How to Use the Feedly MCP in CrewAI

Q: Can CrewAI agents collaborate on Feedly stream analysis?

They can. One agent retrieves the stream with getstreamcontents, and the rest of the crew analyzes the content based on their assigned roles.

Q: Is it possible to limit which Feedly tools a CrewAI agent can use?

Yes. You use the toolfilter option in your CrewAI setup to restrict agents to read-only tools like getentry if you want to prevent accidental deletions.

Deploy autonomous research crews using this Feedly MCP Server for CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Feedly MCP to CrewAI

Create your Vinkius account to connect Feedly 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 Feedly with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous research crews for CrewAI

Assign a research agent to use `get_stream_contents` while a monitor agent watches for specific keywords. They share context to decide what's worth your time. It acts like a dedicated research team that never sleeps. They filter the noise so you only see the signal.

Cross-reference topics with Feedly

Use `search_topics` to find fresh perspectives on your current projects. Your CrewAI agents pull this data and synthesize it into a briefing. It keeps your research grounded in current events. The agent finds the context, and your crew builds the narrative.

Systematic archive management

Give your CrewAI agents permission to `list_boards` and `get_entry` to organize your research. They can move items between boards based on the project phase. It automates the organization of your reading material. You stop manually filing articles and start reading the finished summary.

Setup guide

Set up Feedly 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 Feedly tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You add the server URL to the agent's MCP list. CrewAI handles the connection and exposes all 12 tools to the crew.

They can. One agent retrieves the stream with `get_stream_contents`, and the rest of the crew analyzes the content based on their assigned roles.

Yes. You use the tool_filter option in your CrewAI setup to restrict agents to read-only tools like `get_entry` if you want to prevent accidental deletions.

You should implement a local queue to throttle the number of concurrent requests. This prevents your crew from hitting the API limits during heavy search tasks.

The token is injected at the server level through environment variables. It is never exposed to the agents themselves or logged in your session history.

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