TechOneDigital Request an MCP architecture review

Based on the current stable MCP specification

Gateway & governance

Govern the MCP estate without turning the gateway into the protocol.

Use an MCP gateway when multiple hosts or servers need shared routing, policy and telemetry. Keep enterprise approval, server contracts and business authorisation explicit.

For

Enterprise architects and platform owners

Use when

Multiple hosts or servers may need shared routing, policy or telemetry.

Outcome

A direct-versus-gateway decision, control-plane boundaries and an ownership model.

Technical guide by , Founder & Technology Consultant.

TechOne architecture position

Use three distinct control points: runtime routing, catalogue governance and server enforcement.

The gateway controls traffic, the approval catalogue records what the organisation has approved, and each MCP server enforces its own contracts and downstream rules. One team may operate all three, but ownership, decision rights and evidence must remain distinct.

Illustrative architecture scenario, not a customer case.

See these boundaries in one CRM change.

Follow a proposed opportunity update through identity, object permissions, exact-action approval, command execution and outcome reconciliation. The example connects gateway, security and production decisions.

Follow the CRM walkthrough

Illustrative reference architecture

A gateway earns its place by enforcing a shared rule.

It is not required by MCP. Introduce one when multiple hosts or servers need common routing, policy, inventory or telemetry, while keeping business authorisation in the system that owns the decision.

Topology decision

Direct connection or governed gateway?

OptionUse whenRequired controlsTrade-off
Direct client-to-server connectionOne approved host connects to a small number of servers within an existing trust boundary, and identity, network, rate limiting and audit controls already exist at the endpoints.Pinned endpoint, audience-bound authorisation, server-side access control, tested schemas, direct telemetry and an approved catalogue record.Fewer shared components and failure modes, but policy, discovery and evidence can fragment as the number of hosts and servers grows.
Shared MCP gatewayMultiple hosts or business units require consistent ingress, destination control, metering, trace correlation and coarse capability policy across many remote servers.High availability, route ownership, integration with active approval-catalogue records, fail-closed policy, credential separation, privacy-aware logging and a tested bypass prohibition.Consistent control and visibility, but the gateway becomes critical infrastructure and may create a large blast radius if policy or routing is wrong.
Domain gateways or segmented ingressRisk, residency, ownership or availability requirements differ materially between domains such as finance, operations and public information.Common approval-catalogue model and evidence standard, with separate route sets, owners, credentials and failure domains.Better isolation and accountability, with more platform components to operate and keep consistent.
Aggregating MCP endpointThe enterprise deliberately wants to expose a curated virtual capability surface rather than route transparently to independent servers.Explicit server ownership, name-collision policy, schema translation rules, provenance in results, version compatibility, conformance tests and retirement behaviour.Simpler client configuration, but aggregation changes contracts and must be governed as more than a network proxy.

MCP gateway architecture nodes

  1. 01

    Core MCP participant

    MCP host

    The AI application that coordinates one or more MCP clients and decides how discovered capabilities are made available to the model and user.

    The host owns user experience, model context, consent and confirmation behaviour. The gateway must not infer user intent on the host’s behalf.
  2. 02

    Core MCP participant

    MCP client

    The host-side component that communicates with one MCP server, sends version and capability metadata and calls server primitives.

    Client identity metadata is useful for display, logging and compatibility, but it is not an authentication credential or an authorisation decision.
  3. 03

    Enterprise infrastructure component, not a core MCP primitive

    MCP gateway

    A controlled ingress and routing tier for approved remote MCP traffic, with policy enforcement, metering, rate limits, trace propagation and operational isolation where the architecture requires them.

    A transparent gateway that forwards messages unchanged does not become an MCP participant merely because it carries MCP traffic. A gateway that terminates the MCP interaction, originates new MCP requests, aggregates capabilities or presents them from its own endpoint takes on the corresponding client and server responsibilities and must be governed and tested accordingly.
  4. 04

    Enterprise governance component, distinct from the official MCP Registry and not a runtime MCP primitive

    Enterprise approval catalogue

    The approved inventory of servers, releases, owners, endpoints, transports, protocol support, authentication profiles, capability fingerprints and lifecycle states.

