# collab_session_start

Create and bind a credential-fenced session. The bearer is written to a mode-0600 local file and is never returned in tool output.

Agent View of the PolicyLayer registry record for `collab_session_start`. HTML page: https://policylayer.com/tools/dev-agenttool-agenttool/collab-session-start

## Facts

- Tool: `collab_session_start`
- Server: Agenttool (`https://api.agenttool.dev/v1/mcp`) — https://policylayer.com/tools/dev-agenttool-agenttool.md
- Homepage: https://github.com/cambridgetcg/agenttool
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "collab_session_start",
    "arguments": {}
  }
}
```

## Why collab_session_start is rated High

collab_session_start triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

## Use case

AI agents invoke collab_session_start to trigger actions in Agenttool. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Agenttool:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "collab_session_start": {
      "limits": [
        {
          "counter": "collab_session_start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Agenttool (83)

- `collab_cursor_reset` — Destructive — https://policylayer.com/tools/dev-agenttool-agenttool/collab-cursor-reset.md
- `collab_session_end` — Destructive — https://policylayer.com/tools/dev-agenttool-agenttool/collab-session-end.md
- `at_think` — Execute — https://policylayer.com/tools/dev-agenttool-agenttool/at-think.md
- `collab_task_review` — Execute — https://policylayer.com/tools/dev-agenttool-agenttool/collab-task-review.md
- `listings.invoke` — Execute — https://policylayer.com/tools/dev-agenttool-agenttool/listings.invoke.md
- `agent.profile` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/agent.profile.md
- `at_chronicle` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/at-chronicle.md
- `at_consolidate` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/at-consolidate.md
- `at_recall` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/at-recall.md
- `at_substrate` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/at-substrate.md
- `at_voice` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/at-voice.md
- `at_vow` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/at-vow.md
- `at_witness` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/at-witness.md
- `browser_act` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/browser-act.md
- `browser_capabilities` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/browser-capabilities.md
- `browser_extract` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/browser-extract.md
- `browser_observe` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/browser-observe.md
- `browser_screenshot` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/browser-screenshot.md
- `browser_tabs` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/browser-tabs.md
- `canon.list_types` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/canon.list-types.md
- `canon.lookup` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/canon.lookup.md
- `canon.summary` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/canon.summary.md
- `check_gi_recognition` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/check-gi-recognition.md
- `chronicle.recent` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/chronicle.recent.md
- `collab_anchor_status` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/collab-anchor-status.md
- `collab_cursor_ack` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/collab-cursor-ack.md
- `collab_decision_record` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/collab-decision-record.md
- `collab_events_since` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/collab-events-since.md
- `collab_handoff_offer` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/collab-handoff-offer.md
- `collab_handoff_respond` — Read — https://policylayer.com/tools/dev-agenttool-agenttool/collab-handoff-respond.md
- …and 53 more: https://policylayer.com/tools/dev-agenttool-agenttool.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=dev-agenttool-agenttool · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-agenttool-agenttool