GitHub logoChatGPT logo
GitHub · ChatGPT

Connect GitHub to ChatGPT. For your whole team.

GitHub's official MCP server signs in one person with OAuth and ships write tools for issues, pull requests, files and merges unless you remember the read-only switch. Loopthink holds one fine-grained read token for the repositories you choose, gives every ChatGPT user in your team their own login, and lets Engineering, Product and Management see exactly what their role allows.

Free for your own server · Team from €99 · EU-hosted

The problem

GitHub in a chat client, today.

Today a team that wants GitHub in an AI client either has every person sign in with their own GitHub account, which is fine for engineers and a paid seat for everyone else, or shares one token. A shared classic token reaches every repository its owner can see and can push, merge and delete. GitHub's audit log then shows the token's owner, not the person who typed the prompt.

Who may do what

One matrix for GitHub. Roles across, tools down.

ToolEngineeringProductManagement
Repositories & code Engineering may use Repositories & codeProduct may not use Repositories & codeManagement may not use Repositories & code
Issues Engineering may use IssuesProduct may use IssuesManagement may use Issues
Pull requests Engineering may use Pull requestsProduct may use Pull requestsManagement may use Pull requests
Actions runs Engineering may use Actions runsProduct may not use Actions runsManagement may use Actions runs
Security alerts Engineering may use Security alertsProduct may not use Security alertsManagement may not use Security alerts
Write actions off by defaultEngineering may not use Write actionsProduct may not use Write actionsManagement may not use Write actions

Masked for every role: commit author emails, secrets and tokens quoted in issues, external contributors' names.

You set this once. Every ChatGPT user in your team gets exactly this.

How to connect

Once on the GitHub side, once in ChatGPT.

GitHub logo

On the GitHub side

Fine-grained personal access token, read permissions, selected repositories

  1. 1

    GitHub → Settings → Developer settings → Personal access tokens → Fine-grained tokens → Generate new token. Resource owner: your organisation. Repository access: only the repositories your team should reach.

  2. 2

    Permissions: Contents Read, Issues Read, Pull requests Read, Actions Read. Metadata is included. Nothing on Write. An organisation owner approves the token once.

  3. 3

    Paste the token into Loopthink. Your team never sees it; each person signs in with their own identity.

ChatGPT logo

In ChatGPT

Custom connector, OAuth

  1. 1

    An admin turns on Developer mode: Settings → Apps → Advanced settings. On Enterprise and Edu, admins first grant it under Permissions & Roles → Connected Data.

  2. 2

    Workspace settings → Apps → Create: paste your Loopthink connector URL, choose OAuth, click Scan Tools, then Create. Publish the draft under Workspace settings → Apps → Drafts.

  3. 3

    Each team member picks Loopthink from the tools menu in a chat, or @mentions it, and signs in once with their own account.

Full MCP apps are available on ChatGPT Business, Enterprise and Edu; Pro can connect read-only MCP servers in developer mode. Published apps show up in every member's Apps settings with the label custom.

Steps checked against the vendor documentation on 17 September 2026: GitHub MCP server · Set up the GitHub MCP server · Fine-grained personal access tokens · Token permissions · Developer mode and MCP apps in ChatGPT · Connectors in ChatGPT

Loopthink sits in between: it holds the key, shows ChatGPT a normal login, and applies your roles on every call.

What you get

Four checks between ChatGPT and GitHub.

  1. 01

    Identify

    OIDC/SSO against your own IdP, including Microsoft Entra. The call runs as the person who made it, never as a shared service account.

  2. 02

    Authorize

    Per-role, per-tool, read or write. Anything not explicitly granted never shows up in the tool list in the first place.

  3. 03

    Mask

    Field-level masking and pseudonymization applied on your side, before the result travels. The model never sees the raw field. Composio, AnythingMCP and both provider tunnels have no field-level masking at all.

  4. 04

    Log

    Who asked, which tool, which records, which fields were masked. One audit trail across every AI client, exportable for review.

Use cases

What people actually ask ChatGPT about GitHub.

  • Engineering

    “Which pull requests have waited for a review for more than three days?”

  • Product

    “Which issues labelled customer-bug were closed this sprint, and which are still open?”

  • Management

    “How many releases shipped this quarter, and did any deploy workflow fail?”

Each question runs as the person who asked it, with that person's role. A Product colleague asking the Engineering question gets the tools their own role allows, not an error, not more.

Compare

Four ways to put GitHub into ChatGPT.

Native GitHub connectorBuild it yourselfEnterprise gateways1Loopthink
Per-user identityOne personal login, all its rightsOnly if you build itYesYes, every call runs as the person who asked
Tool-level rolesNoYour codeYesYes, write off by default
Field maskingNoYour codeNot documentedYes, before the model sees the data
Published priceIncluded in your GitHub planYour engineers' timeContact salesFree, Team from €99
EU companyNoWhatever you areMostly USYes, Germany

Native GitHub connector: Official GitHub MCP server with OAuth. The signed-in person's rights across their repositories; write tools on unless the URL ends in /readonly.

1 MintMCP, MCP Manager, Pomerium

Coming from one of them? Composio alternative · MintMCP alternative · MCP Manager alternative · AnythingMCP alternative

FAQ

Before you connect.

Does every team member need their own GitHub account?
No. Loopthink holds one key or token for GitHub. Your people sign in to Loopthink with their own identity, and every call to GitHub is logged under their name. Seats in GitHub stay where they are today.
Who has to add the connector in ChatGPT?
One person with the right to add connectors in your ChatGPT workspace, once. After that every team member enables it for themselves. Nobody pastes a key, nobody edits a config file.
Where does the GitHub key live?
In Loopthink, encrypted, in the EU. It never reaches ChatGPT and never reaches the people using the connector. Rotate it in GitHub whenever you like and paste the new one once.
Can somebody write to GitHub from the chat?
Not unless you switch it on. Write actions are a separate row in the permission matrix and are off for every role by default. If a role needs one write tool, you grant that one tool to that one role.
What does the model see?
The result of the tool call, after masking. Fields you mark as personal, such as emails, names or card details, are masked before the answer travels to ChatGPT. The model gets the numbers, not the people.
Is there an audit trail?
Yes. Who asked, which tool, which parameters, which fields were masked, when. One log across every client your team uses, exportable for review.
What does it cost?
Free for one person and your own MCP server, forever. Team starts at €99 per month and covers the built connector, per-person identity, roles, masking and audit for the whole team. Prices are on the pricing page, no call needed.
We already run our own MCP server for GitHub. Does it still work?
Yes. Point it at Loopthink and it inherits the same login, roles, masking and audit. Nothing on the server has to change.

GitHub in ChatGPT, with rules.

One key in Loopthink, one login per person, one matrix that decides who may do what.

Free for your own server · Team from €99 · EU-hosted