ComplyEdge Python SDK

Runtime EU AI Act Article 5 and Article 50 enforcement. Open source.

Choose the Right Package

complyedge is the Python client for the hosted ComplyEdge runtime API. It enforces policy decisions in your application and records the resulting evidence trail. For an offline command-line linter with no API key, use TrustLint instead.

• ComplyEdge package
• TrustLint package
• Documentation
• Trust portal

Installation

pip install complyedge

Quick Start — EU AI Act in Three Lines

from complyedge import compliance_check

@compliance_check(jurisdiction="EU", agent_id="my-agent")
def my_agent(prompt):
    return llm.generate(prompt)  # every input and output checked

That's it. Every input and output is checked against the EU AI Act rule corpus (Article 5, Article 50, GPAI). Violations are blocked before they reach the user, with legal citation, rule ID, and timestamp on every check.

Classifiers (eu-ai-act-* MCPs) score the system. ComplyEdge denies this prompt or output now. Article 50 here is unlabeled or deceptive use, not C2PA watermarking.

pip install complyedge
pip install trustlint
pip install 'complyedge[mcp]'
pip install 'complyedge[agents]'
npx -y @complyedge/mcp
claude mcp add complyedge -- npx -y @complyedge/mcp

OpenAI Agents extra (hosted path; needs COMPLYEDGE_API_KEY): from complyedge.agents import create_compliance_guardrail

GitHub Action: uses: complyedge/trustlint-action@v1

GOPAL is an OPA library in your process. ComplyEdge is per-request deny + citation + trust page + MCP.

The decorator reads your API key from the COMPLYEDGE_API_KEY environment variable by default. Pass api_key_env="MY_VAR" to use a different one.

Multi-Jurisdiction Enforcement

jurisdiction selects which rule corpus is evaluated server-side.

@compliance_check(jurisdiction="EU", agent_id="hr-screening")
def hr_screening(candidate: str) -> str:
    return llm.generate(candidate)

Per-rule scoping (e.g. only Article 5) is planned but not yet exposed in the SDK — all rules for the selected jurisdiction run today.

Additional Installation Options

# Development setup
pip install complyedge[dev]

# Local development from source
pip install -e ./sdks/python

Client API — Without the Decorator

from complyedge import ComplyEdge

ce = ComplyEdge(api_key="your-key")
result = ce.check("AI-generated content", jurisdiction="EU")

if result.allowed:
    print("Content approved")
else:
    for v in result.violations:
        print(f"{v.rule_id}: {v.citation}")

Or the global convenience functions:

from complyedge import is_safe, check
import os

api_key = os.environ["COMPLYEDGE_API_KEY"]

# Boolean check
if not is_safe(text, api_key=api_key, jurisdiction="EU"):
    raise ValueError("Compliance violation")

# Full result
result = check(text, api_key=api_key, jurisdiction="EU")

MCP Server — Use ComplyEdge as an AI Agent Tool

Agent/MCP tools that check prompts and outputs against ComplyEdge’s TrustLint corpus with article-cited findings — not another EU AI Act risk-tier chatbot and not a law-search database.

Hosted Streamable HTTP (preferred for remote / Smithery Toolbox): https://mcp.complyedge.io/mcp

npx -y @smithery/cli@latest mcp add complyedge/complyedge --client cursor

Local stdio for any MCP-compatible host (Claude, Cursor, Inspector):

pip install 'complyedge[mcp]>=0.2.8'
python -m complyedge.mcp_server
# or: complyedge-mcp

Add to your MCP client config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "complyedge": {
      "command": "complyedge-mcp"
    }
  }
}

(command/args with python -m complyedge.mcp_server is also valid.)

Exposed tools (TrustLint offline YAML corpus):

No API key is required for these tools. The optional extra installs mcp and trustlint (engine + bundled rules). This MCP path does not run the REST API policy engine.

Documentation

• Quick start
• API reference
• Browser playground
• Trust badge setup