How to Use the Firebase (REST & Admin APIs) MCP in CrewAI

Q: How do I configure CrewAI to use the Firebase (REST & Admin APIs) tools?

Install crewai and pass your Vinkius server URL in the mcps array of your Agent configuration. For finer control, use MCPServerHTTP to filter specific tools.

Q: Can different CrewAI agents access different Firebase (REST & Admin APIs) tools?

Yes. You can use a tool filter to expose firestorelistdocs to your research agent while restricting firestoredeletedoc to your moderator agent.

Q: How do CrewAI agents share data retrieved from Firebase (REST & Admin APIs)?

Agents use CrewAI's shared memory. When one agent runs rtdbget, the retrieved JSON payload is stored in the crew's memory, making it accessible to other agents in subsequent tasks.

Run autonomous multi-agent teams to manage your Firebase (REST & Admin APIs) databases and user accounts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firebase (REST & Admin APIs) MCP to CrewAI

Create your Vinkius account to connect Firebase (REST & Admin APIs) to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Firebase (REST & Admin APIs) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative database auditing using this MCP Server

`firestore_list_docs` lets a research agent scan your collections for outdated or malformed records. Once identified, a moderator agent uses `firestore_patch_doc` to apply the necessary corrections. This team-based approach keeps your production data clean. By separating the scanning and editing roles, you reduce the risk of accidental batch deletions or corrupted fields.

Realtime Database state synchronization

`rtdb_get` allows a monitoring agent to pull the current state of your live database. If the agent detects an anomaly, it passes the data to a coordinator agent to make decisions. The coordinator then runs `rtdb_put` to overwrite the incorrect state. This feedback loop runs entirely in the background without needing human intervention.

Automated user escalation and notification

`auth_lookup` helps a support agent verify a customer's account status when a ticket is opened. If the agent finds an issue, it coordinates with a notification agent to alert the user. The notification agent then triggers `fcm_send_message` to send a push notification directly to the user's device, resolving the support loop autonomously.

Setup guide

Set up Firebase (REST & Admin APIs) MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Firebase (REST & Admin APIs) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Firebase (REST & Admin APIs) Analyst",
    goal="Access and analyze Firebase (REST & Admin APIs) data via MCP.",
    backstory="Expert analyst with direct Firebase (REST & Admin APIs) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Firebase (REST & Admin APIs) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Firebase (REST & Admin APIs) Analyst",
        goal="Access and analyze Firebase (REST & Admin APIs) data via MCP.",
        backstory="Expert analyst with direct Firebase (REST & Admin APIs) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Firebase (REST & Admin APIs) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Firebase. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Firebase (REST & Admin APIs) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Firebase (REST & Admin APIs) MCP in CrewAI

Install `crewai` and pass your Vinkius server URL in the `mcps` array of your Agent configuration. For finer control, use `MCPServerHTTP` to filter specific tools.

Yes. You can use a tool filter to expose `firestore_list_docs` to your research agent while restricting `firestore_delete_doc` to your moderator agent.

Agents use CrewAI's shared memory. When one agent runs `rtdb_get`, the retrieved JSON payload is stored in the crew's memory, making it accessible to other agents in subsequent tasks.

The agent will log the error and can use its self-healing capabilities to retry the operation or escalate the failure to another agent in the crew.

All interactions with your Firebase user records and Firestore documents run through Vinkius's secure, ephemeral V8 sandboxes. Your credentials are never persisted on disk, keeping your customer data safe.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript