How to Use the GitBook MCP in CrewAI

Q: Does CrewAI support searching across multiple GitBook spaces?

Yes, your CrewAI research agent can use listspaces to find all spaces, then loop through them using searchcontent. The shared memory allows other agents in the crew to immediately analyze the results.

Deploy specialized agent crews to audit your GitBook spaces with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitBook MCP to CrewAI

Create your Vinkius account to connect GitBook 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 GitBook with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate GitBook audits using a CrewAI team

The `list_pages` tool allows your CrewAI research agent to map out the entire GitBook documentation tree. This agent then hands the GitBook page IDs over to a CrewAI writer agent for deeper analysis. By dividing the GitBook work, your CrewAI team avoids hitting rate limits while processing large spaces. This team-based approach ensures thorough verification of every single GitBook document.

Aggregate GitBook metrics with an MCP Server

The `list_organizations` tool provides your CrewAI manager agent with a high-level view of your GitBook workspace structure. Your CrewAI team uses this data to delegate auditing tasks across different business units. This setup lets you run parallel audits across multiple GitBook teams. Your CrewAI agents coordinate through shared memory to avoid duplicating efforts on the same GitBook spaces.

Cross-reference GitBook content automatically with CrewAI

The `search_content` tool lets your CrewAI quality assurance agent find duplicate topics across different GitBook guides. The CrewAI agent queries your spaces to flag conflicting instructions. Once duplicates are found, the CrewAI agent uses `get_page` to pull the raw GitBook text and compare them. Your CrewAI team then generates a clean report detailing exactly which GitBook pages need consolidation.

Setup guide

Set up GitBook 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 GitBook tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You configure the server URL directly in your Python script using the `mcps` parameter. This automatically registers tools like `get_page` and `list_pages` for your crew.

No, this MCP Server only supports read operations. Your agents can identify issues using `get_page` but must output their recommendations to a local file or ticketing system.

You should assign specific tools to specialized agents rather than giving every agent access to all tools. For example, let only one agent use `get_page` to control the request rate.

Yes, your CrewAI research agent can use `list_spaces` to find all spaces, then loop through them using `search_content`. The shared memory allows other agents in the crew to immediately analyze the results.

All communication goes through encrypted transport layers. Your organization lists, space structures, and page contents are processed strictly in memory and are never persisted or logged.

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