    The catalogue describes what the organisation has approved. It may reference metadata from the official MCP Registry or another registry, but that metadata is not enterprise approval. The catalogue does not execute tools, proxy traffic or replace live protocol discovery. A live server response remains authoritative for what that endpoint currently exposes, subject to enterprise policy.
  5. 05

    Core MCP participant

    MCP server

    The programme that exposes tools, resources or prompts to MCP clients and implements the protocol contract for its endpoint.

    The server validates inputs, checks access, applies business rules, calls downstream systems, sanitises outputs and returns protocol-correct results. These duties cannot be delegated to a catalogue entry.
  6. 06

    Enterprise security dependency

    Identity and policy services

    Authenticate principals, issue or validate audience-bound credentials, resolve scopes and attributes, and supply policy decisions where required.

    The gateway may enforce a policy decision, but the MCP server must still validate credentials and permissions applicable to its protected resource. Token passthrough is not an acceptable shortcut.
  7. 07

    System of record or operational dependency

    Downstream system

    The API, database, document store or business service that the MCP server reads or changes.

    Its native permissions, data rules and transaction controls remain in force. MCP does not supersede the downstream system’s security or integrity model.
  8. 08

    Enterprise operations dependency

    Observability and evidence store

    Correlate requests across host, gateway, server and downstream services and preserve approved operational evidence without recording secrets unnecessarily.

    Telemetry is evidence of what infrastructure observed, not proof that a business outcome was correct. Logs require access control, retention and redaction rules of their own.

Illustrative topology. A direct host-to-server connection remains valid when central mediation adds no useful control.

Do not collapse the planes

Discovery, policy, execution and evidence have different owners.

Data plane

Carries live MCP requests and responses between clients and approved servers.

For current Streamable HTTP, infrastructure can route and meter using MCP-Protocol-Version, Mcp-Method and, where defined, Mcp-Name. An intermediary that evaluates Mcp-Name must decode its Base64 sentinel form before comparison, preserve case-sensitive value semantics and avoid gateway-only normalisation that would identify a different name or URI from the body. The JSON-RPC body remains the source of truth, and the receiving server must reject a header/body mismatch.

Request identifier, authenticated principal, target server, Mcp-Method, Mcp-Name where present, decision, latency, response class and trace correlation, with sensitive arguments and credentials excluded or redacted.

Control plane

Applies enterprise decisions about which principals, hosts, servers and named capabilities may communicate.

Identity, audience, scope, server state, risk class and environment are evaluated before routing or execution. A gateway denial does not remove the server’s duty to authorise and validate the request.

Policy version, matched rule, decision, reason, approver where required and the exact capability identity evaluated.

Governance plane

Maintains the approved catalogue, ownership, schema evidence, lifecycle state and change decisions.

A release is assessed against its approval-catalogue record, schema fingerprints, privileges, tests and operational evidence before its state changes. The governance plane does not sit in the protocol request path by necessity.

Approved catalogue record, review decision, test report, risk acceptance where applicable, effective date, replacement path and retirement evidence.

Gateway boundary

Centralise cross-cutting controls, not hidden authority.

The gateway can own

  • Route without inventing protocol semanticsRoute Streamable HTTP requests using the standard MCP-Protocol-Version and Mcp-Method headers, plus Mcp-Name for tools/call, resources/read and prompts/get. For tasks/get, tasks/update and tasks/cancel, Mcp-Name carries the task identifier only when the Tasks extension is enabled. Decode the Base64 sentinel form before comparison, preserve case-sensitive value semantics and do not introduce intermediary-specific name or URI normalisation. Preserve the body unchanged unless the gateway is explicitly designed and tested as a protocol-aware intermediary.
  • Restrict destinations to approved server recordsResolve routes from a controlled configuration linked to active enterprise approval-catalogue records. Do not allow request-supplied hosts, arbitrary redirects or unreviewed discovery metadata to become routing destinations.
  • Enforce transport and edge policyTerminate or pass through TLS according to the trust model, validate the intended audience at the protected-resource boundary, apply request-size and rate limits, and reject unsupported protocol versions or destinations before they consume downstream capacity.
  • Apply capability-aware policy where evidence existsUse Mcp-Method and Mcp-Name for routing, metering and coarse policy only when the header is present for that method. Do not infer arguments, business intent or safety from a tool name. The MCP server remains responsible for validating the body and enforcing operation-level rules.
  • Preserve identity and credential boundariesForward only credentials intended for the target MCP protected resource. Never pass an inbound token through to a downstream API. Downstream access uses a separate credential flow owned by the MCP server or an approved identity broker.
  • Propagate trace context and record decisionsKeep correlation across the host, gateway, MCP server and downstream call. Record routing and policy decisions without logging bearer tokens, cookies, secrets or unrestricted tool arguments.
  • Fail closed on ambiguous routesReject unknown servers, inactive catalogue records, unsupported versions, malformed routing metadata and policy failures. Do not silently fall back to a broader server or a less restrictive route.
  • Isolate availability failuresUse bounded timeouts, connection limits, circuit controls and health information so one slow or failing MCP server does not exhaust the shared ingress tier.

