How to Use the Glean MCP in CrewAI

Q: Can a CrewAI agent search for specific people in Glean?

Yes. Your HR agent can call searchpeople to find employee profiles, roles, and contact details. This allows the crew to automatically route questions to the correct team lead.

Q: How do I limit which Glean tools CrewAI can use on this MCP Server?

You use the MCPServerHTTP class from crewai.mcp and set a toolfilter. This restricts your agents to safe tools like search while blocking destructive tools like deletedocument.

Q: How do I verify that my crew can reach the server?

You trigger checkgleanstatus before starting your crew's task execution. This ensures that your autonomous agents don't waste API tokens trying to search an offline workspace index.

Deploy specialized teams of agents to search and index workspace data using CrewAI and Glean.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glean MCP to CrewAI

Create your Vinkius account to connect Glean 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 Glean with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent research using this MCP Server

This setup uses `search` to let your CrewAI research agents dig up historical project files. A specialized researcher agent queries your workspace, while an analyst agent synthesizes the results into a single report. The agents share a common memory space. This means the analyst agent can read the output of `get_document` fetched by the researcher without needing to query the server again.

CrewAI agents manage your document collections

This system runs `list_collections` to let a moderator agent audit your company's knowledge base. The agent identifies empty or outdated collections and uses `delete_document` to prune them automatically. You establish strict guardrails for these operations. A monitor agent watches the session and can halt the crew if it attempts to delete files from restricted directories.

Index new files with specialized agent validation

This MCP capability uses `index_document` to register newly created files into your organization's search index. Before indexing, a CrewAI editor agent checks the file for formatting, while a compliance agent ensures no sensitive keys are written. Once approved, the writer agent calls the indexing tool. This multi-step validation prevents dirty or non-compliant data from polluting your search results.

Setup guide

Set up Glean 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 Glean tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the server URL directly into your CrewAI Agent definition using the `mcps` parameter. The agent automatically discovers tools like `search` and uses them when researching tasks.

Yes. Your HR agent can call `search_people` to find employee profiles, roles, and contact details. This allows the crew to automatically route questions to the correct team lead.

You use the `MCPServerHTTP` class from `crewai.mcp` and set a `tool_filter`. This restricts your agents to safe tools like `search` while blocking destructive tools like `delete_document`.

You trigger `check_glean_status` before starting your crew's task execution. This ensures that your autonomous agents don't waste API tokens trying to search an offline workspace index.

Your internal documents and wiki entries are protected by Vinkius's zero-trust architecture. The MCP Server executes in an ephemeral V8 sandbox, ensuring your private corporate knowledge never leaves your secure infrastructure.

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