AI 에이전트가 Firestore, Auth, Storage, Functions와 상호작용할 수 있도록 지원하는 고성능 Firebase 에뮬레이터 로컬 대체 도구입니다.
다른 이름 firenook-dev/firenook
- 스타
- 106
- Tools
- 55
- 다운로드, 30일
- —
- 최신 버전
- 0.2.5
- 마지막 커밋
- 2026년 11월 14일
- 라이선스
- Apache-2.0
Firenook MCP란?
AI 에이전트가 Firestore, Auth, Storage, Functions와 상호작용할 수 있도록 지원하는 고성능 Firebase 에뮬레이터 로컬 대체 도구입니다. 55개 도구를 제공합니다. 예: firenook_status, emulators_export, firestore_get.
프로젝트 README에서 생성된 요약
Firenook MCP server 정보
Firebase 애플리케이션을 개발하는 개발자는 Firenook를 사용하여 Firestore, Auth, Storage, Functions를 테스트하기 위한 고성능 로컬 환경을 구축할 수 있습니다. 공식 Firebase Local Emulator Suite를 즉시 대체할 수 있는 드롭인 도구이므로, 기존의 firebase.json, SDK, 포트를 그대로 유지하면서도 훨씬 빠른 쓰기 속도와 낮은 메모리 사용량을 확보할 수 있습니다. 이 시스템은 네이티브 Rust 서비스로 구축되었으며 실행을 위해 Node 22, 24 또는 26 버전이 필요합니다.
AI 코딩 에이전트와 통합하려면 firenook mcp 명령어를 사용하면 됩니다. 이를 통해 Claude Code, Cursor, VS Code와 같은 도구가 로컬 백엔드와 직접 상호작용할 수 있습니다. 이 MCP server는 Firestore, 사용자 토큰, 로그, 함수 호출, Security Rules 결정, Storage, Pub/Sub, Cloud Tasks, Eventarc를 관리하기 위한 전용 도구를 제공합니다. 가볍게 설계되어 설정 시 Java나 기타 무거운 의존성을 설치할 필요가 없습니다.
활용 사례
- 1AI를 활용한 백엔드 테스트 자동화AI 에이전트에게 Firestore 데이터와 함수 로그를 검사할 수 있는 권한을 부여하여 로컬 환경의 디버깅을 수행합니다.
- 2로컬 개발 사이클 가속화표준 Firebase 에뮬레이터를 대체하여 대규모 작업 시 더 빠른 쓰기 속도와 적은 메모리 소비를 실현합니다.
- 3로컬 데이터의 지속성 유지AI에게 실행 세션이 바뀌어도 상태가 유지되는 로컬 데이터베이스를 관리하도록 지시합니다.
- 4새 프로젝트의 신속한 초기화에이전트에게 처음부터 완전한 로컬 에뮬레이션 환경을 구축하도록 요청합니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
Firenook MCP 설치 방법
형식 확인: 2026년 11월 10일Cursor에 추가Goose에 추가Claude Code에 Firenook MCP 설치
$ claude mcp add firenook -- npx -y firenook mcpCursor에 Firenook MCP 설치
~/.cursor/mcp.json
{
"mcpServers": {
"firenook": {
"command": "npx",
"args": [
"-y",
"firenook",
"mcp"
]
}
}
}VS Code에 Firenook MCP 설치
.vscode/mcp.json
{
"servers": {
"firenook": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"firenook",
"mcp"
]
}
}
}VS Code CLI에 Firenook MCP 설치
$ code --add-mcp '{"name":"firenook","type":"stdio","command":"npx","args":["-y","firenook","mcp"]}'Claude Desktop에 Firenook MCP 설치
claude_desktop_config.json
{
"mcpServers": {
"firenook": {
"command": "npx",
"args": [
"-y",
"firenook",
"mcp"
]
}
}
}Codex에 Firenook MCP 설치
$ codex mcp add firenook -- npx -y firenook mcpCodex config.toml에 Firenook MCP 설치
~/.codex/config.toml
[mcp_servers.firenook] command = "npx" args = ["-y", "firenook", "mcp"]
Gemini CLI에 Firenook MCP 설치
$ gemini mcp add -s user firenook npx -- -y firenook mcpGemini settings.json에 Firenook MCP 설치
~/.gemini/settings.json
{
"mcpServers": {
"firenook": {
"command": "npx",
"args": [
"-y",
"firenook",
"mcp"
]
}
}
}HostedMCP가 2026년 11월 16일에 실행 확인
firenook 0.2.5을(를) 네트워크와 키가 없는 격리된 컨테이너에서 이 명령으로 실행했습니다. 응답하며 도구 55개를 보여 주었습니다.
