Connect GitHub MCP to your AI agents, securely.
One secured endpoint for every GitHub call your AI agents make, scoped per user, inspected, and logged.Try GitHub MCP now
What your agents can ask once GitHub MCP is connected.
“List open issues assigned to me across repositories”
“Open a pull request from this branch”
“Check this repository for exposed secrets”
“Summarise what changed in the last 10 commits”
“Find every repository using a deprecated dependency”
“Show which workflows failed on main this week”
Select the tools your AI agents can call
96 tools from the GitHub MCP schema.
Showing 96 tools
What GitHub MCP exposes
GitHub MCP groups its 96 tools into 15 categories, each with a suggested starting policy.
| Category | Covers | Access | Suggested policy |
|---|---|---|---|
| Repositories & Files | Files, branches, commits, releases, tags, collaborators, and stars | Read / Write | Scope repositories; approve destructive changes |
| Search | Search code, commits, repositories, issues, PRs, users, and organizations | Read | Limit access to intended resources |
| Issues & Labels | Issues, comments, sub-issues, custom fields, types, and labels | Read / Write | Audit changes |
| Pull Requests | PR details, diffs, reviews, branch updates, and merges | Read / Write | Require approval for merges |
| Actions | Workflows, runs, jobs, artifacts, and logs | Read / Write | Restrict workflow execution |
| Projects | Projects, items, fields, views, and status updates | Read / Write | Scope projects; audit changes |
| Discussions | Discussions, categories, comments, replies, and answers | Read / Write | Audit publishing and deletion |
| Security | Code scanning, Dependabot, exposed secrets, and security advisories | Read | Limit access to security findings |
| Code Quality | Individual code quality findings | Read | Scope repository access |
| Governance | Rulesets and custom properties | Read / Write | Require approval for policy changes |
| People & Teams | Authenticated profile, teams, and team members | Read | Limit organization access |
| Notifications | Notification details, read status, and subscriptions | Read / Write | Keep changes scoped to the user |
| Gists | Gist content, creation, and updates | Read / Write | Review content before publishing |
| Copilot | Issue assignments, automated reviews, coding tasks, and Spaces | Read / Write | Approve agent task execution |
| Documentation | GitHub product and support documentation search | Read | Allow documentation searches |
Connect GitHub MCP to your AI agent
Four steps, under ten minutes.
- 01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
- 02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
- 03
Connect GitHub
Find GitHub in the tool list and connect it.
- 04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.
Permissions down to the single tool
You do not allow GitHub MCP or block it. You allow the exact tools each agent can call, one by one.
| GitHub MCP | 96 TOOLS AVAILABLE |
|---|---|
| Code review agent | 4 tools, read only |
| Issue triage bot | 9 tools |
| Platform team assistant | all 96 tools |
- Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
- Default denyA tool you have not enabled is never exposed to the agent.
- Approval on writesTools that change or delete things can require a human to confirm.
Is GitHub MCP secure?
One endpoint instead of raw credentials. Every call is checked against policy and logged.
| AI agentsConnect through your MCP client configuration. | NeuralTrustApply controls based on your configuration. | GitHub MCP96 documented tools. |
|---|---|---|
| Coding assistants | Connection & credentialsper user | Repositories & Files21 tools |
| Internal copilots | Tool access policiesdeny by default | Issues & Labels12 tools |
| Workflow automations | Request & response inspectioninline | Security10 tools |
| Compatible MCP clients | Activity monitoringalerts and logs | All other tools53 tools |
Use GitHub MCP with any AI agent framework
Setup guides for the tools your team already uses.
- Claude CodeSetup guide
- CursorSetup guide
- CodexSetup guide
- WindsurfSetup guide
- Gemini CLISetup guide
- Google AntigravitySetup guide
- GitHub CopilotSetup guide
- Claude EnterpriseSetup guide
- Microsoft Copilot StudioSetup guide
- Open WebUISetup guide
- LangChainSetup guide
- HaystackSetup guide
- Strands AgentsSetup guide
- Vercel AI SDKSetup guide
- n8nSetup guide
Common questions about running GitHub MCP through TrustGate.
Other MCP servers
More servers from the catalog.
GitLab
Securely connect your AI agents to GitLab through TrustGate: projects, repositories, merge requests, work items, pipelines and vulnerabilities, scoped per agent and logged.
46 toolsViewNotion
Securely connect your AI agents to Notion through TrustGate: pages, databases, comments, files and agent sessions, scoped per agent and logged.
65 toolsViewLinear
Securely connect your AI agents to Linear through TrustGate: issues, projects, cycles, documents and teams, scoped per agent and logged.
78 toolsView
Connect GitHub MCP instantly
Pick the tools, point your agent at TrustGate, and GitHub MCP is live: scoped, inspected, logged.