Product

One appliance, five connected stages, on your infrastructure

MERIDVAR combines an enterprise AI governance layer with an admission gateway that can refuse an AI request before the model provider is contacted. You install it and you operate it. There is no MERIDVAR cloud.

  • Software you install and operate
  • Runs on a Docker host on your private network
  • One appliance for one organisation
  • Nothing is sent to MERIDVAR
MERIDVAR consoleIllustrative

Gateway decision Refused

A request carrying a national identification number, sent from the console playground.

01 identitypass
02 shadow-aipass
03 prompt-dlprefused: national identifier
04 to 17skipped
Provider calls
0
Stored sample
Masked

The refusal names the rule that caused it. Nothing was sent, and nothing is billed.

The path of a request

What enters, what is checked, and what is left behind

  1. What enters

    A request arrives through the OpenAI-compatible API, the console playground or the proxy path.

  2. What is analysed

    The whole request is read: string content, content blocks, system messages, tool call arguments and tool results.

  3. Where policy applies

    A pipeline of seventeen stages applies your policy, from identity and shadow AI to prompt DLP, data residency, budgets and approved models.

  4. What is blocked

    Any licensed, enforcing stage may refuse. Every later stage is skipped, the provider is never called and nothing is billed.

  5. What is allowed

    An admitted request is sent to Anthropic, OpenAI, Azure OpenAI, xAI or a self-hosted model endpoint.

  6. What is recorded

    Each decision is written to an append-only, hash-chained log, ready for an audit package. Findings keep masked samples.

The five stages

Discover, assess, approve, control and prove

Every capability below is documented as shipped in the current release.

01 Discover

What AI is in use?

  • AI inventory. A register of AI systems observed in traffic or declared by a person, each with its provenance, owner, purpose, vendor, models and lifecycle status.
  • Shadow AI discovery. Traffic compared with your list of sanctioned providers, in off, observe or enforce mode. Proxy and DNS logs can be uploaded for traffic that never touched the gateway.
  • Agents and MCP servers. An agent registry with signed identities, and a declared MCP server inventory with tool-level risk. Endpoint agents report local AI tools.

AI security

MERIDVAR consoleIllustrative

AI inventory

Systems that this appliance observed in traffic or that a person declared.

AI systemProvenanceStatus
Support reply assistantObserved in gateway trafficCandidate
Contract summariserDeclared by an operatorDeclared
Unsanctioned chat serviceFound in an uploaded proxy logCandidate
Legacy translation botDeclared by an operatorRetired

An observation never becomes a declaration on its own. A person confirms it.

02 Assess

How risky is it?

  • Versioned questionnaires. Three questionnaires ship with the product: an AI system baseline, AI vendor due diligence, and an AI agent and MCP server review. A published version never changes.
  • Rules-based risk classification. Low, Moderate, High or Critical, from published rules, with a reason code for every factor. The same facts always give the same level.

AI risk

MERIDVAR consoleIllustrative

Risk classification High

Computed by published rules from the completed baseline assessment.

FactorSourceReaches
Personal data can reach itAssessment answerModerate
A linked MCP server has a tool that can deleteMCP inventoryHigh
Use for training is unknownUnknown is never read as safeModerate

This level requires a privacy review, a security review and an approved vendor before approval can be requested.

03 Approve

Who approved it, and until when?

  • Reviews and approvals. Privacy and security reviews with findings and conditions. Approval with separation of duties, a pinned basis and an end date.
  • Vendor governance. Each vendor’s own classification and approval, and every AI system that depends on that vendor.

AI governance

ReviewsIllustrative

Support reply assistant

Each review records the reviewer’s decision, with findings, conditions and the next review date.

Privacy review2 findings, 1 conditionNo objection
Security reviewTool and MCP access: gapNo objection
Vendor approvalHolds until its end dateApproved

A privacy review is not a DPIA. A security review is not a certification. The console says so on the page.

04 Control

What is allowed through?

  • Admission gateway. A seventeen-stage pipeline: prompt DLP in ten categories, threat detection, data residency, vendor requirements, team budgets, approved models, OIDC and agent signatures.

AI security

Gateway policyIllustrative

Policy

Edited in the console. Enforced on every routed request.

Shadow AI discoveryOffObserveEnforce
National identification numbersBlockRedactAllow and log
Payment cardsBlockRedactAllow and log
Email addressesBlockRedactAllow and log
Residency when the region is unknownFails closed
Team budget capHardSoft

05 Prove

Can we prove it?

  • Evidence and audit. An append-only, hash-chained log with optional Ed25519 signatures, an integrated status for each subject and a downloadable audit package.