Firenook MCP 도구 55
tools/list로 서버에서 직접 읽음firenook_statusThe running Firenook suite: how the project was found, hub locator, hub status, the emulators listing (host and port per service) and the CLI version; with no project, the suites whose locators answer.
emulators_exportExport the running Firestore, Auth and Storage data to a directory outside the project (firenook emulators:export).
firestore_getRead one Firestore document by path (collection/document[/subcollection/document]); returns its fields as plain JSON or exists:false.
firestore_queryRun a structured query over one collection, or with collectionGroup over every collection with that id (Firestore runQuery): optional where filters, ordering and limit; returns matching documents as plain JSON.
firestore_countCount the documents of a collection, or with collectionGroup of every collection with that id, that match optional where filters (a COUNT aggregation; no documents are read back).
firestore_setWrite a Firestore document from plain JSON: replaces it, or with merge:true updates only the given top-level fields.
firestore_deleteDelete a document (recursive:true also its subcollections) or a collection (its documents; recursive:true everything beneath) through the emulator delete route.
firestore_list_collectionsList collection ids at the database root or under a document (listCollectionIds).
firestore_missing_indexesThe indexes production would refuse the app's queries for: each one a query needed that its database's index file (firestore.indexes.json) does not declare, with the entry to add under indexes or fieldOverrides, the first query that needed it (fields and operators, no values), how many did and when; saving the file puts it in force at once.
auth_list_usersList Auth emulator accounts (accounts:batchGet) with uid, email, phone, display name, claims and provider data.
auth_get_userLook up one Auth account by uid, email or phone number (accounts:lookup).
auth_create_userCreate an Auth emulator account with a synthetic email/password, phone number or display name (never real credentials).
| firenook_status | The running Firenook suite: how the project was found, hub locator, hub status, the emulators listing (host and port per service) and the CLI version; with no project, the suites whose locators answer. | |
| emulators_export | Export the running Firestore, Auth and Storage data to a directory outside the project (firenook emulators:export). | |
| firestore_get | Read one Firestore document by path (collection/document[/subcollection/document]); returns its fields as plain JSON or exists:false. | |
| firestore_query | Run a structured query over one collection, or with collectionGroup over every collection with that id (Firestore runQuery): optional where filters, ordering and limit; returns matching documents as plain JSON. | |
| firestore_count | Count the documents of a collection, or with collectionGroup of every collection with that id, that match optional where filters (a COUNT aggregation; no documents are read back). | |
| firestore_set | Write a Firestore document from plain JSON: replaces it, or with merge:true updates only the given top-level fields. | |
| firestore_delete | Delete a document (recursive:true also its subcollections) or a collection (its documents; recursive:true everything beneath) through the emulator delete route. | |
| firestore_list_collections | List collection ids at the database root or under a document (listCollectionIds). | |
| firestore_missing_indexes | The indexes production would refuse the app's queries for: each one a query needed that its database's index file (firestore.indexes.json) does not declare, with the entry to add under indexes or fieldOverrides, the first query that needed it (fields and operators, no values), how many did and when; saving the file puts it in force at once. | |
| auth_list_users | List Auth emulator accounts (accounts:batchGet) with uid, email, phone, display name, claims and provider data. | |
| auth_get_user | Look up one Auth account by uid, email or phone number (accounts:lookup). | |
| auth_create_user | Create an Auth emulator account with a synthetic email/password, phone number or display name (never real credentials). |
도구 55개 모두 보기도구 수 줄이기
auth_delete_userDelete one Auth emulator account by uid (accounts:delete).
