
ActTrace
- 1 repo stars
- Updated May 20, 2026
- goww7/acttrace
io.github.goww7/acttrace is a MCP server that classifies AI systems under the EU AI Act and generates Article 50 transparency notices.
About
ActTrace MCP server gives developers a narrow, high-leverage EU AI Act toolkit inside their coding agent. When you embed models into customer-facing flows, you need a disciplined view of risk classification and the transparency language Article 50 expects; ActTrace exposes those steps as MCP tools over stdio via acttrace-mcp on PyPI at version 0.1.0. founders shipping agents, APIs, or SaaS copilots use it during Ship security reviews to structure governance conversations before launch, especially when legal budget is thin but EU exposure is real. The registry metadata highlights eu-ai-act, compliance, and article-50 tags, signaling developer-tool plus compliance positioning rather than full legal advisory. You still validate outputs with counsel; ActTrace accelerates drafting and classification loops in Claude Code or Cursor. Pair it with broader obligation servers when you also track US state laws or healthcare rules.
- Classifies AI systems under the EU AI Act risk tiers from MCP tool calls
- Generates Article 50 transparency notice content for user-facing disclosure workflows
- PyPI acttrace-mcp v0.1.0 with uvx-friendly stdio transport
- Publisher tags include eu-ai-act, article-50, risk-classification, ai-governance, and compliance
- Focused EU scope—complements broader multi-framework servers like GovernMy for Colorado or HIPAA topics
ActTrace by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add acttrace-mcp -- uvx acttrace-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 1 |
|---|---|
| Package | acttrace-mcp |
| Transport | STDIO |
| Auth | None |
| Last updated | May 20, 2026 |
| Repository | goww7/acttrace ↗ |
What it does
Classify your AI product under the EU AI Act and draft Article 50 transparency notices from the agent via ActTrace MCP before you publish AI-facing UX.
Who is it for?
Best when you're targeting EU users and need structured EU AI Act classification and transparency drafting from MCP tools during pre-launch reviews.
Skip if: Products with zero EU exposure seeking only US HIPAA/SOX coverage, or teams wanting certified legal opinions without human review.
What you get
After adding acttrace-mcp over stdio, your agent can produce EU AI Act risk classifications and Article 50 notice drafts you refine before go-live.
- EU AI Act risk classification output for your described AI system
- Draft Article 50 transparency notice text for user-facing channels
- Repeatable governance MCP workflow documented at https://github.com/goww7/acttrace
By the numbers
- Registry version 0.1.0; PyPI identifier acttrace-mcp; stdio transport with uvx runtime hint
- Publisher-provided tags: eu-ai-act, ai-act, compliance, ai-governance, article-50, transparency, risk-classification
- Repository and website: https://github.com/goww7/acttrace
README.md
ActTrace
A developer-facing EU AI Act compliance API for non-financial SaaS and technology companies. ActTrace gives an engineering team three things, self-serve, over an API or via MCP:
- A deterministic risk classification of an AI feature under the EU AI Act.
- A ready-to-ship Article 50 transparency notice.
- A free diagnostic as the public entry point.
Not legal advice. ActTrace provides operational compliance workflow support and documentation drafts. It does not provide legal advice, does not certify compliance, and does not replace review by qualified counsel. Every response carries this disclaimer.
ActTrace is scoped for non-financial companies. Financial-services use
cases (banking, trading, portfolio/investment advice, credit scoring, …) are
deliberately classified out_of_scope_financial_services.
Install — Claude Code plugin / MCP server
ActTrace ships as a Claude Code plugin: an acttrace skill plus a local MCP
server. The MCP server runs via uvx — a deterministic rules engine, offline,
no API key.
/plugin marketplace add goww7/acttrace
/plugin install acttrace@acttrace
Then ask Claude "Is my chatbot EU AI Act compliant?" or "Write an Article 50
notice for our support assistant." The MCP server also runs standalone with
any MCP client: uvx acttrace-mcp.
