How do I find my Subdomain and API Key?

Your subdomain is the first part of your Recurly portal URL (e.g., if you log in at `myproject.recurly.com`, your subdomain is `myproject`). To get your API Key, navigate inside Recurly to Integrations > API Credentials and generate or copy your 'Private API Key'.

Can it accidentally charge my customers?

While the server can manage subscriptions (e.g., setting up a customer with a plan), it strictly follows the billing logic predefined in your Recurly catalog settings. It doesn't bypass credit card validation or execute arbitrary charges directly without a plan context.

Does cancelling a subscription remove the account entirely?

No, using `cancel_subscription` stops future renewals for that specific plan item instance. The underlying user billing account remains intact and can hold other valid subscriptions or past invoices.

Recurly MCP Server for LlamaIndex 10 tools — connect in under 2 minutes

Name: Recurly
Availability: InStock
Author: Vinkius

docs.llamaindex.ai/en/stable/module_guides/tools/mcp

Built by Vinkius GDPR 10 Tools Framework

LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Recurly as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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 Recurly. "
            "You have 10 tools available."
        ),
    )

    response = await agent.run(
        "What tools are available in Recurly?"
    )
    print(response)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Recurly MCP Server

Connect your Recurly subscription billing and management platform securely to your conversational AI agent. Activating this integration transforms your AI into a dynamic revenue operations assistant, giving it the autonomy to look up accounts, adjust active subscription states, and analyze invoice pipelines directly from the terminal.

LlamaIndex agents combine Recurly tool responses with indexed documents for comprehensive, grounded answers. Connect 10 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

Account Management — Quickly list your customer directory, view detailed billing profiles, or instantly create a new account mapping without opening the vendor console.
Subscription Operations — Easily search and read subscription lifecycle states, enroll users in fresh catalog plans, un-cancel previous subscriptions, or permanently cancel an ongoing billing mandate.
Invoice & Plan Catalogs — Retrieve the list of historical generated invoices to verify successful automated payments or pull all active billing models (Catalog Plans) to review available products.

The Recurly MCP Server exposes 10 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 Recurly to LlamaIndex via MCP

Follow these steps to integrate the Recurly 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 10 tools from Recurly

Why Use LlamaIndex with the Recurly MCP Server

LlamaIndex provides unique advantages when paired with Recurly through the Model Context Protocol.

Data-first architecture: LlamaIndex agents combine Recurly tool responses with indexed documents for comprehensive, grounded answers

Query pipeline framework lets you chain Recurly tool calls with transformations, filters, and re-rankers in a typed pipeline

Multi-source reasoning: agents can query Recurly, a vector store, and a SQL database in a single turn and synthesize results

Observability integrations show exactly what Recurly tools were called, what data was returned, and how it influenced the final answer

Recurly + LlamaIndex Use Cases

Practical scenarios where LlamaIndex combined with the Recurly MCP Server delivers measurable value.

Hybrid search: combine Recurly real-time data with embedded document indexes for answers that are both current and comprehensive

Data enrichment: query Recurly 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 Recurly for fresh data

Analytical workflows: chain Recurly queries with LlamaIndex's data connectors to build multi-source analytical reports

Recurly MCP Tools for LlamaIndex (10)

These 10 tools become available when you connect Recurly to LlamaIndex via MCP:

cancel_subscription

This action is irreversible. Cancels an active subscription

create_account

Specify code, email, and name. Creates a new customer account

create_subscription

Creates a new subscription for an account

get_account_details

Retrieves details for a specific customer account

get_subscription_details

Retrieves details for a specific subscription

list_accounts

Lists all customer accounts in Recurly

list_catalog_plans

Lists all available subscription plans in the product catalog

list_invoices

Lists all generated invoices

list_subscriptions

Lists all subscriptions managed by Recurly

reactivate_subscription

Reactivates a previously cancelled or expired subscription

Example Prompts for Recurly in LlamaIndex

Ready-to-use prompts you can give your LlamaIndex agent to start working with Recurly immediately.

"List the last 5 invoices generated in our account."

"Cancel the subscription with ID 'sub_39xjd82kw0'."

"Retrieve the billing details for account code 'cus_alpha_92'."

Troubleshooting Recurly MCP Server with LlamaIndex

Common issues when connecting Recurly to LlamaIndex through the Vinkius, and how to resolve them.

BasicMCPClient not found

Install: pip install llama-index-tools-mcp

Recurly + LlamaIndex FAQ

Common questions about integrating Recurly MCP Server with LlamaIndex.

How does LlamaIndex connect to MCP servers?

Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.

Can I combine MCP tools with vector stores?

Yes. LlamaIndex agents can query Recurly tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.