auth_oob_codesThe pending out-of-band codes (email verification, password reset, sign-in links) the Auth emulator holds instead of sending email.
auth_verification_codesThe pending phone verification codes the Auth emulator holds instead of sending SMS.
auth_mint_tokenMint a Firebase ID token (valid one hour) and refresh token for an existing Auth emulator user, so an agent can call a function or the REST API as that user; claims replace the custom claims for this token only.
auth_set_claimsSet an Auth emulator user's custom claims: replace them (as the Admin SDK's setCustomUserClaims does) or with mode merge change only the given keys (a null value removes that key).
auth_remove_claimsRemove the named custom claim keys from an Auth emulator user, keeping its other claims.
auth_disable_userDisable an Auth emulator account: its sign-ins and token refreshes fail until it is enabled again.
auth_enable_userEnable a disabled Auth emulator account again.
auth_revoke_tokensRevoke an Auth emulator user's refresh tokens (validSince moves to now), so its existing sessions must sign in again.
auth_list_tenantsList the Auth emulator's tenants (multi-tenancy) with their user counts and sign-in settings.
storage_listList Storage objects and folder prefixes under a prefix (one level, like listAll).
storage_get_metadataThe metadata of one Storage object (content type, size, timestamps, custom metadata, download tokens) or exists:false.
storage_readRead a Storage object's content: text inline (text, JSON, XML, SVG...), anything else as base64; at most maxBytes are returned and truncated says whether there is more.
storage_uploadUpload (create or replace) a Storage object from text or base64 bytes with a content type and custom metadata, as the Admin SDK would (rules skipped; finalize triggers run).
storage_deleteDESTRUCTIVE: delete one Storage object, or with a path ending in / every object under that folder.
storage_copyCopy a Storage object (or a folder, a path ending in /) to a new path, in the same or another bucket; refuses to overwrite unless overwrite is true.
storage_moveMove (rename) a Storage object or a folder (a path ending in /), in the same or another bucket; refuses to overwrite unless overwrite is true.
functions_listThe functions loaded by the running suite: name, region, generation, trigger kind, event type or schedule, and the HTTPS URL of request/callable functions.
functions_invokeInvoke a loaded function: an HTTPS/callable request with data, or with eventData a background event (Firestore before/after, Storage object, Pub/Sub message, Auth user, schedule, Eventarc custom event, task queue payload) shaped as the official functions shell sends it.
functions_list_callsRecent function calls, newest first: trigger kind and cause, outcome (succeeded, failed, timedOut, crashed...), HTTP status, duration and the first line of the error.
functions_get_callOne function call in full: its cause, request (method, path, headers, body), response (status, body), event payload, the error with its stack trace, the call's console output and timings.
functions_replay_callRun a recorded function call again with the same request or event (after a fix, say) and report the new call: outcome, status, response body and its id for functions_get_call.
logs_searchSearch the suite's log (every emulator and every function's console output) by service, level, function, call, text and time; returns the newest matching lines, oldest first.
logs_facetsCount the log lines matching a filter by level, service, function, codebase, extension instance and kind, to see where errors and warnings come from before reading them.
rules_getThe Security Rules in force: the Firestore rules of a database and the Storage rules of a bucket (source, whether they are enforced, the file and its problems).
rules_evaluateAsk the rules in force (or a draft) whether a request would be allowed: get, list, create, update or delete on a Firestore path or Storage object as a given user or unauthenticated; returns the verdict, the rule line that decided it and each evaluated expression's value. Nothing is written.
rules_list_denialsRecent requests the Security Rules denied (app clients only; admin and owner requests skip the rules), newest last; with explain, the rule lines that denied each one.
