How to Use the DocBreach MCP in CrewAI

Q: How does DocBreach search help my CrewAI team?

Your research agent uses docs.search to find specific parameters or settings across a documentation domain. It keeps your CrewAI team focused on the relevant data rather than parsing irrelevant pages.

Q: How do DocBreach tools handle large documentation sites for CrewAI?

You use docs.map to get an index of the site first. This prevents your CrewAI agents from wasting memory on irrelevant pages and helps them target only the necessary sections.

Equip your CrewAI multi-agent teams with real-time documentation access to automate research and operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocBreach MCP to CrewAI

Create your Vinkius account to connect DocBreach 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 DocBreach with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent research with DocBreach

Deploy a research agent in your CrewAI team to find technical sources. `docs.discover` lets the agent find the right documentation site for any library or API. This keeps your team autonomous. One agent researches the docs, while another agent parses the information, allowing the crew to operate without manual oversight.

Parsing documentation with CrewAI

Agents need to read deep documentation. `docs.read` processes technical pages into Markdown, which is the ideal format for CrewAI agents to ingest and summarize. The tool also provides related links. Your agent can follow these links to gather setup instructions or security protocols, building a complete picture of the task at hand.

Structured extraction for automated actions

Your CrewAI agents can act on API endpoints once they understand the schema. `docs.extract` pulls these details from OpenAPI specs so the agent can build valid payloads. This is essential for autonomous operations. By feeding extracted data into the agent's memory, you ensure the crew executes commands that actually match the API requirements.

Setup guide

Set up DocBreach 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 DocBreach tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Your research agent uses `docs.search` to find specific parameters or settings across a documentation domain. It keeps your CrewAI team focused on the relevant data rather than parsing irrelevant pages.

Yes. You can use tool filters in your MCP configuration to ensure only the research-focused agents in your CrewAI team can access `docs.discover` or `docs.map`.

You use `docs.map` to get an index of the site first. This prevents your CrewAI agents from wasting memory on irrelevant pages and helps them target only the necessary sections.

All documentation is processed in an ephemeral sandbox. Your CrewAI team receives the output, but the server does not retain your search history or the documentation content you process.

DocBreach avoids browser rendering, which eliminates the risk of malicious scripts or tracking pixels common in heavy web scrapers. This keeps your CrewAI environment clean and secure.

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