Skip to main content
Glama

SovereignRoute + AP2 (io.github.srigenmedia/sovereign-route)

mcptry

India DPDP/RBI Geo-Pinned <5ms LLM Router with AP2 Mandates, x402/MPP Billing & 12% FinOps (https://route.srigenmedia.com)

SovereignRoute routes AI inference across Indian sovereign cloud endpoints (asia-south1, ap-south-1, asia-south2, ap-south-2), scrubs regulated Indian PII in volatile request memory before upstream dispatch, enforces cryptographic AP2 (Intent -> Cart -> Payment) mandates, and caps runaway agent spend atomically.

Endpoints

  • FinOps Cockpit: https://route.srigenmedia.com

  • Streamable HTTP MCP Endpoint: https://route.srigenmedia.com/mcp

  • OpenAI-Compatible Chat Completions: https://route.srigenmedia.com/v1/chat/completions

  • Health Check: https://route.srigenmedia.com/health

Related MCP server: llm-guard-gateway

MCP Client Configuration (mcp_config.json)

{
  "mcpServers": {
    "sovereign-route": {
      "type": "streamable-http",
      "url": "https://route.srigenmedia.com/mcp",
      "headers": {
        "Authorization": "Bearer ${SOVEREIGN_ROUTE_API_KEY}"
      }
    }
  }
}

Available MCP Tools

  1. route_classify_prompt — Scrub regulated Indian PII in volatile memory, classify prompt complexity in <5ms, and resolve a DPDP/RBI geo-pinned upstream region.

  2. route_get_savings_ledger — Inspect live RouteBudgetCoordinatorDO daily/monthly USD spend and freeze state.

  3. route_verify_ap2_mandate — Verify an Ed25519 or ES256 chained AP2 Intent -> Cart -> Payment mandate bundle against TTL, ceiling, and D1 anti-replay nonces.

  4. route_trigger_budget_freeze — Atomically freeze/unfreeze a tenant spend coordinator and dispatch a <50ms Kavach KYA kill-switch sync.

14-Day Shadow Audit & License

See docs/14-day-shadow-audit.md for the 14-day zero-risk shadow audit guide and SECURITY.md for our zero-PII and fail-closed security architecture. Released under the MIT License.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Privacy-preserving AI gateway. Sanitises PII before prompts reach Anthropic / OpenAI / your LLM, then emits a signed cryptographic certificate per call (Ed25519 + RFC 3161 + Sigstore Rekor). EU GDPR + AI Act ready. Free tier 500/mo with BYOK.
      1
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides a governance gateway for LLM and agent traffic via MCP, blocking prompt injection, redacting PII, enforcing per-tenant token budgets, and caching repeat questions semantically. Enables AI agents to route model calls through the same guardrails instead of calling providers directly.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to call external endpoints under per-endpoint policy enforcement, with credentials and personal data kept inside a hardware enclave and every allowed or denied attempt recorded to an immutable audit ledger.
      2
      ISC
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables self-hosted AI gateway and agent control plane with governed MCP tools, virtual-key budgets, caching, and audit, supporting OpenAI, Anthropic, Gemini, MCP, and A2A protocols. It provides deterministic prompt enhancement and governed execution with a zero-credential first run.
      10
      Apache 2.0