Ansvar Gateway - Cited Legal & Compliance MCP for AI Agents
Ansvar Systems · Cybersecurity & IT
Certification per AWS Marketplace.
Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
## Cited Legal Answers for AI Agents
Ansvar Systems (Sweden) operates gateway.ansvar.eu, an MCP gateway that gives AI agents cited access to European and US law. Connect the AI assistant your team already uses - Claude, ChatGPT, Copilot, Cursor, or any MCP client - via OAuth and query 49 live jurisdictions. Every answer carries paragraph-level citations to the official publisher.
Show the rest of the publisher’s description (27 more lines)
## What You Get
- 340,000+ national laws with 5.8 million individually citable provisions, plus EU regulations and technical standards
- 49 live jurisdictions across Europe and the US; the audited index at ansvar.eu/coverage shows the current set
- Paragraph-level citations linked to the official publisher on every answer
- Case law, preparatory works, and authority guidance on premium plans
- Compliance workflows: threat modeling (STRIDE/LINDDUN, TARA), DPIA, and gap analysis for NIS2, DORA, CRA, GDPR, and the EU AI Act
- Audit-ready output: full citation trails a reviewer can check against the source text
## How It Works
- Subscribe on AWS Marketplace. The subscription is free and no payment runs through AWS.
- Create your Ansvar account with Google, Microsoft, or email sign-in.
- Add gateway.ansvar.eu to your MCP client and approve the OAuth prompt. Setup guides for each client are at docs.ansvar.eu.
- Ask your first question: "Using Ansvar, what does NIS2 Article 21 require of a medium-sized SaaS provider?"
## Fail-Closed Accuracy
The gateway puts correctness above availability. If a source is unreachable, you get an explicit error instead of an uncited model guess. Compliance documentation and audit preparation depend on answers you can verify, so every served row names its source, publisher, and license.
## Compliance Workflows
Beyond retrieval, structured workflows produce reviewable deliverables:
- Threat modeling with STRIDE, LINDDUN, and TARA methodologies, grounded in cited legal context
- Data Protection Impact Assessments grounded in the applicable regulation
- Gap analysis for NIS2, DORA, CRA, GDPR, and the EU AI Act with article-level references
Each output includes the citation chain, so reviewers can verify claims against the source text. The free plan includes one watermarked workflow run per month to judge the output quality; paid plans unlock the full catalog and workflows on your own uploaded documents.
## Security and Hosting
- EU-hosted infrastructure, GDPR-compliant by design, DPA available
- TLS 1.2+ on all endpoints; OAuth 2.1 client access
- Every served corpus passes a source-licensing audit before it goes live
- ISO 27001:2022: ISMS implemented; certification audit targeted Q3 2026
## Get Started
The free plan (100 searches per day, one workflow run per month, self-serve sign-up) lets your team evaluate citation quality before paying. Paid plans are billed by Ansvar Systems at ansvar.eu. Setup documentation: docs.ansvar.eu.
Highlights
Highlighted by the publisher on AWS Marketplace.
Paragraph-level citations across 49 live jurisdictions: 340,000+ national laws and 5.8 million provisions, plus EU regulations (GDPR, NIS2, DORA, CRA, AI Act) and technical standards. Every answer links to the official publisher, so a reviewer can check any claim against the source text. Case law, preparatory works, and authority guidance are available on premium plans.
Compliance workflows built in: threat modeling (STRIDE/LINDDUN, TARA), DPIA, and NIS2/DORA/CRA/GDPR/AI Act gap analysis, each producing reviewable output with full citation trails. Works with Claude, ChatGPT, Copilot, Cursor, and any other MCP client over OAuth. No SDK and no custom integration required.
Fail-closed by design: an unreachable source returns an explicit error, never an uncited model answer. EU-hosted, DPA available, and every served corpus is source-licensing audited. ISO 27001:2022 ISMS implemented; certification audit targeted Q3 2026. Free plan: 100 searches per day and one workflow run per month, self-serve sign-up.
Preview
3 images
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
- 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
Plans and pricing as listed
1 listed- Units
Refund terms
As stated by the publisher on AWS Marketplace.
This product is free of charge on AWS Marketplace; no fees are collected through AWS, so refunds do not apply. Paid subscriptions purchased directly from Ansvar Systems (outside AWS Marketplace) are governed by the terms at https://ansvar.eu/terms.
Sources
Publisher resources
4 linksLinked repositories
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.
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.