How to Use the BlogIn MCP in LlamaIndex

Q: Can I index BlogIn comments for semantic search?

Yes. You can build a pipeline that calls listrecentcomments and indexes the text into a vector store. This lets your LlamaIndex agent search through team feedback to find context on past decisions.

Q: How does LlamaIndex handle updates to BlogIn posts?

You can schedule a vector index refresh that runs listposts to find new content. The agent compares the post IDs with your existing vector store and only indexes the new or updated posts.

Q: Can I limit which MCP tools the agent can use?

Yes, you can use the allowedtools filter when setting up the tool spec. If you only want your agent to read data, you can restrict it to listposts and listinternalpages while blocking write tools.

Q: Does LlamaIndex send my BlogIn wiki pages to third parties?

No, your internal wiki pages and posts retrieved via listinternalpages are processed locally within your pipeline. Vinkius executes the tool calls in a secure, zero-trust sandbox. Your proprietary company knowledge never trains public models.

Index your company's internal updates into LlamaIndex vector stores using this 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 BlogIn MCP to LlamaIndex

Create your Vinkius account to connect BlogIn 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 BlogIn with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index company blogs for semantic search

The `list_posts` tool pulls your entire company blog history so your agent can index it for semantic search. Instead of guessing where information lives, your LlamaIndex pipeline treats your internal blog as a live document store. Your agent uses `get_post_details` to retrieve the full text of specific posts during query time. This grounds your agent's answers in actual company history, eliminating hallucinations about past projects or policy changes.

Query your team directory using this MCP Server

The `list_team_members` tool exposes your entire organizational structure to your RAG application. Your agent queries this list to find subject matter experts based on who wrote what post. By linking team profiles with posts retrieved via `list_posts`, the agent maps expertise across your company. It answers complex questions about who owns specific projects without manual directory lookups.

Build a dynamic RAG pipeline for LlamaIndex

The `list_internal_pages` tool lets your agent index your company's internal wiki pages alongside active blog posts. Your LlamaIndex pipeline automatically updates its vector store whenever a new page is added. The agent uses `list_recent_comments` to track ongoing discussions around these wiki pages. This ensures your knowledge base includes the latest team context and decisions, not just static documentation.

Setup guide

Set up BlogIn 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 BlogIn 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 BlogIn tools.",
)
response = await agent.run("List recent BlogIn 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 BlogIn. 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 BlogIn 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 BlogIn MCP in LlamaIndex

Install llama-index-tools-mcp and initialize the client to expose the MCP tools. Convert the client into a tool spec and pass it to your FunctionAgent. Your agent can then run semantic queries across `list_posts` instantly.

Yes. You can build a pipeline that calls `list_recent_comments` and indexes the text into a vector store. This lets your LlamaIndex agent search through team feedback to find context on past decisions.

You can schedule a vector index refresh that runs `list_posts` to find new content. The agent compares the post IDs with your existing vector store and only indexes the new or updated posts.

Yes, you can use the allowed_tools filter when setting up the tool spec. If you only want your agent to read data, you can restrict it to `list_posts` and `list_internal_pages` while blocking write tools.

No, your internal wiki pages and posts retrieved via `list_internal_pages` are processed locally within your pipeline. Vinkius executes the tool calls in a secure, zero-trust sandbox. Your proprietary company knowledge never trains public 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