ONE PRODUCT · FOUR COMPONENTS

Verosek Gateway handles it all.

AI Gateway routes every LLM call. MCP Tools execute every action under per-key access control. Shield scans every request, response, and tool output. Audit Vault signs every step. They share identity, share the trace, and ship as one binary.

01

Component spotlights

What each component actually ships.

Each card lists the concrete numbers, the things it does, and a sample of the endpoints it serves. Click through for the full deep-dive.

Component 01

AI Gateway

Same SDK. Any model. Any provider.

15 endpoints< 30 ms P99 overhead3 / 3 SDK coverage
  • Twelve OpenAI endpoints + native Anthropic /v1/messages + native Gemini /v1beta
  • Cross-SDK translation: Claude through OpenAI SDK, GPT through Anthropic, etc.
  • Per-model parameter quirks normalised (max_completion_tokens, system→developer)
  • Virtual keys: budget, TTL, rotate, revoke, audit binding (vsk_… / vkr_…)
  • Weighted routing, priority fallback, 3-fail cooldown

Endpoints (sample)

  • POST /v1/chat/completions
  • POST /v1/messages
  • POST /v1beta/models/{model}:generateContent
  • POST /v1/embeddings
  • PATCH /api/v1/keys/{key_ref}
  • POST /api/v1/keys/{key_ref}/rotate
Read the AI Gateway deep-dive

Component 02

MCP Tools

Tools your agents can use. Safely.

10 GA connectors6 access-rule types2 transports
  • Postgres, MySQL, MongoDB, Redis, Elasticsearch, GitHub, GitLab, Filesystem, Slack, Stripe
  • Per-(key, connection, tool) access rules: allowlists, blocklists, max_rows, max_amount_cents
  • Argument rewriting (LIMIT injection, PII redaction) recorded as MODIFY in trace
  • LLM + tools loop OR MCP-only via /mcp (Claude Desktop / Cursor / VS Code)
  • Connection credentials encrypted with AES-256-GCM at rest

Endpoints (sample)

  • POST /mcp (JSON-RPC: tools/list, tools/call)
  • POST /api/v1/tool-access
  • GET /api/v1/keys/{key_ref}/tools
  • PATCH /api/v1/connections/{connection_id}
Read the MCP Tools deep-dive

Component 03

Shield

Twelve checks. Every request scanned.

CHK-001…024 scanners4 profiles6 PII languages
  • Scan points: pre-LLM, post-tool, post-LLM, session-drift
  • Modes per check: off / log_only / enforce — graduate when false-positives drop
  • fail_closed default for prompt injection; fail_open for advisory checks
  • Multilingual PII engine + 17 secret regex patterns (AWS, GitHub, Stripe, …)
  • Custom PII recognizers via POST /api/v1/security/custom-pii

Endpoints (sample)

  • GET /api/v1/security/profiles
  • GET /api/v1/security/policies/{profile_name}/export
  • POST /api/v1/security/policies/import
  • POST /api/v1/security/topics
Read the Shield deep-dive

Component 04

Audit Vault

Every step signed. Every decision explainable.

10 TraceStep typesHMAC-SHA256 signing0 network calls offline
  • SessionTrace per request: ordered TraceSteps + aggregate counters + signature
  • Decision receipts for every BLOCK / MODIFY / TERMINATE / HOLD verdict
  • Offline verify with verosek-verify-receipt CLI (stdlib-only, no network)
  • NIST AI RMF + EU AI Act evidence bundles drawn from real trace data
  • Constant-time HMAC compare; canonical JSON serialisation; receipt_version tag

Endpoints (sample)

  • GET /api/v1/traces
  • GET /api/v1/traces/{trace_id}/verify
  • GET /api/v1/security/receipts/{trace_id}
  • GET /api/v1/security/compliance/{framework_id}
Read the Audit Vault deep-dive
02

Capability matrix

What overlaps, what doesn’t, in one table.

Identity, the audit trace, and offline operation are universal. Per-call decisions and payload rewriting are concentrated in MCP and Shield.

CapabilityGatewayMCPShieldAudit
Per-key identity (vsk_…)
Per-call enforcement decision
Argument / payload rewriting
Writes to the signed audit trace
Off-the-hot-path async work
Offline / air-gap clean
Survives gateway restart
AES-256-GCM at rest
HMAC-SHA256 signed
NIST AI RMF evidence
EU AI Act evidence

One product. Four components. Zero integration gap.

FAIL_CLOSED by default. Every tool call scanned. Every decision signed.