How to Use the Feedly MCP in LlamaIndex

Q: How do I connect the Feedly MCP Server to my LlamaIndex pipeline?

Use llama-index-tools-mcp to initialize BasicMCPClient with the Vinkius URL. Convert the connection to tools using McpToolSpec and pass them to your FunctionAgent.

Q: Can LlamaIndex index historical articles from my Feedly boards?

Yes. LlamaIndex can run getboardcontents to fetch past entries from your saved boards. It then chunks and indexes this text so you can query historical data.

Q: How does LlamaIndex handle token limits when reading large Feedly streams?

The framework chunks the text returned by getstreamcontents before embedding it. This prevents your LLM from hitting context window limits when reading massive RSS feeds.

Q: Can I filter which Feedly tools LlamaIndex can access?

Yes, you can use the allowedtools filter during setup. For example, you can restrict the agent to getentry and listcollections while blocking write tools.

Index your Feedly streams directly into LlamaIndex vector stores for semantic search.

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 LlamaIndex

Create your Vinkius account to connect Feedly to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Feedly MCP Server feeds into vector stores

LlamaIndex changes how you consume news by turning raw RSS feeds into searchable vector databases. This Feedly MCP Server pulls articles via `get_stream_contents` and indexes them on the fly. Instead of reading hundreds of unread articles, you query your index. Your agent uses `get_entry` to fetch specific details and updates your knowledge base with fresh context.

Semantic search across your Feedly boards

Stop scrolling through old bookmarks. This Feedly MCP Server uses LlamaIndex to query `list_boards` and `get_board_contents` to build a semantic map of your saved articles. You can ask your agent about specific trends, and it will search your curated boards instead of pulling generic web results. Your retrieval stays grounded in sources you actually trust.

Ground RAG applications in your curated subscriptions

Avoid hallucinations by forcing your LLM to answer using your actual Feedly subscriptions. This Feedly MCP Server exposes `get_subscriptions` so LlamaIndex knows exactly which feeds to query. If a topic is missing, the agent runs `search_topics` to find relevant articles and ingest them. You get a self-updating knowledge base that grows as you track industry news.

Setup guide

Set up Feedly MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Feedly MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Feedly tools.",
)
response = await agent.run("List recent Feedly data")

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 LlamaIndex

Use `llama-index-tools-mcp` to initialize `BasicMCPClient` with the Vinkius URL. Convert the connection to tools using `McpToolSpec` and pass them to your `FunctionAgent`.

Yes. LlamaIndex can run `get_board_contents` to fetch past entries from your saved boards. It then chunks and indexes this text so you can query historical data.

The framework chunks the text returned by `get_stream_contents` before embedding it. This prevents your LLM from hitting context window limits when reading massive RSS feeds.

Yes, you can use the `allowed_tools` filter during setup. For example, you can restrict the agent to `get_entry` and `list_collections` while blocking write tools.

Vinkius isolates the connector execution to prevent leaks. Your Feedly developer token and the RSS article indexes built by LlamaIndex are handled in memory and never stored on persistent Vinkius disks.

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