The gateway cannot prove

  • A gateway is not a core MCP primitiveThe core participants are hosts, clients and servers. A transparent gateway may remain deployment infrastructure outside those roles. A terminating or aggregating gateway assumes client or server responsibilities for the MCP interaction it terminates and must not present its own behaviour as a core protocol guarantee.
  • A gateway is not the enterprise approval catalogueRuntime routing configuration may be generated from approved catalogue records, but a route table is not a complete ownership, version, evidence or retirement record.
  • A gateway is not the MCP serverIt cannot replace server-side input validation, resource URI checks, tool access controls, downstream authorisation, output sanitisation or business integrity rules.
  • Headers do not prove that a call is safeMcp-Method and Mcp-Name expose routable metadata. They do not describe all arguments, affected records, user intent or operational impact.
  • A catalogue approval is not perpetual trustAn approved record can become stale as schemas, dependencies, credentials, ownership or risk change. Live enforcement and periodic review remain necessary.
  • A gateway cannot make token passthrough validTokens must be issued for and validated by the intended MCP resource. The server must use separate credentials when it calls downstream APIs.
  • Aggregation creates a new responsibility boundaryIf a gateway merges tool lists, rewrites names, translates schemas or returns results as one MCP endpoint, it is performing server-like behaviour that requires its own contracts, versioning, conformance tests and ownership.

Enterprise approval catalogue

The enterprise approval catalogue is not a runtime substitute for protocol discovery.

Keep registry metadata, enterprise approval and live capability evidence distinct. The official MCP Registry and other registries can provide server distribution metadata. An enterprise approval catalogue may reference or import that metadata, but it remains a separate record of internal approval, ownership and environment-specific controls.

  • Record IDStable enterprise identifier independent of display name or deployment URL.
  • Server identity and ownerApproved server name, accountable business owner, technical owner, support team and escalation route.
  • Canonical server URIThe exact protected-resource identifier and approved endpoint or endpoints per environment.
  • Source and provenanceInternal build, approved supplier or metadata referenced from the official MCP Registry or another registry, with repository, package or artefact reference where applicable.
  • Release versionThe deployable server release governed by the record; never infer compatibility from a moving latest tag.
  • Protocol supportSupported MCP revisions, required extensions and any documented legacy compatibility.
  • Transport profilestdio, Streamable HTTP or an explicitly reviewed custom transport, including endpoint and network boundary.
  • Authorisation profileProtected-resource metadata, issuer, accepted audiences, scope model, client types and downstream credential boundary. No secrets belong in the record.
  • Capability inventoryApproved tools, resources and prompts, including names, risk class, owning system and expected human decision points.
  • Schema fingerprintEnterprise governance hash over the canonicalised capability contract, including name, input schema and output schema where present, used to detect an unreviewed contract change. This is a TechOne governance control, not an MCP protocol field.
  • Schema evidenceThe canonical contract artefact, fingerprint algorithm and normalisation rules required to reproduce the recorded fingerprint.
  • Data classificationThe highest data class each capability may access or return, with residency and retention constraints.
  • Operational profileTimeouts, rate limits, dependencies, service objective, telemetry destination and runbook.
  • Lifecycle stateProposed, assessed, approved, active, restricted, deprecated, retired or rejected, with effective date and decision owner.
  • Replacement and retirementSuccessor record, migration deadline, client notification plan, credential revocation and evidence-retention requirements.
  • Review evidenceArchitecture, security, privacy, conformance, acceptance and operational review references appropriate to the risk.

