# github_check_token_scopes Check the current OAuth token Agent View of the PolicyLayer registry record for `github_check_token_scopes`. HTML page: https://policylayer.com/tools/sagemcp-sagemcp/github-check-token-scopes ## Facts - Tool: `github_check_token_scopes` - Server: Sage MCP (`sagemcp/sagemcp`) — https://policylayer.com/tools/sagemcp-sagemcp.md - Homepage: https://github.com/sagemcp/sagemcp - Risk category: Read (Low risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Allowed ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "github_check_token_scopes", "arguments": {} } } ``` ## Why github_check_token_scopes is rated Low This tool retrieves information about the OAuth token's permissions and scopes. It is a non-destructive, read-only operation that queries existing data without creating, modifying, deleting, or executing any actions. The minimal blast radius if misused is reading token scope information, which could inform an attacker of available permissions but does not directly enable access or changes. From the tool's own definition: "Tool name 'github_check_token_scopes' and description 'Check the current OAuth token' indicate a read-only query of token metadata/scopes without modification or execution." ## Use case AI agents call github_check_token_scopes to retrieve information from Sage MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere. ## Recommended policy (PolicyLayer) Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Sage MCP: ```json { "version": "1", "default": "deny", "tools": { "github_check_token_scopes": {} } } ``` ## Other tools on Sage MCP (358) - `claude_code_delete_invite` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/claude-code-delete-invite.md - `claude_code_remove_user` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/claude-code-remove-user.md - `codex_delete_user` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/codex-delete-user.md - `confluence_delete_page` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/confluence-delete-page.md - `copilot_remove_seats` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/copilot-remove-seats.md - `cursor_remove_member` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/cursor-remove-member.md - `discord_delete_message` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/discord-delete-message.md - `excel_clear_range` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/excel-clear-range.md - `excel_delete_worksheet` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/excel-delete-worksheet.md - `gmail_trash_message` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/gmail-trash-message.md - `google_sheets_batch_update` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/google-sheets-batch-update.md - `google_sheets_clear_range` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/google-sheets-clear-range.md - `google_sheets_delete_sheet` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/google-sheets-delete-sheet.md - `google_slides_delete_slide` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/google-slides-delete-slide.md - `outlook_delete_message` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/outlook-delete-message.md - `powerpoint_delete_presentation` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/powerpoint-delete-presentation.md - `slack_reactions_remove` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/slack-reactions-remove.md - `zoom_delete_meeting` — Destructive — https://policylayer.com/tools/sagemcp-sagemcp/zoom-delete-meeting.md - `bitbucket_trigger_pipeline` — Execute — https://policylayer.com/tools/sagemcp-sagemcp/bitbucket-trigger-pipeline.md - `excel_run_formula` — Execute — https://policylayer.com/tools/sagemcp-sagemcp/excel-run-formula.md - `gitlab_retry_pipeline` — Execute — https://policylayer.com/tools/sagemcp-sagemcp/gitlab-retry-pipeline.md - `copilot_add_seats` — Financial — https://policylayer.com/tools/sagemcp-sagemcp/copilot-add-seats.md - `cursor_set_user_spend_limit` — Financial — https://policylayer.com/tools/sagemcp-sagemcp/cursor-set-user-spend-limit.md - `bitbucket_get_diff` — Read — https://policylayer.com/tools/sagemcp-sagemcp/bitbucket-get-diff.md - `bitbucket_get_file` — Read — https://policylayer.com/tools/sagemcp-sagemcp/bitbucket-get-file.md - `bitbucket_get_issue` — Read — https://policylayer.com/tools/sagemcp-sagemcp/bitbucket-get-issue.md - `bitbucket_get_pipeline` — Read — https://policylayer.com/tools/sagemcp-sagemcp/bitbucket-get-pipeline.md - `bitbucket_get_pull_request` — Read — https://policylayer.com/tools/sagemcp-sagemcp/bitbucket-get-pull-request.md - `bitbucket_get_repository` — Read — https://policylayer.com/tools/sagemcp-sagemcp/bitbucket-get-repository.md - `bitbucket_list_branches` — Read — https://policylayer.com/tools/sagemcp-sagemcp/bitbucket-list-branches.md - …and 328 more: https://policylayer.com/tools/sagemcp-sagemcp.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=sagemcp-sagemcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/sagemcp-sagemcp