GitHub + Claude Code

Build a GitHub agent with Claude Code

Have Claude Code build a GitHub agent with the Agent200 SDK: managed OAuth, ready-made tools and one API key.

On this page
  1. Overview
  2. Before you start
  3. Setup steps
  4. Test your connection
  5. Instructions for AI agents
  6. GitHub tools
  7. How it works
  8. Troubleshooting

Overview

This guide has Claude Code build a GitHub agent with the Agent200 SDK, in your own project. When you finish, your agent can call the GitHub tools for each of your users.

Claude Code writes the code from the steps below; Agent200 runs the GitHub calls with each user's own connection and handles the OAuth flow and the tokens. You do not build or maintain a GitHub integration.

Connector
GitHub
Works with
Claude Code ยท Coding agent, with the SDK
Authentication
Managed OAuth, per end user
Tools
4 tools
Model in examples
openai/gpt-5.6-sol

Before you start

  • An Agent200 API key. Create one on the API keys page of the dashboard.
  • GitHub enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
  • An end user with a GitHub account. They approve access once, on GitHub's own page.
  • Claude Code in your project. It writes the code with the Agent200 SDK; you review it.

Connect GitHub to Claude Code

  1. 1

    Step 1: Create your Agent200 API key

    Open the API keys page in the Agent200 dashboard and choose Create an API key. Copy the key and store it as an environment variable, AGENT200_API_KEY, or in your secrets manager. One key covers GitHub and every other connector and model enabled for your project. Keep it out of chats, prompts and source control.

    .env
    Conceptual example
    Store the Agent200 API key as an environment variable
    # Keep the key out of your code, prompts and chats.
    export AGENT200_API_KEY="paste-your-key-here"
  2. 2

    Step 2: Give this guide to Claude Code

    Start Claude Code in your project and paste the agent brief from this page, or give it the address of this guide's Markdown version. Claude Code follows the steps below in order: the SDK, the GitHub connection and the first request. Review the code it writes before you run it.

  3. 3

    Step 3: Set up the Agent200 SDK

    Add the SDK to your project and create a client with the key from the environment.

    agent.js
    Conceptual example
    Set up the SDK with the Agent200 API key
    // One Agent200 API key covers every connector enabled for the project.
    const agent200 = new Agent200({
      apiKey: process.env.AGENT200_API_KEY,
    });
  4. 4

    Step 4: Let your user connect GitHub

    Each end user authorizes their own GitHub account once, through managed OAuth. If the user has not connected yet, Agent200 returns an authorization link: show it to them, and they approve access on GitHub's own page. Agent200 handles the callback, stores the tokens and refreshes them.

    connect.js
    Conceptual example
    Let an end user connect their account (managed OAuth)
    // Each end user authorizes their own GitHub account, once.
    const connection = await agent200
      .user("user_123")
      .connect("github");
    
    if (connection.authorizationUrl) {
      // Show this link to your user; Agent200 handles the rest.
      console.log(connection.authorizationUrl);
    }
  5. 5

    Step 5: Run with the GitHub tools

    Name the user, the model and GitHub in the tools. The model decides when a GitHub tool is needed, and Agent200 executes the call with the user's own connection.

    run.js
    Conceptual example
    Run a request with the connector's tools
    const result = await agent200
      .user("user_123")
      .run({
        model: "openai/gpt-5.6-sol",
        input: "List the open bugs assigned to me",
        tools: ["github"],
      });
    
    console.log(result.output);

Test your connection

Run one request to check everything is wired up.

Ask

List the open bugs assigned to me

What should come back

  • An answer in result.output, built from the user's own GitHub data.
  • Behind the scenes, the model calls a GitHub tool, such as github_search_issues, and Agent200 runs it.

If Agent200 returns an authorization link instead, the user has not connected GitHub yet. Go back to the connect step.

Get your API key

Create a key in the Agent200 dashboard. It reaches GitHub and every other connector enabled for your project.

Read the SDK docs

Instructions for AI agents

Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect GitHub to Claude Code.

Agent brief
Goal: connect GitHub to Claude Code with Agent200.
Guide: https://www.agent200.com/tools/github/framework/claude-code/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Make sure GitHub is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Give every request a stable id for the end user. Agent200 uses only that user's own connections.
5. Connect the user's GitHub account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on GitHub.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "github" in the tools. The model decides when a GitHub tool is needed; Agent200 executes the call.
7. Check it works with this request: "List the open bugs assigned to me"
   What should come back:
   - An answer in `result.output`, built from the user's own GitHub data.
   - Behind the scenes, the model calls a GitHub tool, such as `github_search_issues`, and Agent200 runs it.
8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in GitHub, then retry.

The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

The whole guide is also available as Markdown, for agents and LLMs: /tools/github/framework/claude-code.md

GitHub tools Claude Code can call

  • Search issues

    Read
    github_search_issues

    Find issues and pull requests.

  • Create an issue

    Write
    github_create_issue

    Open an issue in a repository.

  • Read a file

    Read
    github_get_content

    Read a file from a repository.

  • Comment

    Write
    github_create_comment

    Comment on an issue or pull request.

How it works

  1. 01

    Your app sends the request

    It calls Agent200 with the model, instructions, the input, the end user's id and the GitHub tools.

  2. 02

    The model picks a tool

    The model decides whether a GitHub tool is needed, and with which arguments.

  3. 03

    Agent200 runs the call

    It uses that user's own GitHub connection, within the endpoints and scopes your project allows, and returns the result to the model.

  4. 04

    Your app gets the result

    Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's GitHub account.

Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and GitHub enforces what its API grants.

Troubleshooting

The request says GitHub authorization is required

The end user has not connected GitHub yet, or the connection needs to be approved again. Agent200 returns an authorization link: show it to the user, let them approve access on GitHub's own page, then run the request again.

Claude Code does not use the GitHub tools

Check that GitHub is enabled for your project in the dashboard's Connectors settings and that it is in the tools you send with the request. Naming GitHub in the request, or in the instructions, also helps the model choose the right tool.

A tool call is refused or returns less than expected

Agent200 runs only what your project allows (services, endpoints and scopes), and GitHub returns only what the end user authorized. Widen the endpoints or scopes in the dashboard if the agent needs more, then ask the user to connect GitHub again so they can approve the new access.

The results come from the wrong account

Every request names an end user (user_123 in the examples). Pass the id of the person your agent is working for: Agent200 then uses only that user's GitHub connection, never another user's.

The API key was pasted into a chat or committed

Create a new key on the API keys page, update AGENT200_API_KEY wherever your app reads it, and stop using the old one. Keep keys in environment variables or a secrets manager, never in prompts, chats or source control.

Use GitHub with another framework

200 OK

GitHub, connected to Claude Code.
One SDK. One API key.

Agent200 handles the OAuth, the tokens and every tool call. You keep your agent, your model and your code.

Book a demo.
See it in action.

Tell us who you are, then pick a time for a 1:1 session with an expert from our team.

We use your details only to email you about Agent200. See the Privacy Policy.

Pick a time. We'll take it from there.

A 1:1 session with an expert from our team, about what you are building.

Open in Calendly (opens in a new tab)