pubsub_publishPublish a message to a Pub/Sub emulator topic: string data as given, other JSON as its text (base64-encoded on the wire), plus attributes.
pubsub_list_topicsThe Pub/Sub emulator's topics with their published counts, subscriptions and the functions they trigger (schedule topics included).
pubsub_list_subscriptionsEvery Pub/Sub subscription (of every topic, and detached ones) with its delivery type, filter, dead-letter topic and backlog.
pubsub_peekPeek at a subscription's backlog in delivery order without pulling, leasing or acking anything: each message's state, attempts, attributes and data.
tasks_statsQueue statistics of the Cloud Tasks emulator (queueStats).
tasks_listThe Cloud Tasks queues (with their pending and running counts) and the tasks waiting in them; with queue, only that queue's tasks, optionally in one state.
tasks_runDispatch one waiting Cloud Tasks task now instead of at its schedule time (it is sent on the next tick).
schedules_listThe scheduled functions (onSchedule, pubsub.schedule): expression, time zone, next runs, paused state and the latest runs with their delivery.
schedules_runRun a scheduled function now: publish one tick to its schedule topic, as Cloud Scheduler would, and report the run.
eventarc_publishPublish a custom CloudEvent to an Eventarc channel (default the project's Firebase channel), as getEventarc().channel().publish() does, and report which functions received it and how each call ended.
eventarc_list_eventsThe Eventarc events the suite received, newest first (custom events, replays and the Firebase services' own), with how many functions matched, received or failed each.
eventarc_get_eventOne Eventarc event with its attributes, data and every function delivery (outcome, duration, invocation id for functions_get_call).
eventarc_replay_eventDeliver a received Eventarc event again to the functions it matches (a new event, origin replay) and report the new deliveries.
extensions_listThe Firebase Extensions instances the suite runs: reference and version, state (running, loading, failed) with the load error, and their function count.
extensions_reloadReload one Extensions instance (re-read its .env parameters and source, restart its functions) and report its state and functions afterwards.
emulators_clearDESTRUCTIVE: delete all data of the chosen services (every Firestore document, every Auth user and tenant, every Storage object, every Pub/Sub topic, subscription, schema and message, every Cloud Tasks task and its history). Clearing more than one service needs confirmProject set to the project id.
| auth_delete_user | Delete one Auth emulator account by uid (accounts:delete). | |
| auth_oob_codes | The pending out-of-band codes (email verification, password reset, sign-in links) the Auth emulator holds instead of sending email. | |
| auth_verification_codes | The pending phone verification codes the Auth emulator holds instead of sending SMS. | |
| auth_mint_token | Mint a Firebase ID token (valid one hour) and refresh token for an existing Auth emulator user, so an agent can call a function or the REST API as that user; claims replace the custom claims for this token only. | |
| auth_set_claims | Set an Auth emulator user's custom claims: replace them (as the Admin SDK's setCustomUserClaims does) or with mode merge change only the given keys (a null value removes that key). | |
| auth_remove_claims | Remove the named custom claim keys from an Auth emulator user, keeping its other claims. | |
| auth_disable_user | Disable an Auth emulator account: its sign-ins and token refreshes fail until it is enabled again. | |
| auth_enable_user | Enable a disabled Auth emulator account again. | |
| auth_revoke_tokens | Revoke an Auth emulator user's refresh tokens (validSince moves to now), so its existing sessions must sign in again. | |
| auth_list_tenants | List the Auth emulator's tenants (multi-tenancy) with their user counts and sign-in settings. | |
| storage_list | List Storage objects and folder prefixes under a prefix (one level, like listAll). | |
| storage_get_metadata | The metadata of one Storage object (content type, size, timestamps, custom metadata, download tokens) or exists:false. | |
| storage_read | Read a Storage object's content: text inline (text, JSON, XML, SVG...), anything else as base64; at most maxBytes are returned and truncated says whether there is more. | |
| storage_upload | Upload (create or replace) a Storage object from text or base64 bytes with a content type and custom metadata, as the Admin SDK would (rules skipped; finalize triggers run). | |
