Pipefy MCP Server for LlamaIndex 14 tools — connect in under 2 minutes
LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Pipefy as an MCP tool provider through the Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import 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 Pipefy. "
"You have 14 tools available."
),
)
response = await agent.run(
"What tools are available in Pipefy?"
)
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 Pipefy MCP Server
Connect your Pipefy account to any AI agent and take full control of your process management workflows through natural conversation.
LlamaIndex agents combine Pipefy tool responses with indexed documents for comprehensive, grounded answers. Connect 14 tools through the 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
- Pipe Discovery — List all pipes (processes) in your organization and inspect their structure, phases, and fields
- Card Management — Create, read, update, and delete cards (items/records) flowing through your pipes
- Field Updates — Update specific field values on existing cards as information changes or processes evolve
- Phase Transitions — Move cards between phases to advance workflow steps (e.g., New → In Progress → Done)
- Card Search — Search for cards by field value to find specific items by email, name, ID, or custom data
- Card Cloning — Duplicate existing cards to quickly create similar items with pre-filled field values
- Organization Info — View organization details, members, and available pipes
- User Profile — Check your authenticated user profile and organization memberships
The Pipefy MCP Server exposes 14 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Pipefy to LlamaIndex via MCP
Follow these steps to integrate the Pipefy MCP Server with LlamaIndex.
Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 14 tools from Pipefy
Why Use LlamaIndex with the Pipefy MCP Server
LlamaIndex provides unique advantages when paired with Pipefy through the Model Context Protocol.
Data-first architecture: LlamaIndex agents combine Pipefy tool responses with indexed documents for comprehensive, grounded answers
Query pipeline framework lets you chain Pipefy tool calls with transformations, filters, and re-rankers in a typed pipeline
Multi-source reasoning: agents can query Pipefy, a vector store, and a SQL database in a single turn and synthesize results
Observability integrations show exactly what Pipefy tools were called, what data was returned, and how it influenced the final answer
Pipefy + LlamaIndex Use Cases
Practical scenarios where LlamaIndex combined with the Pipefy MCP Server delivers measurable value.
Hybrid search: combine Pipefy real-time data with embedded document indexes for answers that are both current and comprehensive
Data enrichment: query Pipefy 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 Pipefy for fresh data
Analytical workflows: chain Pipefy queries with LlamaIndex's data connectors to build multi-source analytical reports
Pipefy MCP Tools for LlamaIndex (14)
These 14 tools become available when you connect Pipefy to LlamaIndex via MCP:
clone_card
You must provide the card_id of the card to clone. The new card is created in the same pipe as the original, starting at the first phase. This is useful for creating similar requests, repeating processes, or using an existing card as a template for new items. The cloned card gets a new unique ID but retains all field data. Clone an existing card to create a duplicate
create_card
You must provide the pipe_id and a JSON object containing field values matching the pipe's required fields. Fields are key-value pairs where keys are field IDs and values are the data to store. Optionally specify a phase_id to start the card in a specific phase (defaults to first phase). Example fields: { "name": "John Doe", "email": "john@example.com", "priority": "High" } Create a new card in a Pipefy pipe
delete_card
You must provide the card_id. This action cannot be undone. Use this to remove test cards, duplicates, or items that were created in error. Be careful as this will also remove all associated data including comments, attachments, and field values for that card. Delete a card from a pipe
get_card
Use the card_id obtained from list_cards to inspect full card information. This is useful for reviewing card details before updating fields or moving to another phase. Get detailed information about a specific card
get_organization
Use the organization_id to inspect your organization's structure, understand team membership, and discover available pipes for card management. Get details of a Pipefy organization
get_phase
Phases represent steps in a pipe's workflow. Use the phase_id obtained from get_pipe or list_phases to inspect phase configuration. This helps understand what fields are required at each step of the workflow. Get details of a specific phase
get_pipe
Each pipe represents a workflow or process with multiple phases (steps) and custom fields. Use the pipe_id to get the structure of a pipe before creating cards or managing cards within it. The response includes all phases with their IDs, names, and the custom fields defined for the pipe. Get details of a specific Pipefy pipe (process)
get_user_profile
Use this to verify API token access and discover organization IDs needed for other queries. This is also useful for understanding which organizations and pipes the user has access to. Get the authenticated user profile
list_cards
Cards represent individual items flowing through the pipe's workflow phases (e.g., requests, tasks, tickets, leads). You must provide the pipe_id. Optionally filter by phase_id to see cards in a specific phase. Each card includes title, current phase, completion status, due date, and assignees. Use this to monitor workflow progress and identify cards that need attention. List all cards in a pipe with optional phase filter
list_phases
Each phase represents a stage that cards flow through in the process. Use this to understand the workflow structure and identify phase IDs for filtering cards or moving cards between phases. The response includes phase names and card counts. List all phases in a pipe
list_pipes
Each pipe represents a structured workflow with phases, fields, and cards. You must provide the organization_id which can be found in your Pipefy URL or obtained from get_user_profile. Use this to discover all available pipes before managing cards within them. List all pipes in an organization
move_card_to_phase
You must provide the card_id and the target phase_id. This is the primary way to advance workflow items through the pipe's process steps. Common use cases: moving a request from "New" to "In Review", advancing a lead to "Qualified", or progressing a task to "Completed". The card retains all its field values after moving. Move a card to a different phase in the pipe
search_cards_by_field
This is useful for finding cards by email, name, ID, or any custom field content. You must provide the pipe_id, field_id (the field to search in), and search_value (text to find). Results include card title, current phase, status, and all field values for matching cards. The search uses a "contains" operator for flexible matching. Search cards in a pipe by a specific field value
update_card_field
You must provide the card_id, the field_id of the field to update, and the new value as a string. This is useful for updating card information as requests progress or details change. Common updates: changing priority, updating contact info, modifying descriptions, or setting dates. Update a specific field value on a card
Example Prompts for Pipefy in LlamaIndex
Ready-to-use prompts you can give your LlamaIndex agent to start working with Pipefy immediately.
"List all pipes in my organization and show me the cards in the 'IT Support' pipe."
"Create a new purchase request card in the Purchase Requests pipe with these details: Requester: Maria Silva, Item: MacBook Pro 16", Quantity: 2, Justification: Design team replacement."
"Search for all cards in the IT Support pipe where the email field contains 'john@company.com' and show me their current status."
Troubleshooting Pipefy MCP Server with LlamaIndex
Common issues when connecting Pipefy to LlamaIndex through the Vinkius, and how to resolve them.
BasicMCPClient not found
pip install llama-index-tools-mcpPipefy + LlamaIndex FAQ
Common questions about integrating Pipefy 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?
Connect Pipefy with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Pipefy to LlamaIndex
Get your token, paste the configuration, and start using 14 tools in under 2 minutes. No API key management needed.