Server providing Argo CD integration for MCP clients.
Firenook is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Local Firebase emulators for coding agents: Firestore, Auth, Storage, Functions, logs, rules checks.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user firenook-mcp '--' npx -y firenook mcp
# 2 — ask your agent for something these tools do
# firenook_status, firestore_get, firestore_query and 17 more
Firenook costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Firenook as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user firenook-mcp '--' npx -y firenook mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
20 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
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.
No parameter schema on file.
Read one Firestore document by path (collection/document[/subcollection/document]); returns its fields as plain JSON or exists:false.
No parameter schema on file.
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.
No parameter schema on file.
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).
No parameter schema on file.
Write a Firestore document from plain JSON: replaces it, or with merge:true updates only the given top-level fields.
No parameter schema on file.
Delete a document (recursive:true also its subcollections) or a collection (its documents; recursive:true everything beneath) through the emulator delete route.
No parameter schema on file.
List collection ids at the database root or under a document (listCollectionIds).
No parameter schema on file.
List Auth emulator accounts (accounts:batchGet) with uid, email, phone, display name, claims and provider data.
No parameter schema on file.
Look up one Auth account by uid, email or phone number (accounts:lookup).
No parameter schema on file.
Create an Auth emulator account with a synthetic email/password, phone number or display name (never real credentials).
No parameter schema on file.
Delete one Auth emulator account by uid (accounts:delete).
No parameter schema on file.
The pending out-of-band codes (email verification, password reset, sign-in links) the Auth emulator holds instead of sending email.
No parameter schema on file.
The pending phone verification codes the Auth emulator holds instead of sending SMS.
No parameter schema on file.
List Storage objects and folder prefixes under a prefix (one level, like listAll).
No parameter schema on file.
The metadata of one Storage object (content type, size, timestamps, custom metadata, download tokens) or exists:false.
No parameter schema on file.
The functions loaded by the running suite: name, region, generation, trigger kind, event type or schedule, and the HTTPS URL of request/callable functions.
No parameter schema on file.
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.
No parameter schema on file.
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.
No parameter schema on file.
Queue statistics of the Cloud Tasks emulator (queueStats).
No parameter schema on file.
Export the running Firestore, Auth and Storage data to a directory outside the project (firenook emulators:export).
No parameter schema on file.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Firenook or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (20 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| firenook_status | no tags | |
| firestore_get | no tags | |
| firestore_query | no tags | |
| firestore_count | no tags | |
| firestore_set | no tags | |
| firestore_delete | no tags | |
| firestore_list_collections | no tags | |
| auth_list_users | no tags | |
| auth_get_user | no tags | |
| auth_create_user | no tags | |
| auth_delete_user | no tags | |
| auth_oob_codes | no tags | |
| auth_verification_codes | no tags | |
| storage_list | no tags | |
| storage_get_metadata | untrusted-input | untrusted-input: keyword "download" |
| functions_list | no tags | |
| functions_invoke | no tags | |
| pubsub_publish | no tags | |
| tasks_stats | no tags | |
| emulators_export | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.2.5. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
No release note was published with this version.
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Firenook can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.