Back to the registry
Agent passport

A2A Protocol Implementation on Bedrock AgentCore - Multi-Agent Systems

Kriv AI · Cybersecurity & IT

No attestation published

Certification per AWS Marketplace.

Provenance reach3 of 12 layers traced

Evidence tier Source Confirmed · 4 captures on record

User ratingNot rated0 reviews on the listing
Runs onUnknownProfessional service
ProvenanceUnknown33% of the provenance layers this product can disclose
Evidence riskHighSign in to see the basis for this band.

What the publisher says

As described on AWS Marketplace.

**Agent-to-Agent (A2A) Protocol is Google's open specification (2024) for agent interoperability, complementing Anthropic MCP. MCP is agent-to-tool; A2A is agent-to-agent: Agent Card publication, AgentSkill metadata, capability negotiation, task delegation, streaming (SSE), cross-vendor interop. Enterprises with multi-agent architectures (orchestrator → specialist chains) require A2A to reduce vendor lock-in and enable cross-account, cross-BU coordination.**

AWS added A2A server support for Bedrock AgentCore Runtime (Nov 2025). Linux Foundation A2A includes 150+ orgs incl. Microsoft, AWS, Salesforce, SAP, ServiceNow. Few A2A protocol integration PS listings exist on AWS Marketplace today — creating a first-mover window.

Show the rest of the publisher’s description (23 more lines)

Existing listings (IBM watsonx Orchestrate, IBM Consulting Advantage, Accenture/Deloitte/PwC offerings, LangGraph/CrewAI implementations) are not A2A-protocol-specific or are high-cost bespoke services ($75K–$500K+). N35 is positioned as first dedicated fixed-fee A2A Protocol Integration SKU on AWS Marketplace.

**A2A components**

Agent Card + AgentSkill definitions; capability negotiation; task delegation (context + aggregation); SSE streaming; JSON-RPC 2.0 transport; OAuth 2.1 + JWT + mTLS auth; IAM Identity Center integration; per-skill ACLs; OpenTelemetry + X-Ray tracing; MCP + A2A interop (MCP = tools, A2A = agents); orchestration patterns (fan-out, sequential, hierarchical, mesh); Cloud Map discovery.

**Reference architecture**

Orchestrator + specialist agents on Bedrock AgentCore (cross-account via PrivateLink/VPC). AgentCore Identity for auth. AgentCore Gateway exposes A2A endpoints. API Gateway + App Mesh routing. CloudWatch + OpenTelemetry + X-Ray observability. EventBridge async events. SageMaker Model Monitor for quality. Bedrock Model Invocation Logging for audit + traceability.

**Use cases**

Healthcare (E4, N23, E3, N33): clinical orchestrator → imaging, lab, CDS, PHI de-ID, billing.

Financial services (N14, N17, N24): trade orchestrator → KYC, AML, credit risk, compliance, surveillance.

**Week-by-week delivery**

W1 Scoping (architecture; Agent Card + AgentSkill; orchestration selection).

W2 Orchestrator + 1 specialist on AgentCore + A2A baseline.

W3 Discovery + delegation + SSE streaming; Foundation closes (30-day warranty).

W4 Standard: up to 5 specialists; MCP + A2A interop; OAuth 2.1 + JWT + mTLS; OpenTelemetry + X-Ray.

W5 Eval (N29) + per-agent cost attribution + handoff (45-day warranty).

W6–7 Enterprise: 10+ agent federation; cross-account A2A; regulated overlay (HIPAA §164.308(a)(1)(ii)(D); SR 11-7 via N24).

W8 Enterprise: N26 + N27 + N31 integration; 60-day hypercare.

**Three tiers**

Foundation $75K (5 wk; 2-agent A2A; Agent Card + AgentSkill registry; OAuth 2.1; 30-day warranty) for Series C–E + Fortune 1000 pilots.

Standard $135K (6 wk; up to 5 specialists; A2A + MCP; OAuth 2.1 + JWT + mTLS; OpenTelemetry + X-Ray; eval harness; cost attribution; 45-day warranty).

Enterprise $200K (8 wk; 10+ agents; cross-account A2A; HIPAA/SR 11-7 overlay; N26/N27/N31; 60-day hypercare). Optional Extra Specialist $25K.

**Important disclosures**

Kriv does NOT develop customer agent logic; deploys A2A infrastructure for customer-authored agents. Does NOT operate A2A post-deployment unless under managed retainer. No SOC 2 / HIPAA / HITRUST / ISO / 42001 certification claims. No legal/regulatory advice. A2A is emerging standard — breaking changes may require remediation. No AgentCore API stability guarantee. AWS + Anthropic + Bedrock costs separate. Regulated overlay does NOT replace dedicated engagements (HIPAA → E3 + N23; SR 11-7 → N24). CPN is not endorsement.

