Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/ringo380/ga-mcp-fullWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ringo380/ga-mcp-full/auth-login)<a href="https://agentmods.dev/commands/ringo380/ga-mcp-full/auth-login"><img src="https://agentmods.dev/badge/commands/ringo380/ga-mcp-full/auth-login/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ringo380/ga-mcp-full/auth-login"><img src="https://agentmods.dev/badge/commands/ringo380/ga-mcp-full/auth-login.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.00410 |
| Opus 5 | $0.00010 | $0.00205 |
| Sonnet 5 | $0.00004 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
auth-login scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/ga-mcp-full:auth-login
Authenticate the ga-mcp-full MCP server against your Google Analytics account.
What this does
Runs ga-mcp-full auth login, which:
- Resolves the OAuth client (env var override →
~/.config/ga-mcp/client_secrets.json→ bundled public Desktop client). - Opens your default browser to Google's consent screen with the
analytics.editscope. - Starts a local HTTP server on
127.0.0.1bound to a random free port (no pre-registration needed — Google's installed-app OAuth accepts any loopback port). - Completes a PKCE-protected (S256) authorization code exchange.
- Caches credentials at
~/.config/ga-mcp/credentials.json(mode0600).
Subsequent Claude Code sessions reuse the cached refresh token automatically — you never need the client ID/secret at runtime after this step.
Steps
-
Run the login command with
Bash:ga-mcp-full auth login -
Report the result to the user. If the command exits non-zero with
client_not_configured, point them at/ga-mcp-full:setupso they can install the CLI or provide a custom OAuth client. -
If the browser does not open automatically, the command prints the auth URL to stderr — surface that URL to the user so they can open it manually.
Notes
- The MCP server does NOT need to be restarted after login — the next tool call will load the new credentials from disk.
- If a cached refresh token has been revoked, tool calls surface
"GA auth required: run /ga-mcp-full:auth-login ..."— rerun this command to re-authenticate.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 39 lines · 19 tokens per session scan A 5673b93b1ec5
auth-login is a command published in the GitHub repository ringo380/ga-mcp-full (0 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 410 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
meta-attach-vault
Interactive wizard to attach an Obsidian vault to a code/dev workspace (the common case), bootstrap a standalone vault, or register a remote vault. Provisions plugins + scaffolds wiki structure + binds .env + edits .gitignore + offers a conventions picker. (Skill meta-attach-vault handles natural-language triggers.).
meta-sync-template
Propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Interactive picker — lists each vault with online status + REST-API-plugin presence, lets you sync all or a subset, with optional --force re-clone. (Skill meta-sync-template handles natural-language triggers…
okf-export
Export a wiki subset as a shareable OKF knowledge bundle (Google's Open Knowledge Format v0.1) — slugified filenames, relative markdown links, per-folder indexes, newest-first log, conformance self-checked. (Skill wiki-export handles the flow via its okf target.).
okf-projections
Régénérer les projections OKF du wiki (index racine + index par répertoire + log) ou vérifier leur dérive (--check).
wiki-boundary
Rank the wiki's "frontier" pages — the crossroads many pages link to that stay thin inside — to decide where research would pay off. Read-only, deterministic, no LLM. The score proposes attention, not importance. (Skill wiki-boundary handles natural-language triggers.).
wiki-graph
Build a typed knowledge graph (Understand-Anything-compatible knowledge-graph.json) from a vault's wiki — articles/entities/claims/sources/topics + relationships — written to wiki-meta/graph/ + a .understand-anything/ copy for the UA dashboard. Deterministic, no LLM. (Skill wiki-graph handles natural-language…