Nue MCP Servers

model context protocol (mcp) is an open specification (originally from anthropic ) that standardizes how ai models and agents connect to external tools business logic, data sources, and services—through a simple request/response interface over http or streaming transports mcp allows ai clients to reliably discover available tools , call them with structured parameters , and receive structured results this enables assistants to interact with real systems in a predictable, secure, and verifiable way, rather than relying solely on ungrounded natural language prompts why mcp matters by separating model specific behavior from tool execution, mcp allows organizations to keep domain logic in one place and reuse it across multiple llms (e g , openai, anthropic, gemini) and agent runtimes this reduces integration friction, avoids model lock in, and makes ai integrations more scalable and maintainable mcp server the tool execution layer an mcp server is any service that implements the model context protocol (mcp) and exposes one or more named tools each with clear descriptions and input schemas that ai clients can call at runtime, the mcp server acts as the execution layer it tells clients which tools are available, authenticates and authorizes incoming requests, runs the requested business logic (e g , calling apis, querying databases), and streams back structured results the server itself remains model agnostic it doesn’t depend on a specific llm all model specific reasoning happens on the client side key responsibilities of an mcp server advertise available tools to clients (including name, description, and parameter schema) for safe discovery receive structured tool calls over json rpc or streaming http/sse, execute the underlying logic, and return results or errors in a predictable format enforce authentication and authorization , ensuring the right data and tools are accessible with the right scope mcp client the ai integration layer an mcp client runs inside your ai application or agent framework it connects to one or more mcp servers, retrieves their tool definitions, and makes them available to the model as part of its prompt and function calling context when the model chooses to call a tool, the mcp client translates that intent into a structured request (e g , http/sse), manages retries and timeouts, and streams the response back to the model for further reasoning the following diagram illustrates the mcp server & client workflow, including deployment options nue mcp servers nue mcp servers are intelligent, model agnostic orchestration layers that connect your revenue data with ai securely and seamlessly instead of a single monolithic server, nue provides multiple specialized mcp servers (e g , lifecycle manager, guided selling, and more), each designed to expose well defined tools for specific parts of your revenue lifecycle these servers bring live, structured business context such as customers, quotes, subscriptions, invoices, and product relationships—directly into ai interactions they enable assistants to safely query data and take approved actions, without needing to hardcode business logic in every interface by bridging nue’s structured data and lifecycle apis with modern ai models, mcp servers power grounded answers, dynamic quoting, and guided workflows across your entire revops stack no matter which llm you choose in nue’s applications, the assistant layer integrates with mcp by configuring the mcp server url and brokering tool use through a standardized client interface this means the same set of tools can work seamlessly across multiple model providers, making our ai features consistent, secure, and extensible because the mcp servers only expose tool definitions and execute business logic, nue can work with multiple ai providers (e g , gpt, claude, gemini) while centralizing guardrails and domain logic once administrators can select a default ai provider and bring their own keys where appropriate, while mcp keeps the tool layer consistent the lifecycle manager mcp server the lifecycle manager mcp is designed to bring intelligence and control to your subscription and order lifecycles —from discovery and analysis to executing changes across customers, subscriptions, invoices, and quotes it provides a rich set of tools—such as getcustomers, getcustomersubscriptions, getcustomerinvoices, getcustomercreditmemos, generatecustomersummary, and generatequotesummary—that allow assistants to answer transactional questions and produce narrative summaries grounded in live data for renewal workflows, getcustomersubscriptions supports an “up for renewal” view using an optional renewaldate parameter this returns active subscriptions ending before the target date, sorted by end date, making it easy to identify upcoming renewals the mcp also supports account hierarchy traversal agents can include child accounts and retrieve data recursively for a complete, depth first view for real time insight, getcustomersubscriptionstoday delivers snapshot intelligence , returning