Overview
ContextIQ Essentials is an MCP-native knowledge server that gives Cowork, Claude Desktop, and AI agents governed access to enterprise knowledge sources. It sits between AI consumers and your organization's documents, controlling which sources each user can query, returning cited answers with source evidence, and keeping retrieval scoped to authorized entitlements. ContextIQ uses Model Context Protocol (MCP) with Streamable HTTP transport, making it compatible with any MCP-enabled AI assistant or agent framework.
The product deploys into your AWS account using CloudFormation. The quickstart provisions Amazon Bedrock AgentCore for running ContextIQ Agents, ECS-based ContextIQ MCP servers, and tools that integrate with Amazon Bedrock Knowledge Bases, S3 Vectors for low-cost vector storage. ContextIQ stack includes user authentication, secure VPC based deployment of application services, a browser-based chat interface, and a Cowork/Claude Desktop setup package. Sample enterprise content is included so teams can evaluate governed knowledge access immediately without preparing their own data. Enterprise data never leaves the customer's AWS account.
ContextIQ Essentials is the starting point for teams evaluating governed agentic AI access patterns. Use it to validate entitlement-scoped retrieval, cited responses, and multi-source knowledge routing before expanding to ContextIQ Enterprise Preview - which adds broader source coverage, custom guardrails, domain-specific validation, and guided rollout for regulated industries.
Highlights
- Built for Cowork, Claude Desktop, and AI agents - ContextIQ exposes enterprise knowledge as MCP tools so AI assistants retrieve only what each user is entitled to access, with cited source evidence in every response.
- Governed knowledge access in your AWS account - Deploy with CloudFormation into your own VPC with Amazon Bedrock AgentCore agents, ECS-based MCP servers, Bedrock Knowledge Bases, and S3 Vectors. Enterprise data never leaves your account.
- Start with Essentials, expand with Enterprise Preview - Evaluate governed agentic AI access patterns today with sample content and a working deployment, then engage ContextIQ Enterprise Preview for broader source coverage, custom guardrails, and guided rollout for regulated industries.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
ContextIQ Essentials is provided at no software charge. Customers are responsible for AWS infrastructure and model usage costs incurred in their own account. No refund applies as there is no software fee.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
ContextIQ Essentials - CloudFormation Deployment
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
ContextIQ Essentials v1.2.10 - Governed knowledge access for Cowork and AI agents via MCP. Includes Amazon Bedrock AgentCore agents, ECS-based MCP servers with tools, Bedrock Knowledge Bases with S3 Vectors, VPC-based deployment, browser chat interface, and Cowork/Claude Desktop setup package. Updates include improved query response performance, ECR pull-through cache reliability, execution role hardening, delegated deployment for non-admin users, and expanded usage instructions.
Additional details
Usage instructions
Prerequisites:
- AWS account with Bedrock model access enabled for Anthropic Claude and Amazon Titan Embed Text V2 in your target region
- IAM permissions to deploy CloudFormation stacks (admin), or the included delegated deployment policy for non-admin users
- Supported regions: us-east-1, us-west-2, eu-west-1, ap-southeast-1
Step 1 - Deploy the Essentials Stack (~30-35 minutes):
- After subscribing, launch the CloudFormation quickstart from the fulfillment page
- Fill in AdminEmail (your email for the initial admin account) and AdminPassword (must include uppercase, lowercase, number, and special character)
- All other parameters have sensible defaults - no changes needed
- Check the IAM capabilities acknowledgment checkbox and click Create stack
What gets deployed: VPC with Application Load Balancer, Amazon Bedrock AgentCore agents, ECS-based MCP servers with tools, two Amazon Bedrock Knowledge Bases (OpenSearch and S3 Vectors), Amazon Cognito user pool with pre-created access groups, Amplify-hosted chat interface, and pre-loaded sample documents for immediate evaluation.
Step 2 - Verify with the Nexus Chat App:
- Open the ChatApp URL from CloudFormation Outputs tab (ChatAppUrl)
- Sign in with the AdminEmail and password you provided during deployment
- Set a permanent password when prompted on first sign-in
- Try a sample query: "What are our current capital ratios and how much buffer do we have under stress?"
Step 3 - Connect Cowork (Claude Desktop):
- Download the Cowork setup package from the stack outputs: aws s3 cp s3://<DocsDistBucket>/cowork/contextiq-cowork.tar.gz . && tar xzf contextiq-cowork.tar.gz && cd contextiq-cowork
- Run the setup script: ./contextiq-setup --username your@email.com
- The script auto-discovers your deployment, authenticates, and configures Claude Desktop
- Restart Claude Desktop - the ContextIQ tool appears in MCP connectors
- Set the ContextIQ connector to "Always Allow" for seamless experience
- Start with: "Tell me about ContextIQ" to activate the MCP server
Step 4 - Onboard Your Team:
- Create Cognito user accounts via the AWS Console (Cognito > User Pools) or the included contextiq-admin-setup script
- Assign users to knowledge base access groups: contextiq-all-kb (both knowledge bases), contextiq-opensearch (regulatory/reference documents only), or contextiq-s3vectors (internal/proprietary content only)
- Distribute Cowork access: ./contextiq-setup --export-config --publish - generates a shareable setup link. End users need only Python 3.10+, no AWS CLI or backend access required
- First-time users must sign in via the Chat App once to set a permanent password before using the Cowork setup script
Step 5 - Add Your Own Documents:
Upload documents to the S3 document buckets shown in CloudFormation Outputs. Amazon Bedrock automatically ingests uploaded documents. Supported formats: PDF, TXT, MD, CSV, DOCX, HTML, JSON.
Monitoring:
- CloudFormation Console: Stack status, outputs, and resource list
- ECS Console: MCP server health, task status, and container logs
- CloudWatch Logs: Application logs under the /contextiq log group
- Cognito Console: User management, group assignments, sign-in activity
- Amazon Bedrock Console: Knowledge base sync status and ingestion history
Uninstall:
Delete the contextiq-essentials CloudFormation stack. All provisioned resources are removed. S3 document buckets containing customer-uploaded content are retained by default and must be deleted manually if desired.
Support:
Email hello@contextiq.us for deployment, configuration, or upgrade questions. Target response time: 2 business days. For ContextIQ Enterprise Preview, contact hello@contextiq.us .
Product documentation: https://contextiq.us/readme
Support
Vendor support
Email support for Marketplace deployment, quickstart usage, and initial configuration. Contact hello@contextiq.us . Target response time: 2 business days for ContextIQ Essentials. Enterprise Preview onboarding and expanded support available by engagement.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.