Omnivore (Read-Later) MCP Server for LlamaIndexGive LlamaIndex instant access to 4 tools to Get Article, Get Me, Save Url, and more
GDPR Free for SubscribersLlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Omnivore (Read-Later) as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.
Ask AI about this MCP Server for LlamaIndex
The Omnivore (Read-Later) MCP Server for LlamaIndex is a standout in the Productivity category — giving your AI agent 4 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
Geminiimport asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
mcp_tool_spec = McpToolSpec(client=mcp_client)
tools = await mcp_tool_spec.to_tool_list_async()
agent = FunctionAgent(
tools=tools,
llm=OpenAI(model="gpt-4o"),
system_prompt=(
"You are an assistant with access to Omnivore (Read-Later). "
"You have 4 tools available."
),
)
response = await agent.run(
"What tools are available in Omnivore (Read-Later)?"
)
print(response)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Omnivore (Read-Later) MCP Server
Connect your Omnivore account to any AI agent to organize your reading list and extract knowledge from saved articles using natural language.
LlamaIndex agents combine Omnivore (Read-Later) tool responses with indexed documents for comprehensive, grounded answers. Connect 4 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
What you can do
- Search & Filter — Use the
search_articlestool to find content using labels, folders, or read status (e.g., 'is:unread label:AI') - Full Content Retrieval — Use
get_articleto fetch the complete text, author, and labels for deep analysis or summarization - Quick Saving — Use
save_urlto instantly add new web links to your library without leaving your conversation - User Profile — Use
get_meto verify your account details and connection status
The Omnivore (Read-Later) MCP Server exposes 4 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
All 4 Omnivore (Read-Later) tools available for LlamaIndex
When LlamaIndex connects to Omnivore (Read-Later) through Vinkius, your AI agent gets direct access to every tool listed below — spanning read-it-later, content-curation, bookmarking, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.
Get article on Omnivore (Read-Later)
Get full content of a specific article
Get me on Omnivore (Read-Later)
Get current Omnivore user details
Save url on Omnivore (Read-Later)
Save a URL to Omnivore library
Search articles on Omnivore (Read-Later)
g., label:Newsletter, in:inbox, is:unread, has:highlights) to find articles. Search and filter articles in Omnivore library
Connect Omnivore (Read-Later) to LlamaIndex via MCP
Follow these steps to wire Omnivore (Read-Later) into LlamaIndex. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.
Install dependencies
pip install llama-index-tools-mcp llama-index-llms-openaiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
agent.py and run: python agent.pyExplore tools
Why Use LlamaIndex with the Omnivore (Read-Later) MCP Server
LlamaIndex provides unique advantages when paired with Omnivore (Read-Later) through the Model Context Protocol.
Data-first architecture: LlamaIndex agents combine Omnivore (Read-Later) tool responses with indexed documents for comprehensive, grounded answers
Query pipeline framework lets you chain Omnivore (Read-Later) tool calls with transformations, filters, and re-rankers in a typed pipeline
Multi-source reasoning: agents can query Omnivore (Read-Later), a vector store, and a SQL database in a single turn and synthesize results
Observability integrations show exactly what Omnivore (Read-Later) tools were called, what data was returned, and how it influenced the final answer
Omnivore (Read-Later) + LlamaIndex Use Cases
Practical scenarios where LlamaIndex combined with the Omnivore (Read-Later) MCP Server delivers measurable value.
Hybrid search: combine Omnivore (Read-Later) real-time data with embedded document indexes for answers that are both current and comprehensive
Data enrichment: query Omnivore (Read-Later) to augment indexed data with live information before generating user-facing responses
Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Omnivore (Read-Later) for fresh data
Analytical workflows: chain Omnivore (Read-Later) queries with LlamaIndex's data connectors to build multi-source analytical reports
Example Prompts for Omnivore (Read-Later) in LlamaIndex
Ready-to-use prompts you can give your LlamaIndex agent to start working with Omnivore (Read-Later) immediately.
"Search my Omnivore library for unread articles about 'Machine Learning'."
"Fetch the full content of the article with slug 'mcp-guide' for username 'alex_dev'."
"Save the URL 'https://blog.omnivore.app/p/getting-started' to my library."
Troubleshooting Omnivore (Read-Later) MCP Server with LlamaIndex
Common issues when connecting Omnivore (Read-Later) to LlamaIndex through Vinkius, and how to resolve them.
BasicMCPClient not found
pip install llama-index-tools-mcpOmnivore (Read-Later) + LlamaIndex FAQ
Common questions about integrating Omnivore (Read-Later) MCP Server with LlamaIndex.
How does LlamaIndex connect to MCP servers?
Can I combine MCP tools with vector stores?
Does LlamaIndex support async MCP calls?
Explore More MCP Servers
View all →
Bidsketch
10 toolsAutomate proposal creation via Bidsketch — list proposals, clients, and templates directly from any AI agent.
MailboxPower
9 toolsDelight contacts with personalized physical gifts, greeting cards, and direct mail sent automatically from your CRM.
Mattermark
10 toolsStartup and venture capital data via Mattermark — search companies, investors, and funding rounds.
Routific
10 toolsConnect your AI assistant to Routific to solve complex vehicle routing problems, dispatch drivers, and manage global delivery timelines natively through chat.