Claude MarketplacesSubmit
srotzin avatar

HiveLaw

srotzin/hivelaw

If you're building AI agents that need to stay compliant with the EU AI Act, this server gives you three audit operations: score outputs for hallucination liability (0-100 scale with risk tiers), verify compliance stamps, and pull agent audit history. It's built on a compliance rules engine that classifies outputs and issues tamper-proof certificates you can present for regulatory reporting. The streamable-http transport means you can call hivelaw_audit_output before responses hit users, get a liability assessment, and decide whether to gate the output. Useful if you're shipping agents in regulated contexts and need a verifiable paper trail.

tools
3
transport
HTTP
last updated
Apr 14, 2026
View on GitHub

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

hivelaw_audit_outputAudit an AI agent's output for hallucination liability under the EU AI Act. Returns a liability score (0-100), risk tier, compliance flags, and recommendations

Audit an AI agent's output for hallucination liability under the EU AI Act. Returns a liability score (0-100), risk tier, compliance flags, and recommendations

No parameter schema in public metadata yet.

hivelaw_verify_stampVerify that a compliance stamp is valid and not expired. Agents present stamps to prove they passed auditing

Verify that a compliance stamp is valid and not expired. Agents present stamps to prove they passed auditing

No parameter schema in public metadata yet.

hivelaw_agent_historyGet the compliance audit history for a specific agent. Returns past audits with scores and flags

Get the compliance audit history for a specific agent. Returns past audits with scores and flags

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

HiveLaw

AI Compliance Auditing — MCP Server

HiveLaw is a Model Context Protocol (MCP) server that audits AI agent outputs for hallucination liability, issues verifiable compliance stamps, and tracks audit history.

MCP Tools

HiveLaw exposes the following MCP tools via GET /v1/mcp/tools and POST /v1/mcp/call:

ToolDescription
hivelaw_audit_outputAudit an AI agent's output for hallucination liability under the EU AI Act. Returns a liability score (0-100), risk tier, compliance flags, and recommendations
hivelaw_verify_stampVerify that a compliance stamp is valid and not expired. Agents present stamps to prove they passed auditing
hivelaw_agent_historyGet the compliance audit history for a specific agent. Returns past audits with scores and flags

Endpoints

  • GET /v1/mcp/tools — List available MCP tools
  • POST /v1/mcp/call — Execute an MCP tool by name
  • POST /v1/contracts/create — Generate a legal contract
  • GET /v1/compliance/status — Check compliance status

Use Cases

View the full README on GitHub

Details

Repository
github.com/srotzin/hivelaw
Website
www.hiveagentiq.com
Transport
HTTP
Registry
MCP registry, active

More from srotzin