How to Use the Extracta MCP in CrewAI

Q: How do CrewAI agents share Extracta extraction IDs?

Your setup agent calls createextraction and writes the resulting ID to the crew's shared memory. The processing agent then reads this ID to run uploadfileurl on incoming documents.

Q: Can a CrewAI agent update an active Extracta schema?

Yes, a specialized manager agent can call updateextraction to adjust target fields. This allows the crew to adapt to new document structures without restarting the execution.

Q: How do I limit which CrewAI agents can access Extracta tools?

Use the toolfilter option in CrewAI's MCP configuration to assign specific tools to specific agents. For example, give deleteextraction only to your admin agent.

Q: What is the role of getresults in a CrewAI pipeline?

The processing agent uses the MCP server to poll getresults and retrieve the structured JSON payload. Once the data is ready, the agent hands the clean JSON to the analysis agent for final reporting.

Q: How does the Extracta and CrewAI integration protect sensitive documents?

Document URLs processed via uploadfileurl are accessed over secure channels and analyzed inside ephemeral sandboxes on our managed MCP platform. Vinkius ensures that no document metadata or extraction histories persist after your CrewAI session completes its run.

Run multi-agent teams that coordinate document classification and data extraction using CrewAI and this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Extracta MCP to CrewAI

Create your Vinkius account to connect Extracta 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 Extracta with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate document extraction across a CrewAI team

The `create_extraction` tool allows your setup agent to define the exact JSON schema required for a project. Once the schema is set, a separate extraction agent handles the document processing. This division of labor keeps your CrewAI agents focused. The setup agent configures the rules, while the processing agent uses `upload_file_url` to ingest files without mixing responsibilities.

Audit extraction configurations with CrewAI roles

The `view_extraction` tool lets an auditor agent inspect active extraction rules to verify compliance. This agent reviews the schema before any documents are processed by the team. If the auditor agent finds a discrepancy, it instructs a developer agent to run `update_extraction` to fix the schema. This collaborative loop ensures high accuracy before processing high-volume files.

Classify and route files using specialized CrewAI agents

The `create_classification` tool runs inside a triage agent to categorize incoming documents as they arrive. This agent determines if a file is an invoice, contract, or receipt based on your defined schema. After the triage agent calls `get_classification_results`, a coordinator agent assigns the file to the correct specialist. Invoices go to the accounting agent, while legal files route to the compliance agent.

Setup guide

Set up Extracta 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 Extracta tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Extracta 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="Extracta Analyst",
        goal="Access and analyze Extracta data via MCP.",
        backstory="Expert analyst with direct Extracta access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Extracta 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 Extracta. 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 Extracta 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 Extracta MCP in CrewAI

Your setup agent calls `create_extraction` and writes the resulting ID to the crew's shared memory. The processing agent then reads this ID to run `upload_file_url` on incoming documents.

Yes, a specialized manager agent can call `update_extraction` to adjust target fields. This allows the crew to adapt to new document structures without restarting the execution.

Use the `tool_filter` option in CrewAI's MCP configuration to assign specific tools to specific agents. For example, give `delete_extraction` only to your admin agent.

The processing agent uses the MCP server to poll `get_results` and retrieve the structured JSON payload. Once the data is ready, the agent hands the clean JSON to the analysis agent for final reporting.

Document URLs processed via `upload_file_url` are accessed over secure channels and analyzed inside ephemeral sandboxes on our managed MCP platform. Vinkius ensures that no document metadata or extraction histories persist after your CrewAI session completes its run.

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