You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+4-1Lines changed: 4 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -162,6 +162,9 @@ This action now supports **read-only** integration with the GitHub-hosted Model
162
162
Context Protocol (MCP) server, which provides access to GitHub tools like
163
163
repository management, issue tracking, and pull request operations.
164
164
165
+
> [!NOTE]
166
+
> The GitHub MCP integration requires a Personal Access Token (PAT) and cannot use the built-in `GITHUB_TOKEN`.
167
+
165
168
```yaml
166
169
steps:
167
170
- name: AI Inference with GitHub Tools
@@ -209,7 +212,7 @@ the action:
209
212
| `endpoint` | The endpoint to use for inference. If you're running this as part of an org, you should probably use the org-specific Models endpoint | `https://models.github.ai/inference` |
210
213
| `max-tokens` | The max number of tokens to generate | 200 |
211
214
| `enable-github-mcp` | Enable Model Context Protocol integration with GitHub tools | `false` |
212
-
| `github-mcp-token` | Token to use for GitHub MCP server (defaults to the main token if not specified). Use a separate PAT for tighter security | `""` |
215
+
| `github-mcp-token` | Token to use for GitHub MCP server (defaults to the main token if not specified). This must be a PAT for MCP to work | `""` |
0 commit comments