GitHub
Enable agents to interact with GitHub repositories. Manage issues, pull requests, reviews, projects, and repository content.
Available Tools
46 tools available in this integration
Github.SetStarred Star or unstar a GitHub repository
Github.ListStargazers List the stargazers of a GitHub repository
Github.CreateIssue Create an issue in a GitHub repository
Github.CreateIssueComment Create a comment on an issue
Github.UpdateIssue Update an existing issue in a repository
Github.GetIssue Get details of a specific issue
Github.ListIssues List issues in a repository with filtering
Github.ListPullRequests List pull requests in a GitHub repository
Github.GetPullRequest Get details of a pull request
Github.UpdatePullRequest Update a pull request
Github.ListPullRequestCommits List commits on a pull request
Github.CreateReplyForReviewComment Create a reply to a review comment
Github.ResolveReviewThread Resolve or unresolve a review thread
Github.ListReviewCommentsOnPullRequest List review comments on a pull request
Github.CreateReviewComment Create a review comment on a pull request
Github.CountStargazers Count the number of stargazers for a repository
Github.ListOrgRepositories List repositories of a GitHub organization
Github.GetRepository Get details of a GitHub repository
Github.ListRepositoryActivities List repository activities such as pushes and merges
Github.ListReviewCommentsInARepository List review comments in a GitHub repository
Github.CreatePullRequest Create a new pull request
Github.MergePullRequest Merge a pull request
Github.SubmitPullRequestReview Submit a review (approve/request changes/comment)
Github.ManagePullRequest Update pull request properties
Github.ManagePullRequestReviewers Add or remove reviewers from a pull request
Github.AssignPullRequestUser Assign a user to a pull request with fuzzy matching
Github.CheckPullRequestMergeStatus Check if a PR is ready to merge
Github.ListProjects List Projects V2 in an organization or user
Github.ListProjectItems List items in a Projects V2 project
Github.SearchProjectItem Search for a specific item in a project
Github.UpdateProjectItem Update field values for a project item
Github.ListProjectFields List all custom fields in a project
Github.ListRepositoryCollaborators List collaborators and teams for a repository
Github.SearchMyRepos Search repositories with fuzzy matching
Github.CreateBranch Create a new branch in a repository
Github.GetFileContents Get the contents of a file in a repository
Github.CreateOrUpdateFile Create or update a file in a repository
Github.UpdateFileLines Replace a block of lines within a file
Github.ListRepositoryLabels List all labels defined in a repository
Github.ManageLabels Add or remove labels from issues or pull requests
Github.WhoAmI Get information about the authenticated user
Github.GetUserRecentActivity Get user's recently created PRs and issues
Github.GetUserOpenItems Get user's currently open PRs and issues
Github.GetReviewWorkload Get PRs awaiting review by the user
Github.GetNotificationSummary Get a summary of user notifications
Github.ListNotifications List notifications with pagination
Why agent-optimized tools matter
Built for intent, not API schemas
Forcing the agent to juggle not only what you want to get done, but also how to operate all the APIs it needs to use is a recipe for disaster. Agent-optimized tools keep the agent focused on the work at hand, not ID hunting.
Up to 100x fewer tokens
Context bloat is a serious problem that gets in the way of real work getting done with agents. Agent-optimized tools return only the fields the agent needs to get the job done, not the full API response. Up to 100x less token consumption on every call.
Coverage for the whole task
Most tasks take more than one action to finish. Agent-optimized tools cover the full sequence so the agent completes the workflow end to end, not just the first lookup.
Consistent at scale
Agent-optimized tools behave the same across every user, every run, every harness, every model, and every effort level. No need for the agent to spend time and tokens re-learning the API shape, it can focus on the task at hand. What works for one user holds up when serving thousands in production.
Your questions, answered
It's built around what an agent is trying to accomplish rather than mirroring GitHub's raw API. Fewer required parameters, far fewer tokens per call, and coverage for the whole task — so agents succeed more often.
Yes. The toolkit is exposed over an MCP gateway that any framework or MCP client can connect to, and we publish install guides for the editors and coding agents we document.
No. Arcade proxies API calls and does not persist your GitHub content. Where GitHub requires credentials, Arcade brokers them and stores them encrypted at rest — the model never sees them.
With Contextual Access policies: require human approval before consequential actions, redact sensitive fields on the way back, or restrict the scopes a given agent gets.
