Works with your AI tools

It fits the stack you already have. Bring your assistant into Claude and other AI apps, give your agents tools that live elsewhere, and use the models you prefer.

At a glance

Fits the tools and AI you already use

  1. 01Your assistant, inside ClaudeYour knowledge in the AI apps your team uses
  2. 02Give your agents new powersConnect events, finance and learning systems
  3. 03The models you preferManaged keys or your own, never locked in
  4. 04Built to connectREST API and single sign-on

01

Bring your assistant into Claude, and beyond

Expose your organisation's tools and knowledge over MCP, the open standard, so your team can work with your data from Claude Desktop and the other AI apps they use.

  • Publish endpoints that third-party AI apps can connect to
  • Decide who can connect: a single app, your admins or your members
  • Secured with tokens or OAuth sign-in

02

Give your agents new powers

It works the other way too. Connect external systems to your agents so they can reach the tools and data that live elsewhere.

  • Connect external MCP servers as tools your agents can call
  • Pass each user's identity through to the connected system
  • See connection status and the tools each server offers

03

The models you prefer

ReadyIntelligence isn't tied to a single AI provider. Use the platform's managed models or bring your own keys, and switch as the technology moves on.

  • Use providers such as OpenAI and Anthropic
  • Use our managed keys, or bring your own
  • Never locked in to one model or vendor

04

Built to connect

For deeper integration, there's a REST API and single sign-on for the assistants you embed on your own sites.

  • A REST API to manage your knowledge base and users
  • Single sign-on for embedded assistants, with OpenID Connect or a signed token from your site

Related reading

Browse all resources

Common questions

Do we need to use ReadyMembership?

No. ReadyIntelligence integrates deeply with ReadyMembership, but it works with any CRM, AMS or membership platform and can be embedded on any website, including WordPress and other CMSs. The full capability, including knowledge search, data questions and permissions, is available whatever your site is built on.

What is MCP, and how does ReadyIntelligence use it?

MCP (Model Context Protocol) is an open standard for connecting AI tools to other systems. ReadyIntelligence uses it in two directions. Other services can be connected to ReadyIntelligence through MCP without custom development. And ReadyIntelligence can itself be used as an MCP server, so your team can work with your knowledge and data from inside Claude and other AI apps, with the same permissions applied as everywhere else.

Which single sign-on options does ReadyIntelligence support?

Two. With OpenID Connect, people sign in through your own identity provider, such as Microsoft Entra ID or Okta, after you register ReadyIntelligence as an application with it. Or your website can pass the assistant a signed token (JWT) for the person already signed in, which ReadyIntelligence verifies before trusting it.

Either way, details your identity provider holds, such as groups or membership type, can decide what each person is allowed to see.

Do our users need another login?

No. Pass the assistant a signed token from your application, or connect your OpenID Connect identity provider, and your users are signed in to it automatically. You choose whether it's for signed-in users only, guests as well, or everyone.

Can it use data from our own product?

Yes. Connect it to your product's API, or import an OpenAPI description, and it can look things up for the person asking. With single sign-on, each call carries that user's own access, so they only see what they're allowed to.

Which AI models does ReadyIntelligence use?

ReadyIntelligence is model-neutral. It uses leading large language models under the hood and can adopt newer or more capable models as they become available, without you having to change how you've configured your assistants. Answers are always grounded in your own content rather than the model's general knowledge.