GitHub PAT connector for AI agents

Tools your engineering agent reaches for on GitHub, scoped per user.

CALL ANY TOOL

Source control end to end: read files, open and merge PRs, triage issues, search code, and drive CI, each call on the user's own API key.

githubpat_search_code

Search code

Search for code across GitHub using search qualifiers (e.g. 'addClass in:file language:js repo:jquery/jquery'). Returns up to 100 results per page. Requires authentication and is limited to 10 requests per minute.

Parameters

Name

Type

Required

Description

string

Required

Search query with optional qualifiers (e.g. 'addClass in:file language:js repo:jquery/jquery')

order

string

Optional

Sort order

page

number

Optional

Page number of results to fetch

per_page

number

Optional

Number of results per page (max 100)

sort

string

Optional

Sort results by indexed (how recently the file was indexed)

githubpat_org_get

Org get

githubpat_search_repos

Search repos

githubpat_gist_get

Gist get

githubpat_search_users

Search users

githubpat_repo_get

Repo get

githubpat_search_issues

Search issues

githubpat_team_get

Team get

githubpat_search_topics

Search topics

githubpat_gist_star

Gist star

githubpat_search_commits

Search commits

githubpat_issue_get

Issue get

githubpat_repo_star

Repo star

githubpat_label_get

Label get

githubpat_tags_list

Tags list

githubpat_branch_get

Branch get

githubpat_gists_list

Gists list

githubpat_commit_get

Commit get

githubpat_issue_lock

Issue lock

githubpat_org_update

Org update

githubpat_readme_get

Readme get

githubpat_teams_list

Teams list

githubpat_file_delete

File delete

githubpat_gist_create

Gist create

githubpat_gist_delete

Gist delete

githubpat_gist_unstar

Gist unstar

githubpat_gist_update

Gist update

githubpat_issues_list

Issues list

githubpat_license_get

License get

githubpat_labels_list

Labels list

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

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);

// GitHub tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["githubpat"], toolNames: [
    "githubpat_pull_request_create",
    "githubpat_issues_list",
    "githubpat_search_code"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Open a PR from fix/login-timeout into main." }] });

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: ["githubpat"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "List open issues labeled bug in api-server." }],
  tools,
});

// Execute the tool call with the user's vaulted GitHub PAT
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: ["githubpat"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Search the org for uses of the deprecated auth client." }],
  tools,
});

// Tool call runs with the user's vaulted GitHub PAT
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: ["githubpat"] }, pageSize: 100,
});

const agent = new Agent({
  name: "github_repo_agent",
  model: "gemini-2.5-pro",
  instruction: "Manage GitHub repos, issues, and PRs for the signed-in user.",
  tools,
});

await agent.run("Merge PR #482 with squash if checks are green.");

Try these prompts

Copy any prompt into your agent. Each maps directly to a GitHub tool. Click to copy, paste into your agent, done.

Ship code

Copy the prompt

Copied

Open a PR from fix/login-timeout into main with a summary of the diff.

Copy the prompt

Copied

Merge PR #482 with squash if checks are green.

Copy the prompt

Copied

Create a branch off main for the payments refactor.

Triage issues and reviews

Copy the prompt

Copied

List open issues labeled bug in api-server.

Copy the prompt

Copied

File an issue for the flaky checkout test and label it ci.

Copy the prompt

Copied

Which PRs are still waiting on review this week?

Search and CI

Copy the prompt

Copied

Search the org for uses of the deprecated auth client.

Copy the prompt

Copied

Trigger the deploy workflow on main.

Copy the prompt

Copied

Why did the last release workflow run fail?

SEE HOW AUTH WORKS

Your users connect once. Their GitHub tokens stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

GitHub (Personal Access Token)

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

Store

Their

GitHub (Personal Access Token)

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

Resolve

When your agent calls a

GitHub (Personal Access Token)

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

Audit

Every

GitHub (Personal Access Token)

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 developer connectors.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared machine-account PAT looks fine in a demo. In production every merge, force-push, and issue edit is attributed to one bot, and you cannot tell who shipped what. 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.

GitHub today. Others 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 GitHub as the user or through a shared key?

As the user. Scalekit resolves the PAT of the person who triggered the agent at request time, so every commit, merge, and issue edit in your audit trail is attributed to a real user, not a shared machine account.

Where is the GitHub token stored?

In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, and can be rotated or revoked from one dashboard.

Can I limit what the agent does in GitHub?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example read and search without merge, delete, or team management. 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.

A PAT can carry broad repo scope. Does the agent get all of it?

No. The token's GitHub scope is the ceiling, not the grant. You choose which of the 113 tools the agent sees, so destructive operations like repo_delete or git_ref_delete stay hidden unless you list them, and Scalekit checks scope before every call.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit