API & Integrations

MCP security model and role scopes

MCP tokens inherit the calling member's role, further clamped by an optional role override. Writes require confirm. Admin actions require admin.

Updated 2026-07-10

1 min read

mcp

security

rbac

Quick answer#

Effective role = min(member role, token role override). Read tools need viewer+, writes need member+ and confirm: true, and add_maintenance_window needs admin.

Guardrails#

Tokens are org-scoped — never cross-tenant

Every call re-validates the calling member's role

Prompt-injection defense: writes require explicit confirm: true from the model

Full audit trail in api_request_logs

Where to find it in Lemwatch#

Settings → MCP tokens → Role override when issuing a token.

How to lock a token down#

Issue a token with role override = viewer.

Give it to your AI client for read-only workflows.

Keep admin-capable tokens for humans only.

Rotate quarterly.

FAQ#

Can a token escalate its own role?#

No. Role override can only *reduce* privileges.

What if a member is removed?#

All tokens they created continue to work (they're org-scoped), but you should revoke any they no longer need.

Manage MCP tokens

MCP tool catalog

Roles and permissions

Was this article helpful?

MCP rate limits and tier gating

What integrations does Lemwatch support?

How do I create and revoke MCP tokens?

MCP tokens are org-scoped bearer secrets. Create them in Settings, copy once, and revoke any time — hashes are stored, plaintext never is.

MCP tool catalog: everything Claude and ChatGPT can call

The 11 MCP tools, 4 resources, and 5 prompts Lemwatch exposes to AI assistants — with what each one does and who can call it.

Team Roles & Permissions

Understand the different access levels for team members.

What integrations does Lemwatch support?

Lemwatch routes alerts to Slack, Discord, Teams, PagerDuty, Telegram, Google Chat, Mattermost, Rocket.Chat, ntfy, generic webhooks, and email.

Back to Help Center