Listing Thumbnail

    MCP Server for SaaS on Amazon Bedrock AgentCore by Assembly

     Info
    Bring your customers' data into Claude and ChatGPT. Assembly builds one MCP server on Amazon Bedrock AgentCore over the APIs you already have, with OAuth sign-in, per-customer access and every call logged.

    Overview

    An MCP server for your SaaS product, built on Amazon Bedrock AgentCore by Assembly

    Assembly is an AWS Advanced Tier Services Partner. We build one MCP (Model Context Protocol) server for your product on Amazon Bedrock AgentCore, on top of the APIs you already have, so your customers get instant insights from their own data in the AI assistants they already use.

    Relation to AWS services This professional service designs, builds and launches an MCP server in your AWS account on Amazon Bedrock AgentCore: AgentCore Gateway turns your existing REST APIs into MCP tools. Customer sign-in uses OAuth through your identity provider with Amazon Cognito, access is controlled with AWS Identity and Access Management (IAM), and every call is logged and measured in Amazon CloudWatch.

    Why an MCP server

    • Close the gap: your customers ask AI assistants for help all day; when their data lives only inside your app, the assistant can't see it. An MCP server lets them ask in Claude or ChatGPT and get answers from your product.
    • Your context, not a guess: your data model, the definitions and KPIs your customers trust, and your workflows become tools, so answers are right for your industry, not just plausible.
    • Built to be chosen: clear tools and precise descriptions help assistants pick your product (what AWS calls agentic discoverability).
    • No rebuild: the MCP server sits on the APIs you have today; customer data stays where it is.

    Who it's for SaaS companies whose customers already work in AI assistants, for example clinic and practice management, spend management and payments, or rostering, payroll and HR platforms.

    How it runs

    1. Map: agree the first use case, the questions customers ask, the tools the MCP server needs and the data each tool can reach.
    2. Secure: design OAuth sign-in through your own identity provider, scoped tokens and access checked on every call, so each customer only sees their own data.
    3. Build: AgentCore Gateway turns your existing APIs into MCP tools, with Python tools for your data team where needed, and MCP Apps that put dashboards and tables right in the conversation.
    4. Launch: connect Claude and ChatGPT, then hand over monitoring, audit logs and running costs.

    What you receive

    • An MCP server your customers connect from Claude and ChatGPT
    • OAuth sign-in with per-customer access
    • Read-only tools over your existing APIs
    • Audit logs and monthly running costs

    Guardrails

    • OAuth sign-in, never API keys
    • Only the signed-in customer's data, checked on every call
    • Read-only tools over your existing APIs
    • Every call logged and measured, ready for usage-based pricing

    Important

    • The engagement starts with an AI Assess for your MCP server, funded by AWS for companies that qualify; the build can be funded too. Funding is subject to AWS approval, and we check your fit with you before anything goes to AWS.
    • You are responsible for any AWS infrastructure and service charges incurred in your AWS account, billed separately from your AWS Marketplace transaction.

    Highlights

    • One MCP server on Amazon Bedrock AgentCore that your customers connect from Claude and ChatGPT, built on the APIs you already have
    • OAuth sign-in through your identity provider, read-only tools and per-customer access checked on every call, with audit logs
    • Starts with an AI Assess funded by AWS for companies that qualify; the build can be funded too, subject to AWS approval

    Details

    Delivery method

    Deployed on AWS
    New

    Introducing multi-product solutions

    You can now purchase comprehensive solutions tailored to use cases and industries.

    Multi-product solutions

    Pricing

    Custom pricing options

    Pricing is based on your specific requirements and eligibility. To get a custom quote for your needs, request a private offer.

    How can we make this page better?

    Tell us how we can improve this page, or report an issue with this product.
    Tell us how we can improve this page, or report an issue with this product.

    Legal

    Content disclaimer

    Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.

    Support

    Vendor support

    Getting in touch Contact Assembly at hello@assembly.cloud  or book a call at https://calendar.app.google/QXUPBVqPkLRJwqG68 .

    Before the engagement We reply to listing enquiries, eligibility questions and private offer requests within two business days (Australian Eastern time). After you accept a private offer, an Assembly engineer contacts you within two business days to start the Map step.

    During the build Your Assembly engineer leads Map, Secure, Build and Launch with your product and engineering team.

    After launch For questions about the MCP server, monitoring, audit logs or running costs, contact your engineer or hello@assembly.cloud .

    Billing For billing questions, email hello@assembly.cloud . We reply within two business days.