4,000+ servers built on vurb.ts
Vinkius
Unlock for AI Agents

Scale AI MCP Server for CrewAIGive CrewAI instant access to 11 tools to Cancel Task, Create Batch, Create Image Annotation Task, and more

MCP Inspector GDPR Free for Subscribers

Connect your CrewAI agents to Scale AI through Vinkius, pass the Edge URL in the `mcps` parameter and every Scale AI tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Ask AI about this MCP Server for CrewAI

Open in ChatGPT Open in Claude Open in Perplexity

The Scale AI MCP Server for CrewAI is a standout in the Ai Frontier category — giving your AI agent 11 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
python
from crewai import Agent, Task, Crew

agent = Agent(
    role="Scale AI Specialist",
    goal="Help users interact with Scale AI effectively",
    backstory=(
        "You are an expert at leveraging Scale AI tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Scale AI "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 11 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)
Scale AI
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Scale AI MCP Server

Connect your Scale AI account to any AI agent to orchestrate large-scale data labeling and fine-tuning pipelines through natural conversation.

When paired with CrewAI, Scale AI becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Scale AI tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

What you can do

  • Project Management — Create and configure projects for specific labeling types like image annotation or semantic segmentation.
  • Batch Operations — Organize high-volume work into batches and finalize them to trigger the labeling process.
  • Multi-Modal Tasks — Submit tasks for Image Annotation, Semantic Segmentation, and Video Playback directly via API.
  • Task Lifecycle — Retrieve detailed status of individual tasks or cancel pending ones to manage your budget and throughput.
  • Parameter Tuning — Update project-level instructions and parameters dynamically to refine labeling quality.

The Scale AI MCP Server exposes 11 tools through the Vinkius. Connect it to CrewAI in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 11 Scale AI tools available for CrewAI

When CrewAI connects to Scale AI through Vinkius, your AI agent gets direct access to every tool listed below — spanning data-labeling, rlhf, machine-learning, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

cancel

Cancel task on Scale AI

Optionally clears the unique_id to reuse it. Cancel a pending task

create

Create batch on Scale AI

Create a new batch

create

Create image annotation task on Scale AI

Create an Image Annotation task

create

Create named entity recognition task on Scale AI

Create a Named Entity Recognition task

create

Create project on Scale AI

Create a new Scale project

create

Create segment annotation task on Scale AI

Create a Semantic Segmentation task

create

Create text collection task on Scale AI

Create a Text Collection task

create

Create video playback annotation task on Scale AI

Create a Video Annotation task

finalize

Finalize batch on Scale AI

Finalize a batch

get

Get task on Scale AI

Retrieve a specific task

update

Update project params on Scale AI

Update project parameters

Connect Scale AI to CrewAI via MCP

Follow these steps to wire Scale AI into CrewAI. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

01

Install CrewAI

Run pip install crewai
02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
03

Customize the agent

Adjust the role, goal, and backstory to fit your use case
04

Run the crew

Run python crew.py. CrewAI auto-discovers 11 tools from Scale AI

Why Use CrewAI with the Scale AI MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Scale AI through the Model Context Protocol.

01

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

02

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

03

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

04

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Scale AI + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Scale AI MCP Server delivers measurable value.

01

Automated multi-step research: a reconnaissance agent queries Scale AI for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

02

Scheduled intelligence reports: set up a crew that periodically queries Scale AI, analyzes trends over time, and generates executive briefings in markdown or PDF format

03

Multi-source enrichment pipelines: chain Scale AI tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

04

Compliance and audit automation: a compliance agent queries Scale AI against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Example Prompts for Scale AI in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Scale AI immediately.

01

"Create a new image annotation project called 'Lidar-Obstacles' for imageannotation."

02

"Submit an image annotation task to project 'Lidar-Obstacles' with the image URL 'https://example.com/car.jpg'."

03

"Finalize the batch named 'sprint-01-batch'."

Troubleshooting Scale AI MCP Server with CrewAI

Common issues when connecting Scale AI to CrewAI through Vinkius, and how to resolve them.

01

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.
02

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".
03

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.
04

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Scale AI + CrewAI FAQ

Common questions about integrating Scale AI MCP Server with CrewAI.

01

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.
02

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.
03

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.
04

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.
05

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.

Explore More MCP Servers

View all →
Clubspeed

Clubspeed

8 tools

Manage entertainment venues and bookings via Clubspeed — track customers, monitor reservations, and manage race heats directly from any AI agent.

Indy

Indy

12 tools

Manage your freelance business with proposals, contracts, time tracking, and invoicing that covers the entire client lifecycle.

Commission Factory

Commission Factory

8 tools

Commission Factory is a leading affiliate marketing network in Asia-Pacific. This MCP server allows affiliates and merchants to retrieve transactions, manage programs, and track performance programmatically.

KnowFirst

KnowFirst

10 tools

Query data intelligence — search entities, audit signals, and track market trends.