Firebase MCP Server
Enables interaction with Firebase projects and services, including deployment, database management, authentication, and local emulation, through natural language.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
firebase
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
form-data uses unsafe random function in form-data for choosing boundary
node-tar: Decompression/parse DoS via unlimited input
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
body-parser vulnerable to denial of service when url encoding is enabled
AI_AGENTEXT_INSTANCE_IDFIREBASE_FUNCTIONS_DISCOVERY_OUTPUT_PATHFIREBASE_MCP_DEBUG_LOGGOOGLE_APPLICATION_CREDENTIALSthat we pass into the emulator through . We only do thisGOOGLE_CLOUD_PROJECTGREETINGPROJECT_ROOT__FIREBASE_DEFAULTS____FIREBASE_FRAMEWORKS_ENTRY____NEXT_REACT_ROOTDependencies
157 dependencies, 1 flagged: puppeteer
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
5/5 tools missing one or more hints — allowed_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); disallowed_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); test_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +2 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Shell command execution
23 child_process/subprocess calls in production code — runs shell commands (src/frameworks/index.ts:480, src/frameworks/index.ts:533, src/frameworks/angular/index.ts:55)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
2 critical, 12 high severity in production deps — form-data@4.0.1 (critical), tar@7.5.11 (critical)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
8 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Dependency freshness
11/70 production deps abandoned (no release in 2+ years): exegesis-express@2022-05-01 (4.3y), cjson@2022-06-13 (4.2y), fuzzy@2022-06-18 (4.2y)
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/firebase-firebase-tools-1b9j2c)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check