How to Use the Sensible MCP in CrewAI

Q: Can a CrewAI agent train a new Sensible parser?

Yes. A specialized training agent can call creategolden to upload reference documents. It then uses extracttextfromgolden to analyze coordinates and configure the extraction rules programmatically.

Q: How does CrewAI handle rate limits on the Sensible MCP Server?

Your crew can monitor performance using getextractionstatistics. If rate limits are approached, the manager agent can throttle execution or queue files using async tools like extractfromurl.

Q: Can I run document classification asynchronously in CrewAI?

Yes. Your routing agent can trigger classifyasync on a batch of files. Once the classification completes, the agent polls the status and assigns the parsing tasks to the appropriate crew members.

Deploy a specialized team of CrewAI agents to classify, parse, and audit documents autonomously with the Sensible MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sensible MCP to CrewAI

Create your Vinkius account to connect Sensible to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sensible with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Autonomous document triage with CrewAI

In a multi-agent setup, your triage agent needs to instantly identify incoming files. By giving them access to this MCP Server, the agent can run `classify_sync` to determine if an upload is an invoice, tax form, or contract. It then hands the file off to the correct specialized agent for deep parsing. This division of labor keeps your autonomous operations running smoothly. The receiver agent does not need to know how to parse; it just routes the document, while the parsing agent uses `extract_sync_with_config` to pull the exact data fields required.

Collaborative quality auditing using CrewAI

Errors in document parsing can ruin downstream databases. A CrewAI analyst agent can call `get_extraction_statistics` to monitor daily performance. If accuracy dips, the analyst flags the issue and instructs a developer agent to run `list_configuration_versions` and identify what changed. The developer agent can then use `update_configuration` to fix the layout rules. This continuous feedback loop happens entirely within your crew, keeping your document pipeline accurate without human intervention.

Automated reporting pipelines with this MCP Server

Your operations crew can handle high-volume reporting without writing custom Python scripts. A coordinator agent pulls historical extraction records using `list_extractions`. It then passes the raw data to a reporting agent, which executes `generate_csv` or `generate_excel` to build clean spreadsheets. The final output is automatically uploaded to your storage or emailed to stakeholders. Your CrewAI team manages the entire lifecycle, from raw PDF ingestion to final spreadsheet delivery.

Setup guide

Set up Sensible 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 Sensible tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Agents share extraction results through CrewAI's memory system. One agent calls `extract_sync` to parse the document, and the resulting JSON is passed directly to downstream agents for analysis.

Yes. A specialized training agent can call `create_golden` to upload reference documents. It then uses `extract_text_from_golden` to analyze coordinates and configure the extraction rules programmatically.

Your crew can monitor performance using `get_extraction_statistics`. If rate limits are approached, the manager agent can throttle execution or queue files using async tools like `extract_from_url`.

Yes. Your routing agent can trigger `classify_async` on a batch of files. Once the classification completes, the agent polls the status and assigns the parsing tasks to the appropriate crew members.

Absolutely. The MCP Server acts as a private conduit, and Vinkius processes all document text and extraction payloads in ephemeral memory. No data is stored or used to train public models.

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