gtm-mcp-server

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.

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ DevTools ai mcp google-tag-manager oauth2 google-api devtools automation tracking ga4 server-side-gtm
⚙ Agent Friendliness
57
/ 100
Can an agent use this?
🔒 Security
67
/ 100
Is it safe for agents?
⚡ Reliability
28
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
85
Documentation
70
Error Messages
0
Auth Simplicity
70
Rate Limits
0

🔒 Security

TLS Enforcement
80
Auth Strength
85
Scope Granularity
40
Dep. Hygiene
50
Secret Handling
70

Uses OAuth 2.1 with PKCE and claims token-based authentication with revocation. README includes safety confirmations for deletions/publishing and workspace-only changes until publish. However, provided content does not detail scope granularity, TLS requirements explicitly, or operational security controls (logging/redaction, audit retention), so scores reflect partial documentation.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
30
Error Recovery
45
AF Security Reliability

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.

Use Cases

  • Generate and maintain GA4/ecommerce tracking setups in GTM via natural language
  • Audit GTM containers for issues (duplicates, naming inconsistencies, orphaned items, best-practice/security concerns)
  • Create triggers, variables, and templates for common measurement patterns
  • Implement consent-aware tracking logic (e.g., fire tags only when analytics consent is granted)
  • Bulk update/rename/organize GTM items across large containers
  • Agencies standardizing multiple client GTM implementations and publishing via versioning
  • Server-side GTM setup for clients and event transformations

Not For

  • Replacing Google Tag Manager UI for teams that need full UI workflows and fine-grained manual control
  • Use cases requiring tight SLAs where failures or partial changes cannot be tolerated
  • Highly regulated environments without assurance of logging, auditability, and data handling practices beyond what’s documented

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: OAuth 2.1 with PKCE
OAuth: Yes Scopes: No

README describes OAuth 2.1 + PKCE and token-based auth that can be revoked; it does not specify exact scopes/granularity in the provided text.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; likely self-hostable only (per Docker instructions) and/or an externally hosted MCP URL.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

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.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for gtm-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered