{"id":"paolobietolini-gtm-mcp-server","name":"gtm-mcp-server","af_score":57.2,"security_score":66.8,"reliability_score":27.5,"what_it_does":"Provides an MCP (Model Context Protocol) server that lets an LLM manage Google Tag Manager (GTM) accounts/containers/workspaces: read GTM entities, create/update/delete tags, triggers, variables, templates, and server-side GTM components, and version/publish changes via guided actions with safety confirmations.","best_when":"You want an LLM-driven, tool-based workflow (with MCP + OAuth) to read and make structured GTM changes, including safe versioning and optional confirmations before destructive actions.","avoid_when":"You cannot authenticate/authorize via the described OAuth flow, or you need guarantees about rate limits, reliability, and error recovery behaviors beyond what’s documented.","last_evaluated":"2026-03-30T15:24:02.549223+00:00","has_mcp":true,"has_api":false,"auth_methods":["OAuth 2.1 with PKCE"],"has_free_tier":false,"known_gotchas":["Google Tag Manager API may silently drop certain trigger condition fields (e.g., `autoEventFilter`) when creating/updating certain trigger types.","Without explicit idempotency guarantees, agents should avoid blindly retrying write operations; prefer pre-checks (e.g., list/get then update) and confirmation steps before deletes/publish."],"error_quality":0.0}