Does this tool parse the document directly or use the cloud engine?

The tool offloads the logic specifically via endpoints mapping back to the Parseur Cloud Engine. The AI acts to organize mailboxes, list templates, and fetch final states securely without computing massive local OCR networks.

Can I upload a raw file string to be parsed?

Yes. Utilizing the explicitly mapped `upload_document` constraint, the agent can inject raw string boundaries identifying formatting, passing files straightforward into the target mailbox ID natively.

Will I see missing required fields if extraction fails?

Absolutely. Querying `get_document_details` lists specific status bounds. If a template expects InvoiceTotal and misses it, the document flags a processing boundary issue precisely traceable here.

Parseur MCP Server for CrewAI 10 tools — connect in under 2 minutes

Name: Parseur
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 10 Tools Framework

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

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Parseur Specialist",
    goal="Help users interact with Parseur effectively",
    backstory=(
        "You are an expert at leveraging Parseur 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 Parseur "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 10 available tools "
        "and what they can do."
    ),
)

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

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 Parseur MCP Server

Bring Parseur Document Extraction arrays directly into your AI workflows. By explicitly mapping into powerful OCR and templating engines, your agent can push unstructured PDFs or bulk emails into remote routing limits, parsing exact text fields securely. Extract fields, examine documents, list defined parse-templates, and retry pipelines without manual intervention.

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

What you can do

Mailboxes & Templates — Examine specifically bound mailboxes tracking which explicit templates dictate data extraction limits mapped natively
Document Navigation — Extract properties showing precisely which unstructured strings were identified inside uploaded payloads checking status: parsed correctly
Payload Uploading — Instruct the node limits mapping upload_document generating raw payloads routing straight into the engine for OCR logic
Job Management — Discover disconnected states mitigating failed validations by pushing retry_document instantly forcing physical pipeline resets

The Parseur MCP Server exposes 10 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Parseur to CrewAI via MCP

Follow these steps to integrate the Parseur MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

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

Customize the agent

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

Run the crew

Run python crew.py — CrewAI auto-discovers 10 tools from Parseur

Why Use CrewAI with the Parseur MCP Server

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

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

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

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

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

Parseur + CrewAI Use Cases

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

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

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

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

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

Parseur MCP Tools for CrewAI (10)

These 10 tools become available when you connect Parseur to CrewAI via MCP:

create_mailbox

The type determines the parsing engine (e.g., "pdf", "email", "attachment"). Once created, you can configure templates and forward documents to the mailbox for automatic extraction. Create a new Parseur mailbox for document parsing

create_template

Pass the template name and a JSON config string defining field mappings. Parseur will use this template to extract structured data from matching documents. Create a new extraction template for a Parseur mailbox

get_document_data

Fields depend on the template configuration (e.g., invoice_number, total_amount, line_items). Only works for documents with status "processed". Retrieve the fully extracted JSON data from a parsed document

get_document_details

Does not include the parsed data itself — use get_document_data for that. Get metadata of a single parsed document

get_mailbox

Use this to verify mailbox setup before sending documents. Get detailed configuration of a specific Parseur mailbox

list_documents

Each entry includes document ID, status (processed, failed, pending), and metadata like sender and received date. List all parsed documents inside a Parseur mailbox

list_mailboxes

Each mailbox represents a parsing pipeline for a specific document type (invoices, receipts, emails). Use the returned mailbox IDs for subsequent operations like listing documents or uploading files. List all Parseur parsing mailboxes

list_templates

Templates define the extraction rules (field names, locations, regex patterns) used to pull structured data from incoming documents. List available extraction templates for a Parseur mailbox

retry_document

Useful after fixing template rules or when the original parse failed due to a transient error. The document will be matched against the latest template rules. Retry parsing a failed or errored Parseur document

upload_document

eml) to the specified mailbox for automatic parsing. The document enters the processing queue and will be parsed according to the mailbox template. Returns the new document ID for tracking. Upload a document URL to a Parseur mailbox for parsing

Example Prompts for Parseur in CrewAI

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

"Check my Parseur mailboxes to find the specific bounding IDs."

"Get the data schema parsed tightly inside document doc_987."

"Upload this snippet of parsed text directly into Mailbox xyz12 for OCR processing."

Troubleshooting Parseur MCP Server with CrewAI

Common issues when connecting Parseur to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

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

Agent not using tools

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

Timeout errors

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

Rate limiting or 429 errors

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

Parseur + CrewAI FAQ

Common questions about integrating Parseur MCP Server with CrewAI.

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.

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.

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.

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.

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.