# mcp.arkforge.tech — software development services — 1 of 5

Home > Browse > By type > saas > mcp.arkforge.tech

> Probe-verified (tier 2 of 3). Last checked 2026-09-26. 1 of 5 capability checks passed. 2 unknown.

- host: mcp.arkforge.tech
- url: https://mcp.arkforge.tech/
- category: software development services
- type: saas

## Probe-verified · tier 2 of 3

Probed live on 2026-09-26 against rubric v1.2. 1 of 5 checks passed. 2 unknown.

- UNKNOWN — Markdown negotiation (`Accept: text/markdown`)
- UNKNOWN — Markdown twin at a predictable URL (`/page.md`)
- FAIL — llms.txt (`/llms.txt`)
- FAIL — API catalog (`RFC 9727`)
- PASS — MCP endpoint answers tools/list (`initialize → tools/list, no credentials`) · on 26 Sep 2026
  - PRESENT — MCP server card (`/.well-known/mcp/server-card.json`): present; its server answers; not scored
  - Platform-supplied: no; not scored
- PASS — Other agent files at well-known paths (`agent-skills/index.json · oauth-authorization-server · oauth-protected-resource · http-message-signatures-directory`): found: OAuth authorization server metadata, OAuth protected resource metadata; not scored

MCP tools (from tools/list on 2026-09-26): scan_project, check_compliance, generate_report, suggest_risk_category, generate_compliance_templates, generate_compliance_roadmap, generate_annex4_package, certify_compliance_report, validate_api_key, register_free_key, gdpr_scan_project, gdpr_check_compliance, gdpr_generate_report, gdpr_generate_templates, combined_compliance_report, get_pricing

## Unverified actions

Read from the page's own content, with the wording each was drawn from. Inference is kept separate from tested facts; an agent completing the action is tier 3.

- **register** — "" → `https://mcp.arkforge.tech/register`

## Summary

Automated compliance scanner for the EU AI Act that analyzes AI codebases, scores documentation, generates compliance roadmaps, and produces auditor-ready Annex IV evidence packages for AI developers before the August 2, 2026 deadline.

## Context

2370 sites in this index share the category "software development services"; 246 are transactional.

## How we grade

- tier 1 — **Declared**: The site says agents are welcome in its robots.txt. A permission, not a capability.
- tier 2 — **Probe-verified** (this site): We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule.
- tier 3 — **Behaviourally verified**: An agent completed the action end to end — booked, bought, submitted — and it worked.

## About this record

Known Good probes sites live and publishes what was tested and when.
Method: https://knowngood.sh/about.md · Rubric: https://knowngood.sh/benchmark

How we found this site: probe discovery. This site didn't declare agent access — we found it by checking the open web. Everything above was tested the same way, against the same rubric, on the date shown. [How we choose what to check, and how to opt out](https://knowngood.sh/bot)

## Where this sits

- saas: https://knowngood.sh/type/saas
- software development services: https://knowngood.sh/category/software-development-services
- legal services (also in): https://knowngood.sh/category/legal-services
- AI consulting agencies (also in): https://knowngood.sh/category/ai-consulting-agencies
- Browse: https://knowngood.sh/browse
- Rubric: https://knowngood.sh/benchmark