Schema change ruleA changed fingerprint opens a review; it does not by itself determine whether the change is compatible. Review must classify additions, removals, renamed capabilities, schema constraint changes, changed descriptions that alter model selection, and any increase in data or action scope.

Runtime ruleCompare the approved record with deployment evidence and live discovery at release time and on a defined review cadence. If the active endpoint exposes an unknown capability or incompatible schema, restrict or withdraw the route until the difference is understood.

Capability states

Approval is a state, not a one-off meeting.

These are governed states with permitted transitions, not a mandatory linear sequence. A capability may be restricted or rejected at different points before it is deprecated or retired.

  • State

    Proposed

    The entry state in a branching lifecycle. An owner has submitted a server or release record, but no enterprise use is authorised.

    Allowed: Design review, isolated development and non-sensitive conformance testing.Exit evidence: Named owners, architecture, capability inventory, initial schemas, data classification and intended consumers support a transition to Assessed. A proposal that cannot meet the baseline moves to Rejected.
  • State

    Assessed

    Architecture, security, data and operational reviews are complete enough for an approval or rejection decision.

    Allowed: Controlled pre-production tests with the approved identities, data and environment.Exit evidence: Resolved findings, test results, authorisation profile, schema fingerprints, runbook and rollback plan support a transition to Approved. Unresolved material risk can lead to Rejected.
  • State

    Approved

    The release and its declared capability surface are approved for a named environment and consumer set.

    Allowed: Deployment preparation and route activation under the approved conditions.Exit evidence: Change decision, deployment artefact identity, effective date and accountable approver support activation. A new finding returns the release to assessment or prevents activation.
  • State

    Active

    The approved endpoint is available through its authorised route and is under operational monitoring.

    Allowed: Only the recorded versions, capabilities, principals, environments and policy conditions.Exit evidence: Operational review can retain Active status. A material change returns to assessment, while an incident, planned replacement or shutdown can branch to Restricted, Deprecated or Retired.
  • State

    Restricted

    Use is temporarily narrowed because of an incident, control gap, ownership issue or unreviewed change.

    Allowed: Explicitly named read-only capabilities, principals or diagnostic traffic only; everything else is denied.Exit evidence: Remediation evidence and re-approval can return the release to Active. Otherwise it moves to Deprecated or Retired.
  • State

    Deprecated

    Existing approved consumers have a time-limited migration window; new consumers are not admitted.

    Allowed: Existing recorded use until the retirement deadline, with heightened change restrictions.Exit evidence: Consumer migration, replacement validation, support closure and a confirmed shutdown support the transition to Retired.
  • State

    Retired

    A terminal state for this release. The route, credentials and deployment are disabled and the record is retained for evidence.

    Allowed: No production calls.Exit evidence: Route removal, credential revocation, endpoint shutdown, consumer confirmation and retained audit references close the lifecycle. Reintroduction requires a new proposal.
  • State

    Rejected

    A terminal decision for this proposal because it was not approved or cannot meet the required controls.

    Allowed: No enterprise deployment or route.Exit evidence: A new proposal must address the recorded decision; rejection is not silently overwritten.

Named accountability

Every capability needs an owner, an operator and evidence.

