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.
npx agentmods add instructions/dasasian/firebase-mcp-server/claude-mdgit clone --depth 1 https://github.com/dasasian/firebase-mcp-serverWrote 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/instructions/dasasian/firebase-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/dasasian/firebase-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/dasasian/firebase-mcp-server/claude-md.svg" alt="Measured on agentmods" 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 | $0.00598 | $0.00598 |
| Opus 5 | $0.00299 | $0.00299 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
firebase-mcp-server CLAUDE.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — working conventions for this repo
What this is
A general-purpose MCP server for Firebase — Firestore, Storage, Auth, and Cloud Logging —
with schema-driven validation and context-efficient tools. Published as
@dasasian/firebase-mcp-server (npm) and io.github.dasasian/firebase-mcp-server (the MCP
registry).
Build / test
npm run build (tsc) · npm run typecheck (tsc --noEmit) · npm test (vitest).
Tests cover the pure logic — path matching (src/shared/path-matcher.ts) and schema
validation (src/shared/validation.ts) — the parts that don't need live Firebase. The
test-*.ts scripts at the repo root are manual integration checks that need real
credentials and deliberately do not run in CI. Keep the unit suite green, and add to it
when you touch src/shared/.
Releasing
MCP server → npm and the MCP registry. Full process + every gotcha: ../PUBLISHING.md.
The short version:
- Update
CHANGELOG.md([Unreleased]→[X.Y.Z] — <date>). NoCHANGELOG.mdyet? Create one (Keep a Changelog format) and backfill the already-published versions fromgit log+ the GitHub releases. - Bump
versionin bothpackage.jsonandserver.json(includingserver.json'spackages[].version) — a drift between them fails the registry publish. - Commit
chore: release X.Y.Zand push. npm publish— needs your OTP. Traps: a404 on PUT= lapsed token (npm login);npm viewcan 404 for ~2 min after a successful publish (confirm withnpm access list packages, don't re-publish).git tag vX.Y.Z && git push origin vX.Y.Z— firespublish-mcp-registry.yml, which publishesserver.jsonto the registry via OIDC (npmX.Y.Zmust already be live). Never runmcp-publisherfrom your laptop — it 403s on the org namespace.gh release create vX.Y.Zwith the CHANGELOG notes; verify the registry showsX.Y.ZasisLatest(the search returns all versions — read theisLatestone).- Update the
dasasian.com/firebase-mcp-serverpage indasasian-web. Onlynpm publishand the release need your credentials; an agent drives the rest.
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.
- 5d ago First seen · 41 lines · 598 tokens per session scan A b9b4c92172b4
firebase-mcp-server CLAUDE.md is an instructions file published in the GitHub repository dasasian/firebase-mcp-server (0 stars, last pushed 20d ago), licensed MIT. It adds 598 tokens to every session, about $0.0030 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.