The GitHub MCP that reacts to your repos, not just reads them
Connect a personal access token once and issues, pull requests, and repo data become workflow steps, while push, PR, and issue webhooks become triggers that start automations the moment something happens.
What the GitHub MCP connector does
The GitHub connector for Mattering Automations covers the day-to-day working surface: create, update, comment on, and close issues, create labels, and query repo info, issues, and pull requests. Three webhook triggers (push, pull request opened, issue opened) start workflows from GitHub events, which is the piece most GitHub integrations leave out.
Every node speaks MCP, the open protocol for connecting AI assistants to tools, so Claude, ChatGPT, and any MCP-capable assistant can use them, alongside Matter, the AI assistant built into the platform. An assistant can triage a new issue, file follow-ups, and open a tracked task in the same breath.
Because Mattering is a work platform rather than middleware, GitHub events land somewhere useful by default: a new issue can become an assigned task with a due date, a push can update a release checklist, and the whole flow lives on one canvas.
One connection, three surfaces
- Visual automations. Drag GitHub nodes onto the canvas and wire them to triggers, conditions, and other apps.
- AI agents, yours or ours. These nodes speak MCP, the open protocol, so Claude, ChatGPT, and any MCP-capable assistant can use them, and Matter, the agent built into the platform, uses them natively.
- The whole platform. Combine with native tasks, projects, and other connectors, no middleware in between.
Every GitHub node, ready to drop on the canvas
11 nodes, generated from the connector itself so this list always matches what ships. Expand a category to browse.
Trigger nodes (start workflows from events) 3
GitHub Issue Opened
Fires when an issue is opened
GitHub PR Opened
Fires when a pull request is opened
GitHub Push
Fires when code is pushed to a repository
Read and query nodes 3
GitHub Issues
List issues in a GitHub repository
GitHub PRs
List pull requests in a GitHub repository
GitHub Repo Info
Get repository metadata
Action nodes 5
Close GitHub Issue
Close a GitHub issue
Create GitHub Issue
Create a new issue in a GitHub repository
Create GitHub Label
Create a label in a GitHub repository
GitHub Comment
Add a comment to a GitHub issue or PR
Update GitHub Issue
Update an existing GitHub issue
Connecting GitHub takes one credential
Create a token at github.com/settings/tokens, either fine-grained (recommended, scoped to specific repos) or classic. Grant repo and issue permissions matching what your automations should touch.
In GitHub, create a personal access token with the repo and issue permissions you want automations to have.
In Mattering Automations, open Connectors, choose GitHub, and create a credential with the token.
The connector verifies the token against GitHub's user endpoint and reports who it authenticated as.
All 11 GitHub nodes appear in the canvas palette; trigger nodes provide a webhook URL to add under your repo's Settings, then Webhooks.
Common uses for the GitHub MCP
Issues that become tracked work
When an issue opens on GitHub, a task appears in Mattering Productivity with the issue linked, assigned, and scheduled, so engineering work and everything around it live in one system.
AI triage on new issues
An agent reads each new issue, labels it, posts a clarifying comment when the report is thin, and routes a task to the right owner.
Release rituals on push
A push to main updates the release checklist, notifies the channel, and opens follow-up tasks for anything the commit messages flag.
PR review flow
A pull request opening spawns a review task with a deadline, and stale PRs surface in a weekly digest queried straight from the repo.
Cross-repo reporting
Query issues and pull requests across repos on a schedule and write the counts into a Mattering database for a real engineering dashboard.
Ops without leaving chat
An MCP-connected assistant files bug reports, adds comments, and closes resolved issues on request, using the same nodes as the canvas.
Example: New GitHub issues become assigned tasks in seconds
Built on the Automations canvas in a few minutes, or described in plain language to Matter and built for you.
Trigger: GitHub Issue Opened fires via webhook the moment an issue is created.
GitHub: Repo Info and the issue payload give the workflow context on the repo and reporter.
An AI step classifies the issue (bug, feature, question) and picks a label.
GitHub: Create Label applies it, and Mattering Productivity creates an assigned task with the issue link and priority set.
GitHub MCP questions, answered
Can an AI agent manage GitHub issues through this MCP?
Yes. Matter and any MCP-connected assistant, including Claude and ChatGPT, can create, update, comment on, label, and close issues, and query issues, pull requests, and repo info, using the same nodes available on the automation canvas.
Does this work with Claude, ChatGPT, or other AI assistants?
Yes. Mattering exposes these nodes over MCP, an open protocol for connecting AI assistants to tools, so any MCP-capable assistant can connect to your workspace and use them. Matter, the assistant built into the platform, uses the same nodes natively.
How is this different from GitHub's own MCP server?
GitHub's MCP server gives an assistant GitHub tools in a chat session. Mattering's connector puts GitHub inside a persistent automation platform: webhook triggers start workflows without anyone prompting, and results land in native tasks, databases, and messages. The two compose fine, and they solve different problems.
What can the webhook triggers do?
Push, pull request opened, and issue opened events can each start a workflow. You add the webhook URL the trigger node provides to your repo settings, and from then on the automation runs the moment the event happens, no polling.
What credential does the connector use?
A GitHub personal access token, fine-grained or classic, sent with GitHub's recommended API version headers and stored encrypted in Google Secret Manager. Fine-grained tokens let you scope access to specific repositories.
What are GitHub's API rate limits?
GitHub allows 5,000 requests per hour for authenticated requests with a personal access token, per GitHub's documentation. Typical automation workloads sit far inside that; the connector surfaces rate limit errors on the node output.
What is not supported?
The connector focuses on issues, pull requests, labels, comments, and repo queries plus the three webhook triggers. Merging PRs, managing branches, releases, Actions, and organization administration are not exposed as nodes.
Put GitHub to work inside your workspace
Connect once, then use every node in visual automations and AI agent workflows across the Mattering platform.
All product names, logos, and brands are property of their respective owners and are used for identification purposes only. Use of these names, logos, and brands does not imply endorsement or affiliation. GitHub is a product of its respective owner; Mattering is an independent platform.