How to Use the Fibery MCP in LlamaIndex

Q: How do I connect Fibery to LlamaIndex?

Install llama-index-tools-mcp via pip. Initialize the BasicMCPClient with your Vinkius endpoint, convert it using McpToolSpec, and call totoollistasync to get the list of tools for your agent.

Q: Can LlamaIndex index comments from Fibery?

Yes, LlamaIndex can pull discussion history using the getcomments tool. It indexes those comment threads as text nodes so your RAG pipeline can search past team discussions.

Q: How does LlamaIndex handle custom fields in Fibery?

The agent uses getschema to discover custom field definitions. LlamaIndex reads this schema to understand how to structure its queries and format new entities when calling createentity.

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

Yes, you can use the allowedtools filter when configuring your McpToolSpec. This lets you restrict your agent to read-only operations like queryentities if you want to prevent automated modifications.

Build RAG pipelines that index your Fibery workspace data and query it directly using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fibery MCP to LlamaIndex

Create your Vinkius account to connect Fibery 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 Fibery with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Fibery data into LlamaIndex

This integration uses `query_entities` and `get_comments` to pull live workspace data into your LlamaIndex document store. Instead of query results sitting as raw JSON, they are parsed and stored as searchable nodes. This means your agent can retrieve actual project discussions and task states during its retrieval steps. By embedding these workspace records into a vector database, your RAG applications can query historical project decisions. You get answers grounded directly in your actual records rather than relying on model hallucinations. The MCP server ensures your index stays fresh by fetching the latest workspace updates on demand.

Semantic search across custom databases

The agent runs `search_entities` to find relevant records across all your custom databases using natural language. It bypasses rigid keyword matching by combining LlamaIndex's semantic search with Fibery's structural queries. Your agent can locate obscure tasks or feature requests even if the user does not know the exact database name. Once the relevant entities are found, the `FunctionAgent` can pull their complete details using `get_entity`. This two-step process of semantic retrieval followed by direct entity fetching makes your agent incredibly precise when answering complex workspace questions.

Automated documentation and task generation

Your agent invokes `create_entity` to generate new tasks or documentation pages directly from your indexed knowledge base. When a user asks a question that reveals a gap in the documentation, the agent drafts the solution and creates the record in the correct space. You implement this by loading the tools via `McpToolSpec` and passing them to your LlamaIndex agent. The agent automatically maps natural language queries to schema-compliant `create_entity` or `add_comment` calls, keeping your documentation and task tracker in sync.

Setup guide

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

Install `llama-index-tools-mcp` via pip. Initialize the `BasicMCPClient` with your Vinkius endpoint, convert it using `McpToolSpec`, and call `to_tool_list_async` to get the list of tools for your agent.

Yes, LlamaIndex can pull discussion history using the `get_comments` tool. It indexes those comment threads as text nodes so your RAG pipeline can search past team discussions.

The agent uses `get_schema` to discover custom field definitions. LlamaIndex reads this schema to understand how to structure its queries and format new entities when calling `create_entity`.

Yes, you can use the `allowed_tools` filter when configuring your `McpToolSpec`. This lets you restrict your agent to read-only operations like `query_entities` if you want to prevent automated modifications.

Absolutely. Your workspace entities and database schemas are processed through an ephemeral, zero-trust MCP sandbox on Vinkius. No data is stored on Vinkius servers, and the connection uses a single token to manage all API authorization securely.

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