Tools overview
Slaunt's tools fall into a few groups. The lifecycle and Context tools are the ones nearly every agent uses on every turn; the rest you reach for when the task needs them.
| Group | Use it to | Tools |
|---|---|---|
| Lifecycle | Report threads and runs to Quaero | thread_begin, run_begin, run_step, run_end, thread_close |
| Slaunt Context | Look up and record what happened | ccr_search, ccr_recent, ccr_log_event, ccr_issue_log, ccr_event_* |
| Tasks | Track work that's still open | tasks_* |
| Workspace | Check identity and load context in one call | identity_context, aki_workspace_context, workspace_people_list |
| Room | Read and organize shared files | room_* |
| GitHub | Verify against repos, PRs, CI | github_* |
| Hooks and capture | Used by client hooks and bridges, not the model | codex_hook_event, claude_hook_event, chat_*, tool_authorize*, threads_* |
| Provider tools | Slack, Notion and other connected providers | e.g. slack.* |
Tools that only appear sometimes
| Tools | Listed when |
|---|---|
claude_hook_event | The connection is an authenticated Claude Code client |
chat_capture, chat_hook_event, chat_events_list | Chats is enabled on the server |
threads_list, threads_read | Threads agent access is enabled (HTTPS only). chat_events_list is hidden in this mode. |
| Provider tools | The workspace has connected providers |
Spawning, messaging or killing agents isn't possible over MCP; use Quaero or KillBar.
Result format
Results carry a readable summary for the model and the full data for code:
{
"content": [{ "type": "text", "text": "Found 1 semantic matches for \"auth deploy\".\n- change: Deployed auth-service v2.3.1 to production. score=0.620 tags=[deploy] @ 2026-11-12T18:04:11.000Z (id=...)" }],
"structuredContent": { "matches": [{ "score": 0.62, "record": { "...": "..." } }] }
}Response shapes in the tool sections describe structuredContent. The optional org_id/project arguments on many tools are only a cross-check against your token; leave them out.