GitHub MCP | OAuth GitHub connector for AI agents

CALL ANY TOOL

Read repos, manage issues and PRs, search code, and trigger workflows. Same toolkit, every framework, no auth plumbing.

github_issues_list

List issues

List issues in a repository with optional filters for state, assignee, labels, and milestone.

Parameters

Name

Type

Required

Description

owner

string

Required

Repository owner (user or org)

repo

string

Required

Repository name

state

string

Optional

Issue state: open, closed, all

assignee

string

Optional

Filter by assignee username

labels

string

Optional

Comma-separated label names

github_issue_create

Create issue

github_pull_requests_list

List pull requests

github_code_search

Search code

github_repo_get

Get repository

github_workflow_run

Trigger workflow

Build your Agent

Drop the toolkit in, point it at the user, and your agent can manage GitHub issues, PRs, and code searches from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["github"], toolNames: ["github_issues_list", "github_pull_requests_list", "github_code_search"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["github"], toolNames: ["github_issues_list", "github_pull_requests_list", "github_code_search"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["github"], toolNames: ["github_issues_list", "github_pull_requests_list", "github_code_search"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/github",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start managing GitHub workflows.

Search & recall

Copy the prompt

Copied

List all open issues labeled [bug] in [repo].

Copy the prompt

Copied

Find all PRs assigned to me across my repos.

Copy the prompt

Copied

Search for [keyword] in the codebase of [repo].

Copy the prompt

Copied

Show me all closed issues from last sprint.

Action & creation

Copy the prompt

Copied

Create an issue in [repo]: [title] — [description].

Copy the prompt

Copied

Assign issue #[id] to [username].

Copy the prompt

Copied

Add label [bug] to issue #[id] in [repo].

Copy the prompt

Copied

Trigger the [workflow name] workflow on [branch].

Code & reviews

Copy the prompt

Copied

List all PRs waiting for review in [repo].

Copy the prompt

Copied

What issues are assigned to [username] in [repo]?

Copy the prompt

Copied

Show me all open issues with no assignee.

Copy the prompt

Copied

Find all PRs merged in the last 7 days.

SEE HOW AUTH WORKS

Users authorize GitHub once. Their account credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

GitHub

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

2

Store

Their

GitHub

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

3

Resolve

When your agent calls a

GitHub

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

4

Audit

Every

GitHub

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

Same per-user auth pattern across other devops agents and MCP connectors. Working code, live demos, fork what fits.

ENGINEERING

Auto-release notes agent

Group merged GitHub PRs by feature, fix, or chore and publish release notes per tag. No manual changelog grooming.

GitHub

View agent

ENGINEERING

DevOps assistant agent

Triage GitHub incidents, open Linear tickets, and notify the on-call channel in Slack with context already attached.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

PR reviews attributed to a bot account

A shared GitHub token looks fine in a demo. In production, every PR comment, review assignment, and commit check runs as a bot account. CODEOWNERS routing breaks. Contribution analytics break. Scalekit resolves the engineer's own credential, so GitHub tracks code ownership correctly.

// shared bot token
token = "sk_github_shared_xxx"
audit → bot_service_account
engineer_filter → broken

// scalekit · per-user
token = resolve(user_id)
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

GitHub today. GitLab, Jira, Linear 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 as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the GitHub oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in GitHub?

Yes. Pass a tool name filter to listScopedTools so the DevOps agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches GitHub.

What happens when a user revokes GitHub access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Org repos or personal repos? Which does the agent reach?

Both, scoped to the authorizing user. Org repos the user has access to, personal repos, and forks. Private repos stay private unless the user has read or write rights at the GitHub level.

GitHub

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