Platform, security, and AI engineering teams selecting a production control architecture.
When to use an MCP proxy, an MCP gateway, or both.
The control gap
The names are often used interchangeably even though they answer different control questions. A proxy describes traffic placement. A security gateway additionally makes and enforces policy decisions using semantic request context.
A proxy earns its place by providing a reliable path: connection handling, routing, protocol adaptation, and sometimes logging. Those functions do not automatically make it an authorization system. Ask whether it can identify the agent and delegated user, parse each tool invocation, resolve the target resource, evaluate versioned policy, and withhold forwarding while approval is pending.
Choose a lightweight proxy when transport consolidation is the actual requirement and downstream servers already enforce complete policy. Choose a security gateway when server implementations are inconsistent or when one organization-wide approval and evidence model is needed. Endram can sit at that decision boundary without claiming to replace every network or API-management function.
What good looks like
A purchase decision based on the enforcement point and evidence the team actually needs, rather than category labels.
- Transparent routing
- Tool schema parsing
- Policy decision depth
- Operational ownership
A production workflow
- Map where an MCP proxy sits in the request path and which failures it can stop.
- Repeat the exercise for an MCP gateway, including identities and resource context visible at decision time.
- Classify required actions as automatic, denied, or human-approved.
- Run representative calls in shadow mode and compare the evidence produced by each design.
Evidence to require
- Enforcement occurs before the external side effect, not after log ingestion.
- Decisions identify the agent and delegated user as separate principals.
- The resource, environment, policy version, reason, and response are retained together.
- Approval is bound to one request and expires instead of creating standing access.
Buyer checklist
- Which option can block the side effect at the moment of execution?
- Which identities and resource attributes are visible to its policy engine?
- Does it support request-bound human approval?
- Can the team export a complete decision trail without reconstructing several logs?
Practical answers
Common implementation questions
Is an MCP proxy a replacement for an MCP gateway?
Usually not. The right design depends on the enforcement point, protocol, and decision context. Many production systems use both, with each protecting the layer it can actually observe.
Where does Endram fit?
Endram is the runtime authorization and approval layer for agent tool calls. It evaluates the requested action before execution and keeps the decision evidence.
Can this be tested without interrupting production?
Yes. Shadow mode shows how candidate policies classify real calls before enforcement is enabled.