How to Use the Felt (Collaborative Maps) MCP in CrewAI

Q: Can multiple CrewAI agents collaborate on the same Felt (Collaborative Maps) project?

Yes, they can. One agent can create the map with createmap, and another agent can immediately use that map's ID to add layers and elements, passing the ID through shared memory.

Q: How do I prevent a CrewAI agent from accidentally deleting a Felt (Collaborative Maps) layer?

You should use a toolfilter in your Python setup to exclude deletelayer and deletemap from the tools exposed to untrusted or autonomous agents.

Q: Which Python libraries do I need to connect CrewAI to this server?

You need to install crewai along with crewaitools. This gives you the necessary HTTP and SSE transport classes to connect directly to the managed endpoint.

Deploy specialized agent teams to analyze, build, and style geographic maps using CrewAI and the Felt 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 Felt (Collaborative Maps) MCP to CrewAI

Create your Vinkius account to connect Felt (Collaborative Maps) 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 Felt (Collaborative Maps) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Multi-Agent GIS Tasks via MCP Server

This MCP Server coordinates multi-agent workflows by letting one agent run `create_map` while another validates the layers. One agent shouldn't have to do everything. They share context using CrewAI's memory system. Once the coordinates are found, the Editor Agent calls `add_elements` to populate the map, while a separate QA Agent runs `get_layer` to verify the accuracy.

Automate Map Auditing and Updates

This MCP Server exposes `list_maps` to let auditing agents scan for outdated project boards and coordinate cleanups. Keep your maps fresh without lifting a finger. The crew can execute `delete_element` on stale markers or completely rebuild outdated layers by calling `delete_layer` followed by `create_layer` with fresh datasets. This ensures your team always works with active geographic data.

Restrict Tool Permissions Across Your Crew

This MCP Server allows you to restrict access to sensitive tools like `delete_map` across your agent crew. You don't want every agent in your crew to have destructive permissions. Junior agents can be restricted to read-only tools like `get_map` or low-risk commands like `add_elements`. This prevents rogue agents from accidentally wiping out your entire spatial database.

Setup guide

Set up Felt (Collaborative Maps) 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 Felt (Collaborative Maps) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Felt (Collaborative Maps) 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 Felt. 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 Felt (Collaborative Maps) 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 Felt (Collaborative Maps) MCP in CrewAI

You can pass your Vinkius endpoint URL directly into the agent's `mcps` configuration array. For more control, use `MCPServerHTTP` to filter which mapping tools each agent can access.

Yes, they can. One agent can create the map with `create_map`, and another agent can immediately use that map's ID to add layers and elements, passing the ID through shared memory.

You should use a `tool_filter` in your Python setup to exclude `delete_layer` and `delete_map` from the tools exposed to untrusted or autonomous agents.

You need to install `crewai` along with `crewai[tools]`. This gives you the necessary HTTP and SSE transport classes to connect directly to the managed endpoint.

Your geographic coordinates and map layers are processed in an isolated, ephemeral V8 sandbox. All credentials are encrypted, and data is never stored or used to train models.

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