Quickstart
python3 -m venv .venv && .venv/bin/pip install -r requirements.txt
.venv/bin/uvicorn acttrace.app:app --reload --port 8080
# 1. Free diagnostic — no key needed
curl -s localhost:8080/api/acttrace/diagnostics/free -H 'content-type: application/json' -d '{
"feature_name": "AI reply assistant",
"description": "Drafts suggested customer support replies for agents.",
"user_facing": true, "model_provider": "OpenAI", "use_case": "support_assist"
}'
# 2. Mint an API key
KEY=$(curl -s -XPOST localhost:8080/api/keys/generate | python3 -c 'import sys,json;print(json.load(sys.stdin)["api_key"])')
# 3. Classify (15 tokens)
curl -s localhost:8080/api/acttrace/classify -H "X-API-Key: $KEY" -H 'content-type: application/json' -d '{
"feature_name": "AI reply assistant",
"description": "Drafts customer support replies shown to agents.",
"use_case": "support_assist", "user_facing": true, "model_provider": "OpenAI"
}'
# 4. Generate an Article 50 notice (10 tokens)
curl -s localhost:8080/api/acttrace/notices -H "X-API-Key: $KEY" -H 'content-type: application/json' -d '{
"ai_system_name": "Support Copilot", "notice_type": "chatbot", "tone": "plain"
}'
Endpoints
| Method & path | Auth | Tokens | Purpose |
|---|---|---|---|
POST /api/acttrace/diagnostics/free |
none | 0 | Public risk diagnostic |
POST /api/acttrace/classify |
key | 15 | Documented risk classification |
POST /api/acttrace/notices |
key | 10 | Article 50 transparency notice |
POST /api/keys/generate |
none | 0 | Issue a free-plan key |
GET /api/health |
none | 0 | Liveness |
Auth is X-API-Key. Responses carry X-Request-ID, X-Plan,
X-Tokens-Charged, X-Tokens-Remaining, X-RateLimit-*. Errors are
structured {"code","message","detail"} (401/403/429).
MCP
python -m acttrace.mcp_server --sse --port 8002 exposes two tools —
acttrace_classify and acttrace_generate_transparency_notice — authenticated
with the same X-API-Key. A Claude Code skill is in skill/acttrace/.
Tests
.venv/bin/python -m pytest -q
54 tests: classification engine (7 acceptance fixtures), conflict guard, notice generator, and HTTP API contract.
Deploy
docker-compose.yml builds a standalone two-container stack (API + MCP) on
ports 8080 / 8002 with its own volume — isolated from FinanceData2. To go live,
append caddy-acttrace.snippet to the shared Caddyfile (replace the
placeholder domain). See BLUEPRINT.md for the full build contract.
Layout
acttrace/
app.py config.py dependencies.py
middleware/ api_key_auth.py
routers/ acttrace.py keys.py
services/ acttrace_service.py acttrace_classification_service.py
acttrace_notice_service.py acttrace_constants.py
api_key_service.py
repositories/ acttrace_repository.py api_key_repository.py
schemas/ acttrace.py
mcp_server/ server.py __main__.py context.py tools/acttrace.py
skill/acttrace/ SKILL.md README.md
tests/
Recommended MCP Servers
How it compares
EU AI Act–specific classification and Article 50 MCP, not a full multi-framework compliance hub.
FAQ
Who is io.github.goww7/acttrace for?
It is for developers and small teams shipping AI systems who must address EU AI Act risk classification and Article 50 transparency during Ship security work.
When should I use io.github.goww7/acttrace?
Use it before launch when you define user-facing AI disclosure, document system risk tier, or prep transparency copy alongside product and legal review.
How do I add io.github.goww7/acttrace to my agent?
Install acttrace-mcp v0.1.0 from PyPI with uvx stdio per repository instructions and register the server in your MCP client configuration.