as of views and upcoming changes when products and price tags are published, it includes product and pricing context for precise reasoning change order operations are fully supported through tools such as set/increase/reduce quantity, renew, co term, adjust price, upgrade/downgrade/swap, cancel, with the options of creating quotes or orders this enables agents to confidently recommend or execute lifecycle actions with clear defaults and guided confirmations—making complex subscription management seamless connect to the lifecycle manager mcp server use the following mcp configuration to connect your favorite mcp client, e g , windsurf, cursor, claude desk, chatgpt, etc nue environment mcp server endpoint authentication nue sandbox https //mcp sandbox nue io/sse https //mcp sandbox nue io/sse nue api key nue api key nue production https //mcp nue io/sse nue api key nue api key { "mcpservers" { "nue lifecycle manager sandbox" { "command" "npx", "args" \[ " y", "mcp remote\@0 1 29", "https //mcp sandbox nue io/sse", " header", "nue api key {{nue api key}}" ] }, "nue lifecycle manager prod" { "command" "npx", "args" \[ " y", "mcp remote\@0 1 29", "https //mcp nue io/sse", " header", "nue api key {{nue api key}}" ] } } } node version cursor, windsurf, claud desk and mcp remote cli rely on your system's node js version, not an embedded one this means that if your system node version is outdated, the mcp servers may fail to start correctly you must be using node js v20 or later for mcp remote and nue mcp servers to function properly you can check your current version by running node v \#if below v20, upgrade using nvm or nvm windows on windows nvm install 20 nvm use 20 after upgrading, restart your clident to ensure the correct node version is being used cursor here are the steps to configure this mcp server in cursor locate cursor's mcp configuration file the file location depends on your operating system macos / cursor/config json windows %userprofile%\\ cursor\config json open or create the configuration file if the file doesn't exist, create it with an empty json object {} if it exists, open it in a text editor add the mcp server configuration insert or merge the mcpservers configuration { "mcpservers" { "nue lifecycle manager sandbox" { "command" "npx", "args" \[ " y", "mcp remote\@0 1 29", "https //mcp sandbox nue io/sse", " header", "nue api key your actual api key here" ] }, "nue lifecycle manager prod" { "command" "npx", "args" \[ " y", "mcp remote\@0 1 29", "https //mcp nue io/sse", " header", "nue api key your actual api key here" ] } } } replace the api key placeholder ⚠️ important replace {{nue api key}} with your actual nue api key save the file and restart cursor ensure the json is valid (no trailing commas, proper brackets) completely quit and reopen cursor for the changes to take effect verify the connection open cursor's ai chat the mcp servers should now be available you can test by asking claude to use nue tools (e g , "list available nue lifecycle tools") windsurf in windsurf, mcp servers are defined inside a configuration file named (if using codeium's native mcp support) macos / codeium/windsurf/mcp server config json windows %userprofile%\\ codeium\windsurf\mcp server config json linux / codeium/windsurf/mcp server config json copy the configuration as follows and replacey nue api key as your own api key { "mcpservers" { "nue lifecycle manager sandbox" { "command" "npx", "args" \[ " y", "mcp remote\@0 1 29", "https //mcp sandbox nue io/sse", " header", "nue api key your actual api key here" ] }, "nue lifecycle manager prod" { "command" "npx", "args" \[ " y", "mcp remote\@0 1 29", "https //mcp nue io/sse", " header", "nue api key your actual api key here" ] } } } save the file, restart windsurf and test your connection using cascade settings ui (if available) open windsurf settings (cmd/ctrl + ,) search for "mcp" or "model context protocol" if there's a ui for mcp configuration, you can add servers there instead this may be under "cascade" or "ai assistant" settings test after successfully connected to the lifecycle manager nue mcp server, test the server by asking the following question what mcp tools are available in nue sandbox? the following tools are currently available customer management getcustomers, postcustomers, patchcustomers, postcustomerscontacts subscriptions getcustomersubscriptions, getsubscriptionupforrenewal, getcustomersubscriptionstoday orders & quotes createchangeorder, createchangequote, generateordersummary, generatequotesummary financial getcustomerinvoices, getcustomercreditmemos analytics generatecustomersummary, fetchcustomersupforrenewal, fetchcustomerswithproduct sales createopportunity, queryopportunities metadata getobjectmetadata, generateproductrelationsummary troubleshooting if it doesn't work check the mcp config json syntax is valid (use a json validator) verify the node v20 or later is used verify npx is available in your path check console/logs for error messages ensure your nue api key is valid and has appropriate permissions