| storage_delete | DESTRUCTIVE: delete one Storage object, or with a path ending in / every object under that folder. | |
| storage_copy | Copy a Storage object (or a folder, a path ending in /) to a new path, in the same or another bucket; refuses to overwrite unless overwrite is true. | |
| storage_move | Move (rename) a Storage object or a folder (a path ending in /), in the same or another bucket; refuses to overwrite unless overwrite is true. | |
| functions_list | The functions loaded by the running suite: name, region, generation, trigger kind, event type or schedule, and the HTTPS URL of request/callable functions. | |
| functions_invoke | Invoke a loaded function: an HTTPS/callable request with data, or with eventData a background event (Firestore before/after, Storage object, Pub/Sub message, Auth user, schedule, Eventarc custom event, task queue payload) shaped as the official functions shell sends it. | |
| functions_list_calls | Recent function calls, newest first: trigger kind and cause, outcome (succeeded, failed, timedOut, crashed...), HTTP status, duration and the first line of the error. | |
| functions_get_call | One function call in full: its cause, request (method, path, headers, body), response (status, body), event payload, the error with its stack trace, the call's console output and timings. | |
| functions_replay_call | Run a recorded function call again with the same request or event (after a fix, say) and report the new call: outcome, status, response body and its id for functions_get_call. | |
| logs_search | Search the suite's log (every emulator and every function's console output) by service, level, function, call, text and time; returns the newest matching lines, oldest first. | |
| logs_facets | Count the log lines matching a filter by level, service, function, codebase, extension instance and kind, to see where errors and warnings come from before reading them. | |
| rules_get | The Security Rules in force: the Firestore rules of a database and the Storage rules of a bucket (source, whether they are enforced, the file and its problems). | |
| rules_evaluate | Ask the rules in force (or a draft) whether a request would be allowed: get, list, create, update or delete on a Firestore path or Storage object as a given user or unauthenticated; returns the verdict, the rule line that decided it and each evaluated expression's value. Nothing is written. | |
| rules_list_denials | Recent requests the Security Rules denied (app clients only; admin and owner requests skip the rules), newest last; with explain, the rule lines that denied each one. | |
| pubsub_publish | Publish a message to a Pub/Sub emulator topic: string data as given, other JSON as its text (base64-encoded on the wire), plus attributes. | |
| pubsub_list_topics | The Pub/Sub emulator's topics with their published counts, subscriptions and the functions they trigger (schedule topics included). | |
| pubsub_list_subscriptions | Every Pub/Sub subscription (of every topic, and detached ones) with its delivery type, filter, dead-letter topic and backlog. | |
| pubsub_peek | Peek at a subscription's backlog in delivery order without pulling, leasing or acking anything: each message's state, attempts, attributes and data. | |
| tasks_stats | Queue statistics of the Cloud Tasks emulator (queueStats). | |
| tasks_list | The Cloud Tasks queues (with their pending and running counts) and the tasks waiting in them; with queue, only that queue's tasks, optionally in one state. | |
| tasks_run | Dispatch one waiting Cloud Tasks task now instead of at its schedule time (it is sent on the next tick). | |
| schedules_list | The scheduled functions (onSchedule, pubsub.schedule): expression, time zone, next runs, paused state and the latest runs with their delivery. | |
| schedules_run | Run a scheduled function now: publish one tick to its schedule topic, as Cloud Scheduler would, and report the run. | |
| eventarc_publish | Publish a custom CloudEvent to an Eventarc channel (default the project's Firebase channel), as getEventarc().channel().publish() does, and report which functions received it and how each call ended. | |
| eventarc_list_events | The Eventarc events the suite received, newest first (custom events, replays and the Firebase services' own), with how many functions matched, received or failed each. | |
