# teams_search_messages

Search across messages in the user

Agent View of the PolicyLayer registry record for `teams_search_messages`. HTML page: https://policylayer.com/tools/sagemcp-sagemcp/teams-search-messages

## Facts

- Tool: `teams_search_messages`
- 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": "teams_search_messages",
    "arguments": {}
  }
}
```

## Why teams_search_messages is rated Low

This is a Read operation: it searches and retrieves messages from Microsoft Teams, producing no side effects. Severity is high rather than low because message content often contains sensitive information (credentials, personal data, business intelligence), making unauthorized search access a significant data exposure risk despite being read-only.

From the tool's own definition: "Tool name is 'teams_search_messages' and description states 'Search across messages in the user' — this retrieves/queries message data without modifying it."

## Use case

AI agents call teams_search_messages 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": {
    "teams_search_messages": {}
  }
}
```

## 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