Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
AppXen is a Managed MCP Infrastructure for AI Agents
The Model Context Protocol (MCP) is becoming the standard way AI models connect to external tools, data sources, and APIs. But running MCP infrastructure in production is complex, you need proxying, authentication, rate limiting, multi-agent coordination, knowledge retrieval, and safety controls. AppXen provides all of it, fully managed, so your team can build AI-powered workflows without building or operating the infrastructure underneath them.
Show the rest of the publisher’s description (32 more lines)
MCP Gateway
The foundation of the AppXen platform. MCP Gateway is a fully managed MCP proxy that connects AI models, including Claude, GPT, and any MCP-compatible client, to your tools and APIs through a single, authenticated endpoint.
Add MCP servers in the AppXen console and they become immediately available to your AI models, your orchestrated workflows, and Claude Desktop. No JSON config files. No credential management across environments. No self-hosted infrastructure to maintain.
Built-in capabilities include:
API key and JWT authentication
Per-tenant rate limiting and usage metering
REST-to-MCP bridging, expose any existing REST API as an MCP tool in minutes
Structured logging and CloudWatch observability
Multi-tenant architecture with isolated routing per customer
Supported integrations: GitHub, Neon Postgres, Supabase, Zapier, AWS CloudWatch, and any REST API endpoint.
RAG Engine
AI agents are only as useful as the context they have access to. RAG Engine is AppXen's managed knowledge layer, upload documents, technical specs, runbooks, or any text-based content, and it becomes instantly searchable by your agents and workflows.
Content is chunked, embedded, and indexed automatically. No vector database to provision. No embedding pipeline to build. Agents query the knowledge base as a native MCP tool, grounded responses, not hallucinations.
Use RAG Engine to give your agents access to internal documentation, product requirements, compliance policies, or any proprietary knowledge that shouldn't leave your control.
Orchestrator
Multi-agent workflows, defined in plain markdown.
Orchestrator lets you compose sequences of specialized agents, each with access to your connected MCP tools and RAG knowledge base, without writing orchestration code. Define what each agent should do in natural language, chain them together, and run the workflow on demand or on a schedule.
Example workflows teams run today:
Code review pipelines that analyze a repo, flag security issues, and write findings to a database
Document analysis workflows that search the knowledge base, cross-reference live data, and produce structured reports
Incident response workflows that pull CloudWatch logs, identify error patterns, and summarize findings for on-call engineers
Outputs can be written to Postgres, surfaced in Claude Desktop, forwarded via webhook, or fed into the next agent in the sequence. Every run is logged and auditable.
How AppXen fits into your stack
AppXen works alongside the tools your team already uses. Connect your existing APIs, databases, and services as MCP tools. Run workflows from Claude Desktop, from your CI/CD pipeline, or on a schedule. Subscribe through AWS Marketplace and usage is metered and billed directly through your AWS account, no separate procurement, no new vendor relationships.
Pricing is pay-as-you-go:
MCP Gateway: per request and per server-hour
RAG Engine: per query and per compute-hour
Orchestrator: per agent-hour and per base-hour
No upfront commitments. No minimum spend. Scale from a single developer to an enterprise team on the same platform.
Built for production from day one
AppXen infrastructure runs on AWS with multi-AZ deployment, 99.9% uptime SLA, end-to-end encryption, and structured audit logging on every request. RTO under 15 minutes. RPO under 5 minutes.
The platform is designed for teams who want the capabilities of a full AI agent infrastructure stack, without the engineering overhead of building and maintaining it themselves.
Highlights
Highlighted by the publisher on AWS Marketplace.
Orchestrator lets you define sophisticated AI workflows without writing orchestration code. Describe what each agent should do in natural language, chain them together, and run on demand or on a schedule. Each agent has full access to your connected MCP tools include GitHub, Postgres, CloudWatch, your own APIs, and your RAG knowledge base. Outputs can be written to a database, forwarded via webhook, or fed into the next agent in the sequence. Every run is logged and auditable.
MCP Gateway Pro is a fully managed MCP proxy that connects AI models to your tools and APIs through a single, authenticated endpoint. Add MCP servers in the console and they become immediately available to your models, your workflows, and Claude Desktop. No JSON config files, no credential management, no self-hosted infrastructure to maintain. Built-in API key and JWT authentication, per-tenant rate limiting, REST-to-MCP bridging, and structured CloudWatch observability included out of the box.
RAG Engine is AppXen's managed knowledge layer, upload documents, technical specs, runbooks, or any text-based content and it becomes instantly searchable by your agents and workflows. Content is chunked, embedded, and indexed automatically. No vector database to provision, no embedding pipeline to build. Agents query the knowledge base as a native MCP tool, giving you grounded responses instead of hallucinations. Your proprietary knowledge, always in your control.
Preview
4 images
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Plans and pricing as listed
8 listed- Units
- Units
- Units
- Units
- Units
- Units
- Units
- Units
Refund terms
As stated by the publisher on AWS Marketplace.
Usage-based service with no upfront fees, you pay only for what you consume. Refunds are generally not applicable as there are no prepaid charges. For billing discrepancies, contact support@appxen.ai within 30 days and we will issue credits for any confirmed overcharges. Cancel anytime through AWS Marketplace with no cancellation fees.
Sources
Publisher resources
3 linksLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.