| eventarc_get_event | One Eventarc event with its attributes, data and every function delivery (outcome, duration, invocation id for functions_get_call). | |
| eventarc_replay_event | Deliver a received Eventarc event again to the functions it matches (a new event, origin replay) and report the new deliveries. | |
| extensions_list | The Firebase Extensions instances the suite runs: reference and version, state (running, loading, failed) with the load error, and their function count. | |
| extensions_reload | Reload one Extensions instance (re-read its .env parameters and source, restart its functions) and report its state and functions afterwards. | |
| emulators_clear | DESTRUCTIVE: delete all data of the chosen services (every Firestore document, every Auth user and tenant, every Storage object, every Pub/Sub topic, subscription, schema and message, every Cloud Tasks task and its history). Clearing more than one service needs confirmProject set to the project id. |
자동 검사
2026년 11월 16일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능firenook-dev/firenook is public and reachablegithub.com/firenook-dev/firenook ↗통과
- 패키지가 이 저장소를 소스로 명시firenook names firenook-dev/firenook as sourcenpmjs.com/package/firenook ↗통과
- 빌드 출처(Sigstore 증명)Sigstore attestation for firenooknpmjs.com/package/firenook/v/0.2.5#provenance ↗통과
- 오픈 소스 라이선스 (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-14github.com/firenook-dev/firenook ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음No popular package one edit away from firenook통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음the package checked; no critical advisoryosv.dev ↗통과
- 모델에 대한 숨겨진 지침 없음A tool description points at credential files결함 발견
- 파괴적인 도구에 라벨 표시됨No tool named like delete, drop or exec통과
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기Already using the Firebase emulators? Install Firenook and change one word:
npm install --save-dev firenook
- firebase emulators:start --import ./data
+ firenook emulators:start --import ./data
Same flags, same ports, and your firebase.json, rules, Functions code and app
stay as they are. In a terminal, run it as npx firenook emulators:start. To
keep your data between runs, add --keep-data.
Firenook needs Node 22, 24 or 26. Starting a new project? npx firenook init
sets one up on one screen, installs it and starts the emulators.
Why Firenook
- A drop-in for the official emulator. It reads
firebase.json,.firebaserc, rules and indexes the way the Firebase CLI does, serves the same ports, and your client and Admin SDKs connect unchanged. It imports and exports the official format. - Fast and light. Native Rust services with the data on disk. On a real application's two-hour workload, Firenook peaked at 2.11 GiB of memory where the official emulator reached 22.57 GiB, answered writes in 5.1 ms against 208 ms at the median, and used 61% less CPU.
- Your data stays. Add
--keep-dataand Firestore, Auth and Storage come back with all your data in about half a second, even with millions of documents. A crash loses at most the last second of writes. - Nothing else to install. No Java, no firebase-tools, nothing else downloaded at install or start (an Extension from the registry is fetched once, on first use). npm or Bun picks the native engine for your machine; Node runs your Functions.
- A console and a terminal made for it, and
firenook mcpfor your coding agent: Firestore, users and their tokens, logs and function calls, Security Rules decisions, Storage, Pub/Sub, Cloud Tasks and Eventarc as tools.npx firenook mcp addsets it up for Claude Code, Cursor and VS Code; other agents run the samenpx firenook mcp.
Switching from the official emulator
Keep firebase-tools for deploying, and add .firenook/ to your .gitignore:
every run keeps its working data there.
$ npx firenook init --adopt --dry-run
skip Firenook: firebase.json configures the hosting emulator, which Firenook does not implement; skipping it.
ok nothing to change; services: firestore, auth, storage, functions
- "emulators": "firebase emulators:start --import ./data --export-on-exit",
+ "emulators": "firenook emulators:start --import ./data --export-on-exit",
Same flags, same ports, the official export format both ways. To keep your
data between runs without exporting, replace --export-on-exit with
--keep-data; ./data is then never written.
Starting fresh instead: npx firenook init.
Getting started
covers both.
The console
The console the Firebase emulators should have had. Google's Emulator UI
has no page for your Functions, Pub/Sub, Cloud Tasks or Eventarc, only a log.