EDP-eligible — engagement fees ($75K–$200K) count toward your AWS Enterprise Discount Program commitment (up to 25%). Structure via Marketplace private offer for EDP alignment. Contact info@kriv.ai or +1-732-433-5564.

Highlights

Highlighted by the publisher on AWS Marketplace.

First A2A Protocol Integration Professional Services SKU on AWS Marketplace — AgentCore A2A server support GA November 2025.** MCP standardizes agent-to-tool; A2A standardizes agent-to-agent. 150+ organizations in Linux Foundation A2A, Microsoft (Azure AI Foundry + Copilot Studio), AWS (AgentCore Runtime), Salesforce, SAP, ServiceNow shipping production. Pure first-mover window of 6–9 months before Deloitte / Accenture / IBM ship dedicated A2A SKUs.

Agent Card publication + AgentSkill registry + capability negotiation + task delegation + streaming responses via Server-Sent Events + JSON-RPC 2.0 transport per A2A specification + OAuth 2.1 + JWT + mTLS cross-agent auth + MCP + A2A interop (agents expose tools via MCP governed by N26, call peers via A2A) + OpenTelemetry + AWS X-Ray cross-agent distributed tracing + orchestration patterns (fan-out / sequential / hierarchical / peer-to-peer mesh) + AWS Cloud Map agent discovery.

AWS Select + Anthropic CPN — use cases: healthcare clinical-orchestrator → specialist agents (imaging/lab/CDS/PHI-de-id/billing); FS trade-orchestrator → specialist agents (KYC/AML/surveillance/credit/compliance).** Three tiers: Foundation $75K (2-agent A2A, 5 wk); Standard $135K (5 specialists + MCP interop + observability, 6 wk); Enterprise $200K (10+ agents + regulated overlay + N26/N27/N31 integration, 8 wk).

Agent build and provenance

See the full provenance

The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.

Compliance

Government
  • FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27

Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.

Vendor

External enrichment · as of 2026-08-29

CompanyKriv AIAutomated
Websitehttps://www.kriv.ai/

Sources

Marketplace listingaws.amazon.comSource
App certificationaws.amazon.comSource

Publisher resources

3 links
Kriv AI Capabilities Overviewkriv.aiSource
Kriv AI on AWS Marketplace (Seller Profile)aws.amazon.comSource
Anthropic Claude Partner Networkwww.anthropic.comSource

Linked repositories

RepositoriesUnknownUnknown

Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.

Pricing
Unknown
Not stated
Delivery
Professional service
**Primary contact.** info@kriv.ai · +1-732-433-5564 · https://kriv.ai/support **Response SLA.** First response within 2 US business days (Mon–Fri 9 am – 6 pm ET, ex-US federal holidays). Active engagements: Engagement Lead within 4 business hours weekdays. Scale-driven multi-agent launches compress to same business day. **Onboarding SLA.** First customer contact within 2 US business days of buyer inquiry / private-offer acceptance. Kickoff within 2–3 weeks of SOW; 5–10 business days scale-driven. **Escalation.** (1) Engagement Lead (named in SOW) → (2) Practice Director (info@kriv.ai) → (3) CEO Abhinav Dangri (info@kriv.ai). **Communication.** Dedicated Microsoft Teams channel; weekly 60-min video checkpoint; Friday written status. Customer SMEs 3–5 hrs/week (Head of AI Platform, Head of ML Engineering, VP Engineering, CAIO, CTO, Head of Enterprise Architecture, CISO, Head of SRE). **Handoff.** Word/Excel/PDF in customer secure share; Agent Card + AgentSkill registry as JSON + Git repo; A2A transport client/server scaffolds as Python / TypeScript; OAuth 2.1 + JWT + mTLS as JSON + Terraform / CDK; OpenTelemetry + X-Ray instrumentation as CloudFormation; orchestration patterns as AgentCore / Step Functions templates. **Out of scope.** Does NOT develop Customer agent business logic. Does NOT operate A2A post-deployment (unless Managed Service retainer). Issues no certifications. No legal / regulatory / compliance advice. **A2A is an emerging open specification, breaking changes may require Customer-side remediation.** No AgentCore API stability guarantee. Regulated overlay at Enterprise does NOT replace E3 / N23 / N24 engagements. **AWS + Anthropic-side billing.** AWS infrastructure + Anthropic API + Bedrock Claude consumption separate. **Holiday coverage.** Closed on US federal holidays.
Open the source listing ↗

Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.