I stop an agent from deleting or changing things in Gladly?
Yes. Restrictions in Elaichi work per action, so you can restrict deleting Gladly customers or updating tasks while leaving reading and summarizing available. A restricted action still appears in Elaichi's tool search, flagged as restricted, but Claude, ChatGPT, Cursor, Microsoft Copilot, or any other client cannot run it, whatever the prompt says.
What happens to a Gladly connection when someone leaves?
When you offboard someone in Elaichi, their access to Gladly through every AI client ends at once. If they were using a shared Gladly connection, it keeps working for everyone else on the team. If you disconnect Gladly in Elaichi altogether, it disappears from Claude, ChatGPT, Cursor, Microsoft Copilot, and every other client in one step.
Does the Gladly MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Gladly is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Gladly?
Yes. Both let Claude, ChatGPT or Cursor use Gladly. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Gladly call.
How is Elaichi different from Composio for Gladly?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Gladly: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Gladly in front of your team
14 days of Black, no credit card. Connect it once and pick what each team can call.
When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.
Add one link to your AI app
The same link for everyone on your team.
https://api.elaichi.ai/mcp
ChatGPT
Claude
Cursor
Microsoft Copilot