Firenook's console covers every service it runs, live, on the Emulator UI's
port, at
http://127.0.0.1:4000/console. It shows every function call with its
trigger, duration and logs, and an inbox of the codes and links Auth would
have sent. It has Firestore and Storage with their rules, Pub/Sub, Cloud
Tasks and Eventarc, and an Overview of every service's health.
What it emulates
Firestore, Authentication, Cloud Storage (with native Security Rules), Cloud
Functions (every trigger type, reload on save, debugging), Extensions, Pub/Sub,
Cloud Tasks and Eventarc. Realtime Database, Hosting, App Hosting and Data
Connect are not emulated; a firebase.json that configures them still starts,
with a warning. See compatibility.
Benchmarks
One real application with 211,205 documents and 6.7 GB in Storage, and two hours of its traffic against each emulator in turn on one server. Firenook answered 25 of the 26 query shapes faster and tied on the last. The method and every figure.
Commands
firenook init [--yes] # a new project: choose, install, start
firenook init --adopt [--dry-run] # adapt an existing firebase.json
firenook doctor # read-only checks, JSON
firenook emulators:start [options] # --only, --project, --import, --export-on-exit, --inspect-functions
firenook emulators:start --keep-data [--import ./seed] # keep data between runs, in .firenook/state
firenook emulators:start --build # compile TypeScript first and on every save
firenook emulators:exec "npm test" # start, run your tests, stop
firenook emulators:export ./export # snapshot a running suite
firenook functions:invoke NAME [--data JSON | --event-data JSON] # call any function, any trigger
firenook ext:vendor [--offline] # copy registry Extensions into the project
firenook mcp # the running suite as tools for a coding agent
firenook mcp add # give Claude Code, Cursor and VS Code that server
firenook state:inspect | state:compact --state-dir DIR
Every command and option: CLI reference.
Requirements
Node 22, 24 or 26 on macOS (Apple silicon or Intel), Linux (x64 or arm64,
glibc 2.28 or newer: RHEL 8, Debian 10, Ubuntu 20.04, node:24-slim and later;
not Alpine) or Windows x64; your Functions run on it, and a codebase whose
engines.node asks for another Node is warned about at start. Keep optional
dependencies enabled: they carry the native engine for your platform. Commit
your lockfile and upgrade on purpose.
License
Apache License 2.0. Firebase, Cloud Firestore, Cloud Functions, Cloud Storage, Cloud Pub/Sub and Cloud Tasks are trademarks of Google LLC; Firenook is not affiliated with or endorsed by Google.
Firenook MCP 질문
Firenook MCP를 Claude Code에 추가하려면 어떻게 하나요?
터미널에서 claude mcp add firenook -- npx -y firenook mcp를 실행합니다. 모든 프로젝트에서 사용할 수 있게 하려면 --scope user를 추가합니다.
Firenook MCP를 Cursor에 추가하려면 어떻게 하나요?
~/.cursor/mcp.json를 열고 mcpServers 아래에 서버를 추가합니다. 위 설치 섹션에 표시된 Cursor 구성을 사용합니다.
Firenook MCP는 어떤 도구를 제공하나요?
55개 도구를 제공합니다. 예: firenook_status, emulators_export, firestore_get, firestore_query, firestore_count.
기존 Firebase 설정과 함께 Firenook를 사용할 수 있나요?
네, 기존의 firebase.json, .firebaserc, rules, indexes를 그대로 읽어오는 드롭인 대체 도구입니다.
Firenook를 실행하려면 Java가 필요한가요?
아니요, Firenook는 네이티브 Rust 서비스를 사용하므로 Java나 firebase-tools가 필요하지 않습니다.
AI 코딩 에이전트를 Firenook에 어떻게 연결하나요?
firenook mcp 명령어를 사용하여 Claude Code, Cursor, VS Code와 같은 에이전트에 Firestore, 사용자, 로그, 함수 호출 등의 도구를 제공할 수 있습니다.