> ## Documentation Index
> Fetch the complete documentation index at: https://docs.slaunt.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Slaunt MCP tools overview

> Slaunt MCP tool groups, conditionally listed tools, and the content plus structuredContent result format.

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](https://docs.slaunt.ai/tools/lifecycle.md) | Report threads and runs to Quaero | `thread_begin`, `run_begin`, `run_step`, `run_end`, `thread_close` |
| [Slaunt Context](https://docs.slaunt.ai/tools/context.md) | Look up and record what happened | `ccr_search`, `ccr_recent`, `ccr_log_event`, `ccr_issue_log`, `ccr_event_*` |
| [Tasks](https://docs.slaunt.ai/tools/tasks.md) | Track work that's still open | `tasks_*` |
| [Workspace](https://docs.slaunt.ai/tools/workspace.md) | Check identity and load context in one call | `identity_context`, `aki_workspace_context`, `workspace_people_list` |
| [Room](https://docs.slaunt.ai/tools/room.md) | Read and organize shared files | `room_*` |
| [GitHub](https://docs.slaunt.ai/tools/github.md) | Verify against repos, PRs, CI | `github_*` |
| [Hooks and capture](https://docs.slaunt.ai/tools/hooks.md) | Used by client hooks and bridges, not the model | `codex_hook_event`, `claude_hook_event`, `chat_*`, `tool_authorize*`, `threads_*` |
| [Provider tools](https://docs.slaunt.ai/tools/gateway.md) | 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:

```json theme={null}
{
  "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 on the tool pages describe `structuredContent`. The optional `org_id`/`project` arguments on many tools are only a cross-check against your token; leave them out.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.