Compliance

Audit packageIllustrative

Support reply assistant

One downloadable package for each AI system and each vendor.

Governance stateIncluded
Classifications, reviews and approvalsIncluded
Assessments, with the questionnaire versions answeredIncluded
Evidence records, with hash, previous hash and signatureIncluded
Public signing keysIncluded

The package states what it does not prove.

The product views on this site are illustrative, with invented example data. They show behaviour documented for the current release and are not screenshots of a customer environment.

How control works

Three ways in, one pipeline, and a refusal that never leaves your network

Any licensed, enforcing stage of the pipeline may refuse. After a refusal, every later stage is skipped, the provider is never called and nothing is billed. The refusal names the rule that caused it.

OpenAI-compatible API
What an SDK, a coding assistant or an agent framework uses. Streaming is supported.
Console playground
For testing and demonstrating a policy before it meets real traffic.
Proxy capture
A PAC file and HTTP CONNECT, for traffic that nobody pointed at the gateway on purpose.
Whole-request scanning
String content, content blocks, system messages, tool call arguments and tool results.
Live dispatch
Anthropic, OpenAI, Azure OpenAI and xAI, plus a self-hosted model endpoint.

Architecture

Where MERIDVAR sits

MERIDVAR reference architectureCallers on the customer network reach AI providers through the MERIDVAR appliance, which runs five connected stages: discover, assess, approve, control and prove. Security, privacy, risk, finance and audit teams read one shared record. Nothing leaves the customer network for MERIDVAR.Your networkOutside your networkPeopleA token for each personAI applicationsOpenAI-compatible APIAI agentsSigned identitiesMCP serversDeclared inventoryUnmanaged trafficPAC file and proxy captureMERIDVAR applianceOne organisation, one appliance, and no control plane in our cloud01DiscoverInventory and shadow AI02AssessQuestionnaires and risk rules03ApproveReviews and approvals04ControlAdmission gateway05ProveEvidence log and audit packageModel providersAnthropic, OpenAI, Azure OpenAI, xAISelf-hosted modelsYour own endpointSaaS AI servicesSeen through uploaded logsAdmitted requests onlyNo telemetry to MERIDVARRuns without internet accessOne shared recordSecurityPrivacyRisk and complianceFinanceAuditEvery team that answers for AI reads the same appliance: visibility, policy, control, evidence and spend.
Controls apply to traffic routed through the gateway. Visibility of other traffic depends on uploaded logs, endpoint agents and declarations.

Compared

The same questions, asked of a cloud-delivered control and of MERIDVAR

QuestionCloud-delivered AI controls, typicallyMERIDVAR
Where is prompt content inspected?On the vendor’s infrastructureOn your network
Where do governance records live?On the vendor’s platformOn your volume
Is there a new processor in the data path?YesNo
Does it operate without internet access?NoYes, once installed, including licensing and signed updates
How is it tenanted?Multi-tenantSingle-tenant appliance

This compares typical deployment architectures, based on public vendor documentation. Several vendors also offer customer-operated components. It is not a legal claim.

What we have measured

The product is held to the same standard of evidence

Zero calls on refusal

23 gateway tests were run against a provider that logs every request it receives. Every refusal made zero calls, and every admission made exactly one.

No identifier in the clear

Prompt DLP findings keep masked samples. The raw identifier is not stored.

Offline updates

A signed incremental update was applied to a real appliance with no internet access. Licences were verified on the appliance.

Governance at scale

The status of 5,000 AI systems was computed in about 70 milliseconds.

Deployment model

You run it, and you keep everything it records

MERIDVAR is delivered as software you install and operate. The architecture is the assurance: what never leaves your environment cannot be exposed by ours.

Self-hosted
The appliance runs on a host you control, inside your own network.
Single-tenant
One appliance serves one organisation. No other tenant’s data sits beside yours.
Customer-controlled
Your policies, your keys and your evidence, on your volume. You decide who has access.
No vendor cloud
There is no MERIDVAR control plane in our cloud and no new data processor in your AI data path.
No vendor telemetry
The appliance sends us nothing. With no integrations configured, it makes no external calls.
Able to run offline
Once installed, it runs without internet access, including signed licences and signed updates.

See MERIDVAR refuse a request on your own network

A working session with the founder, on a host you control.

What happens next

  1. You send the formYour request goes straight to the founder.
  2. We reply by emailWe agree a time and what you want to see.
  3. We run a working sessionWe install the appliance with you, route a test request through it and read the evidence it leaves.