How to Use the Lattice MCP in CrewAI

Q: How do I configure the Lattice MCP Server inside CrewAI?

Pass your Vinkius HTTP URL directly into the mcps list of your CrewAI Agent definition. This automatically exposes tools like listusers and listtasks to that specific agent.

Q: How do CrewAI agents share Lattice user data between themselves?

Agents use CrewAI's shared memory. When one agent calls getuser, the retrieved employee details are shared across the crew, preventing duplicate API calls to your HR directory.

Coordinate autonomous HR agents using CrewAI and the Lattice MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lattice MCP to CrewAI

Create your Vinkius account to connect Lattice 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 Lattice with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run collaborative HR reviews using CrewAI

Your CrewAI agents can use `list_feedback` and `list_goals` simultaneously to build complete performance profiles by splitting the work across specialized roles. Assign one agent to compile feedback and another to analyze goals. A third coordinator agent inside your CrewAI setup evaluates the combined Lattice data to flag high performers automatically. It mimics a real HR ops team, running autonomously without manual intervention.

Track pending Lattice tasks with CrewAI agents

Your CrewAI agents can poll `list_tasks` to identify overdue self-evaluations or pending manager approvals before deadlines slip. Don't let critical review deadlines slip through the cracks of busy schedules. Once found, a specialized escalation agent inside CrewAI looks up the employee's manager using `get_user` and drafts a direct Slack nudge. It keeps your review cycles moving on autopilot.

Feed Lattice feedback into CrewAI agent memory

By querying `get_feedback` and `list_users`, your crew builds a temporary memory bank of Lattice team dynamics and past praise. This gives your agents deep organizational context before they execute tasks. This context allows your CrewAI analysis agents to write highly specific summaries of an employee's contributions when evaluating active `list_reviews` cycles. It replaces generic summaries with actual data.

Setup guide

Set up Lattice 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 Lattice tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius HTTP URL directly into the `mcps` list of your CrewAI Agent definition. This automatically exposes tools like `list_users` and `list_tasks` to that specific agent.

No. The tools provided are strictly read-only, meaning your crew can query `list_feedback` and `get_feedback` but cannot create new entries or edit existing ones.

Agents use CrewAI's shared memory. When one agent calls `get_user`, the retrieved employee details are shared across the crew, preventing duplicate API calls to your HR directory.

Yes. A manager agent can coordinate subordinate agents, delegating tasks like calling `list_goals` to one agent while another gathers data via `list_reviews` before compiling the final report.

Your employee directories and performance goals remain private. The server runs inside an ephemeral, isolated container, ensuring that data retrieved via `get_user` or `list_goals` is processed in-memory and never cached on disk.

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