How to Use the Sally MCP in CrewAI

Q: Can I restrict which Sally tools my CrewAI agents use?

You apply a toolfilter when setting up the server connection. That lets you give the reporting agent access to timesheets while blocking it from creating tasks. Role-based specialization keeps your crew disciplined.

Deploy autonomous CrewAI agents to manage your Sally frontline workforce through this MCP integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sally MCP to CrewAI

Create your Vinkius account to connect Sally to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sally with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Autonomous Project Management

Calling `list_projects` lets your planner agent map out the current workload across the workspace. CrewAI shares this state in memory so the execution agent knows exactly what to do next. The system identifies missing steps by analyzing the output of `get_task`. A separate dispatcher agent takes over to run `create_task` for unassigned work. It sets the labels and P1-P4 priorities based on rules you established. Your crew handles the entire shift setup while you focus on higher-level strategy.

Multi-Agent Labor Audits

Fetching `get_timesheet_report` feeds raw hours to your analyst agent. This agent crunches the numbers to find overtime violations or understaffed shifts. It hands the compiled data to a reporting agent for final review. Before running these heavy queries, a monitor agent fires `check_sally_health`. It verifies the instance is responsive before the rest of the crew starts pulling data. Hierarchical execution means dependencies get checked first.

Sally MCP Server Communication

Running `get_board` gives your moderator agent a full view of the Kanban columns. It reads the status of every job to understand where deskless workers are stuck. The agent spots stalled items and decides if intervention is necessary. When a worker needs guidance, the agent uses `add_comment` to drop instructions directly into the task. The frontline team gets immediate answers without waiting for a human manager. Specialized roles mean one agent only watches while another only speaks.

Setup guide

Set up Sally 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 Sally tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your endpoint URL directly into the mcps array when defining your Agent. You can also use MCPServerHTTP from crewai.mcp for more granular control. It supports stdio, SSE, and Streamable HTTP out of the box.

You apply a tool_filter when setting up the server connection. That lets you give the reporting agent access to timesheets while blocking it from creating tasks. Role-based specialization keeps your crew disciplined.

The framework's internal memory catches the failure and prompts the agent to try a different approach. If update_task rejects a bad status code, the agent reads the error and corrects its payload. Autonomous execution means it fixes its own mistakes.

Each agent maintains its own session based on the tools you assigned it. They communicate findings through CrewAI's shared memory rather than hitting the API twice. That reduces load on the server.

Authenticated user profiles and job assignments exist only within the ephemeral runtime environment. Vinkius manages the authentication layer so you never hardcode credentials into your Python scripts. Once the crew finishes its run, the memory wipes clean.

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