RoleResponsibilityEvidence
Business capability ownerDefines the legitimate outcome, eligible users, unacceptable actions, human decision points and measures of value.Approved purpose, capability scope, risk classification, user population and acceptance scenarios.
MCP server ownerOwns protocol conformance, capability contracts, validation, server-side access control, downstream calls, output handling, releases and support.Versioned code or artefact, schemas, tests, dependency record, runbook, release notes and incident ownership.
Gateway or platform ownerOwns ingress availability, route configuration, edge policy, metering, trace propagation, isolation and recovery of the shared tier.Route-as-code, policy tests, capacity evidence, dashboard, alerting, recovery test and approved change history.
Enterprise approval catalogue custodianMaintains the record model, approval state, provenance, schema evidence, ownership completeness and retirement history.Immutable decision history, validation rules, stale-record reports and reconciliation with active routes and deployments.
Identity and security ownerApproves issuer, audience, scopes, client registration, credential storage, network controls, token separation and security monitoring.Threat model, authorisation tests, protected-resource metadata, issuer configuration, policy decisions and incident procedures.
Downstream system ownerApproves the native API operations, data access, service identity, transaction behaviour, limits and support impact exposed through the MCP server.API contract, permission grant, test tenant evidence, limits, change notice route and revocation procedure.
Operations or SRE ownerMonitors availability and performance, responds to incidents, validates rollback and confirms that telemetry is sufficient without exposing secrets.Service objectives, dashboards, alerts, on-call route, rollback exercise, post-incident record and capacity review.
Risk, privacy and legal reviewersReview the specific data, user, supplier and regulatory implications assigned by internal policy; they do not approve protocol conformance by proxy.Scoped findings, conditions, expiry or review date and accountable internal approval where required.

Changes that require an explicit gate

ChangeTriggerChecksEvidence
New server or first enterprise routeA previously unapproved MCP endpoint, supplier, package or internal server is proposed.Ownership, provenance, protocol support, transport, authentication, capability inventory, data classes, schema fingerprints, downstream permissions, failure tests, telemetry and retirement path.Approved catalogue record, architecture and threat model, conformance and acceptance results, runbook and route-as-code change.
Additive capability or schema changeA tool, resource or prompt is added, or an optional field or enum value expands the contract.New privilege, model-selection effect, name collision, compatibility, data exposure, rate impact, client caching and updated tests.New fingerprint, contract diff, classification decision, acceptance tests and approved release record.
Breaking contract changeA capability is removed or renamed, a required field changes, constraints narrow, output shape changes or behaviour is no longer compatible.Affected consumers, parallel versioning, migration window, route or name strategy, rollback and retirement of the former contract.Consumer inventory, migration plan, dual-run or compatibility test, effective date and deprecation notice.
Privilege or impact increaseRead becomes write, write becomes destructive, accessible records expand, approval is removed or a broader downstream identity is introduced.Business necessity, least privilege, scopes, human approval, separation of duties, rollback, transaction controls and incident containment.Fresh security and business approval, negative tests, exact permission diff and updated risk record.
Authorisation or identity changeIssuer, audience, client registration, scopes, token handling or downstream credential flow changes.Protected-resource metadata, issuer and audience validation, step-up behaviour, token separation, revocation and affected clients.Authorisation-flow test, configuration review, secret-rotation evidence and rollback plan.
Endpoint, transport or gateway route changeCanonical URI, environment endpoint, transport, gateway, region or route policy changes.Resource indicator, TLS, DNS and redirect behaviour, allowlists, latency, availability, cancellation, header/body validation and telemetry continuity.Route diff, connectivity and failure tests, updated approval-catalogue record and post-change verification.
Protocol baseline or extension changeThe server adds or removes a supported MCP revision or optional extension.Client compatibility, fallback behaviour, deprecated features, schema and error changes, conformance suite and operational rollback.Compatibility matrix, conformance results, client validation and approved release notes.
Deprecation and retirementA server, release or capability is no longer strategic, supported, compliant or safe.Consumer inventory, successor, migration deadline, route closure, credential revocation, endpoint shutdown and evidence retention.Deprecation decision, consumer acknowledgements, completed migration, disabled route and retained retirement record.
Emergency restrictionAn incident, vulnerability, ownership loss or unexplained schema difference creates immediate risk.Minimum safe capability set, affected principals, containment route, communication, evidence preservation and restoration criteria.Incident decision, temporary policy, active restriction verification and time-bound remediation owner.

Commercial route

Decide whether an MCP gateway is justified.

We review hosts, servers, trust boundaries, shared controls and operating ownership. The output is a direct-versus-gateway decision and a proportionate governance model.

Request an MCP architecture reviewExplore the complete MCP architecture

Primary sources

Protocol claims are grounded in official sources.

The source list distinguishes core protocol requirements, optional extensions and external implementation guidance. The surrounding enterprise control model is a TechOne architecture recommendation.

