How to Use the Salsa Engage MCP in CrewAI

Q: How do I connect CrewAI to my Salsa Engage database?

You pass your Vinkius MCP URL directly into the mcps array when defining your CrewAI agents. The agents auto-detect tools like listsupporters and use them to query your database during their runs.

Q: Can I limit which Salsa Engage tools a CrewAI agent can use?

Yes. You can use the MCPServerHTTP class from crewai.mcp and apply a toolfilter. This lets you restrict your research agent to read-only tools like listsupportergroups while keeping write tools locked down.

Run autonomous agent crews using CrewAI to analyze Salsa Engage donor data and manage supporter groups.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salsa Engage MCP to CrewAI

Create your Vinkius account to connect Salsa Engage 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 Salsa Engage with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous donor management with CrewAI

The `list_supporters` tool gives your CrewAI research agent immediate access to your entire donor database. The researcher scans these profiles to identify trends, then hands the structured data over to an analyst agent. This teamwork happens completely in the background without you writing custom glue code. Once the analyst agent spots a trend, a coordinator agent uses `assign_supporters_to_group` to organize those donors. Because CrewAI agents share memory, the coordinator knows exactly which profiles the researcher flagged. Your supporter lists stay updated based on actual behavior.

Multi-agent fundraising reporting via CrewAI MCP Server

The `get_engagement_metrics` tool provides the raw financial data your CrewAI analyst agent needs to build reports. The analyst processes these metrics alongside campaign goals to evaluate performance. At the same time, a writer agent drafts summaries based on these findings for your board meetings. To make sure offline efforts aren't missed, the crew runs `list_offline_donations` to pull manual transaction records. Combining these offline numbers with your digital metrics gives you a single, unified view of your fundraising health. It eliminates gaps in your reporting.

Keep your Salsa Engage database clean with CrewAI

The `check_api_health` tool is used by your CrewAI monitor agent to verify connection status before starting a run with this MCP Server. If the API is clear, the crew proceeds with database cleanup tasks. This prevents agents from wasting execution cycles on dead connections. During the cleanup run, the crew uses `upsert_supporter_profile` to merge duplicate records or update outdated contact details. An inspector agent reviews the changes before they are committed, ensuring your data remains accurate. It acts as an automated QA team for your donor database.

Setup guide

Set up Salsa Engage 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 Salsa Engage tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass your Vinkius MCP URL directly into the `mcps` array when defining your CrewAI agents. The agents auto-detect tools like `list_supporters` and use them to query your database during their runs.

Yes. You can use the `MCPServerHTTP` class from `crewai.mcp` and apply a `tool_filter`. This lets you restrict your research agent to read-only tools like `list_supporter_groups` while keeping write tools locked down.

CrewAI agents use shared memory to pass information. One agent can run `list_engagement_activities` to find active donors, and then pass those specific donor IDs to a second agent that runs `assign_supporters_to_group`.

The crew manages rate limits by coordinating agent execution. You can configure your crew's max RPM or use the `check_api_health` tool to pause operations if the server detects heavy traffic.

Your supporter profiles and engagement metrics are handled securely by the Salsa Engage MCP Server via Vinkius's ephemeral V8 sandboxes. Your API keys are managed securely on the server side, so your CrewAI scripts never touch raw credentials.

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