GitHub Copilot MCP connector
The GitHub Copilot connector lets Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent manage seats, pull usage reports, and set content exclusions and coding agent policies, with every call running as the signed-in person and logged.
- Connects with an API key
- Free 14-day trial
- No credit card
Which GitHub Copilot seats have had no activity in 30 days?
Working in GitHub Copilot with Elaichi
-
Get single GitHub Copilot seat by ID
-
List all GitHub Copilot seats
-
List all GitHub Copilot content exclusions
How to connect GitHub Copilot to Claude, ChatGPT, Cursor or Microsoft Copilot
Step by step, for each AI app
GitHub Copilot 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.
GitHub Copilot 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.
GitHub Copilot 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.
GitHub Copilot 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.
GitHub Copilot 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 GitHub Copilot 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 GitHub Copilot through Elaichi
Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in GitHub Copilot is logged.
-
Engineering leadership
See who is actually using GitHub Copilot
Pull the latest enterprise usage report and the per-user report, then ask which seats have gone quiet. Idle seats and the teams that lean on GitHub Copilot the most show up without opening a spreadsheet.
-
IT
Put a new hire on a GitHub Copilot seat
Add a person or a whole team to GitHub Copilot seats on their first day, and confirm the seat is live by looking it up by ID. Remove seats in bulk when a contractor engagement ends.
-
Finance
Reconcile the GitHub Copilot bill each month
List current billing, compare assigned seats to headcount, and flag the seats to drop before the next cycle. The numbers come from GitHub Copilot itself, not from a forwarded screenshot.
-
Security
Keep sensitive repositories out of suggestions
Review the current content exclusions and update them in bulk when a repository is marked confidential. The change is made once and recorded with the name of the person who asked for it.
-
Platform
Decide which repositories the coding agent can touch
List the repositories and permissions the GitHub Copilot coding agent has today, update them, or remove a repository it should no longer work in. Permission changes are applied in one pass instead of one setting at a time.
-
Engineering managers
Roll out coding agent policies across the enterprise
Create an enterprise coding agent policy, update a set of them together, and delete the ones that no longer apply. Then pull the daily team report to see whether adoption moved after the change.
Try asking
- “Which GitHub Copilot seats have had no activity in 30 days?”
- “Add the new platform team hires to GitHub Copilot seats.”
- “Summarize last week's GitHub Copilot usage report by team.”
What connecting GitHub Copilot gets you
6 screens from Elaichi, each doing one job for your GitHub Copilot account.
Ask Elaichi to work across your apps.
Which GitHub Copilot seats have had no activity in 30 days?
Add the new platform team hires to GitHub Copilot seats.
Summarize last week's GitHub Copilot usage report by team.
Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot
The agent
Ask who uses GitHub Copilot, in plain words.
Three starter prompts pull live seats, usage reports and billing straight from GitHub Copilot.
Copy the endpoint
AI apps
One endpoint puts GitHub Copilot in every client.
Claude, ChatGPT and Cursor share one governed endpoint, no SDK and no shared API key.
Tool catalog
32 GitHub Copilot tools, no code to write.
Seats, content exclusions, coding agent policies, billing and usage reports, ready the moment you connect.
Toolboxes
Every team gets its own GitHub Copilot toolbox.
IT handles seats, Finance sees billing, Security owns exclusions, each from a toolbox scoped to them.
Shared connections
Share GitHub Copilot access, never the API key.
One admin connects, teams and members work through it, and nobody else sees a credential.
Audit log
Every GitHub Copilot change carries a name.
When, who, what happened, type and resource, for every seat added or policy changed.
From answering questions to doing the work
A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.
GitHub Copilot digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch seats
GitHub Copilot
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
GitHub Copilot
Queued
Workflows
A schedule runs the GitHub Copilot seat review.
Idle seats are fetched, grouped by team, drafted into a digest, approved, then posted back.
GitHub Copilot health
Refreshed 4 minutes ago · every 15 minutes · from the seats collection
Seats
1,284 ↓ 12%
Content exclusions
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Seats created
Last 14 days
By team
Share of activity
Enterprise admin 34%
IT helpdesk 27%
Finance 21%
Security 18%
Collections and dashboards
GitHub Copilot adoption, measured without a prompt.
Four metrics, a 14 day seat chart and team breakdown, computed on schedule with no model.
For IT and engineering
Elaichi vs Zapier MCP vs Composio for GitHub Copilot
All three can connect GitHub Copilot 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 GitHub Copilot tools | Allow or restrict single GitHub Copilot 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 GitHub Copilot 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.
GitHub Copilot tools for your AI agents
32 tools are ready to call through Elaichi's MCP endpoint the moment you connect GitHub Copilot, 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 GitHub Copilot to Claude?
Connect GitHub Copilot in Elaichi by pasting the API key from your GitHub enterprise settings, which is the whole sign-in step. There is no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude signs you in to Elaichi as yourself and GitHub Copilot is ready to ask about.
Does GitHub Copilot work with ChatGPT and Cursor as well as Claude?
Yes. Once GitHub Copilot 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 GitHub Copilot once and every client picks it up.
What can an AI agent actually do with my GitHub Copilot data?
With GitHub Copilot connected, an agent can look up and assign seats for people and teams, pull the daily and latest usage reports for users, teams and repositories, read billing, and manage content exclusions, coding agent policies, permissions and repositories. Ask things like which seats have been idle for a month or add the new platform hires to seats. Short, concrete asks work better than long paragraphs.
Does connecting GitHub Copilot give the AI access to my whole enterprise?
No. A GitHub Copilot connection in Elaichi carries only what the key you added is allowed to do, and each person still signs in to Elaichi as themselves, so every call is tied to a named person. Elaichi can narrow that access with roles and restrictions, and it can never widen it beyond what GitHub Copilot already permits.
Can I stop an agent from deleting or changing things in GitHub Copilot?
Yes. Restrictions in Elaichi work per action on GitHub Copilot, so you can allow reading usage reports while restricting seat removal, repository deletion or policy changes, and set that on a role or on one person. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.
What happens to a GitHub Copilot connection when someone leaves?
Offboarding a person in Elaichi ends their access to GitHub Copilot through every client at once. A GitHub Copilot connection that was shared keeps working for everyone else on the team. If you disconnect GitHub Copilot in Elaichi, it is removed from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client in one step.
Does the GitHub Copilot MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. GitHub Copilot 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 GitHub Copilot?
Yes. Both let Claude, ChatGPT or Cursor use GitHub Copilot. 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 GitHub Copilot call.
How is Elaichi different from Composio for GitHub Copilot?
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 GitHub Copilot: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put GitHub Copilot 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