  1. MCP core specificationNormative protocol baseline and links to core protocol, server features, transports, authorisation and versioning.
  2. MCP architecture overviewHost, client and server roles; data and transport layers; tools, resources and prompts as protocol primitives.
  3. MCP transport overviewTransport responsibilities, Streamable HTTP, per-request metadata, mirrored HTTP routing metadata and the body as source of truth.
  4. MCP protocol release notesStateless protocol operation and the Mcp-Method and Mcp-Name routing headers for Streamable HTTP.
  5. MCP authorisation specificationProtected-resource roles, resource indicators, audience validation, scope guidance and the prohibition on accepting or transiting tokens intended for other resources.
  6. MCP security best practicesConfused-deputy, token-passthrough, SSRF, state-handle, local-server and authorisation security considerations.
  7. MCP versioning and compatibilityPer-request protocol versioning, server discovery, extension negotiation and compatibility with earlier handshake-based revisions.
  8. Official MCP Registry referenceThe official public registry API and server metadata model.
  9. Introducing the MCP RegistryThe distinction between the public MCP Registry and public or private sub-registries built for organisation-specific criteria.

Direct answers

Questions that expose the hidden architecture decision.

Is an MCP gateway part of the MCP core protocol?

No. MCP defines hosts, clients and servers, together with protocol primitives such as tools, resources and prompts. A transparent gateway can route, meter and enforce edge policy as enterprise deployment infrastructure. A gateway that terminates an MCP interaction, originates new requests or aggregates capabilities assumes the corresponding client or server responsibilities. Its additional behaviour remains an enterprise architecture choice, not a core protocol guarantee.

What is the difference between an MCP gateway and an MCP server?

An MCP server exposes protocol capabilities and owns their contracts, validation, access control and downstream behaviour. A transparent gateway forwards requests to approved servers and applies shared infrastructure controls without becoming an MCP participant. If a gateway terminates the MCP interaction, originates new requests, or merges, renames or rewrites capabilities at its own endpoint, it takes on client or server responsibilities that require explicit contracts, governance and testing.

What is the difference between a gateway, the official MCP Registry and an enterprise approval catalogue?

The gateway is in the runtime request path. The official MCP Registry and other registries provide distribution metadata for finding server implementations. The enterprise approval catalogue records which servers, releases, owners, endpoints and capability surfaces the organisation has approved for a specific environment. Catalogue approval can configure or constrain routes, but the catalogue does not execute tools and registry presence is not enterprise approval.

Can a gateway route MCP calls without parsing the JSON-RPC body?

For current Streamable HTTP, infrastructure can route and meter requests using MCP-Protocol-Version, Mcp-Method and Mcp-Name where defined. An intermediary that inspects Mcp-Name must decode its Base64 sentinel form before comparison and must not create a different identity through gateway-only normalisation. The body remains the source of truth, and the MCP server must reject a request when mirrored headers and body disagree. Headers expose routing metadata, not the full business meaning or safety of a call.

Is schema fingerprinting required by MCP?

No. Schema fingerprinting is an enterprise governance control proposed here to detect changes in approved capability contracts. The organisation must define canonicalisation and hashing rules, retain the source schema and review the semantic change; a fingerprint alone does not establish compatibility or safety.

Should the enterprise approval catalogue replace live MCP discovery?

No. The catalogue records what the enterprise approved, while live discovery reports what an endpoint currently exposes. Release and periodic controls should compare the two. An unexplained capability or schema difference should restrict the route until it is reviewed.

When is a direct MCP connection preferable to a gateway?

A direct connection can be preferable when one approved host connects to a small number of servers inside an existing trust boundary and endpoint controls already provide identity, authorisation, limits and audit evidence. A gateway becomes more useful when many hosts and servers need consistent destination control, metering, trace correlation and operational isolation.

Can the gateway forward a user token to the downstream business API?

No. The MCP server must accept only tokens intended for its protected resource, and token passthrough to a downstream API is forbidden. Downstream access requires a separate credential or delegated flow designed for that API and governed by the server and identity architecture.

What must happen when a server is retired?

Stop new consumers, identify and migrate existing ones, remove the active route, revoke credentials, shut down the endpoint, close support ownership and retain the approval decision and required audit evidence. Deleting a catalogue entry alone does not retire a deployed server.