AI Act Radar vs Melta UI
A side-by-side look at the AI Act Radar and Melta UI MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose AI Act Radar for legal work; choose Melta UI for legal as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose AI Act Radar when
- You need dedicated capabilities in the Legal domain.
- You have the keys it needs:
AIA_SECRET.
Choose Melta UI when
- You need dedicated capabilities in the Legal domain.
- You prefer a local stdio subprocess transport.
- You want tools like
get_token, get_component, check_rule.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Legal | Legal |
| Quality signal | 31/100 · Emerging | 69/100 · Great |
| Install command | Not confirmed yet | Confirmed |
| Transport | — | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | AIA_SECRET | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 202 |
| Directory activity | 0 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | Not listed | 6 |
| Full listing | View AI Act Radar | View Melta UI |
Tools & capabilities
AI Act Radar tools
No tool names declared yet. Check the project README from the listing page.
Melta UI tools 6
get_tokenGet a design token by dot-path. Returns the token object with its value and class mapping.get_componentGet component metadata including variants, sizes, accessibility requirements, HTML sample, per-state specs (stateSpecs: disabled/loading/open/empty etc. — each with delta class strings + aria changes), and anatomy parts (overlay/container/th etc. with element/roles/class). Prefer these structured fields over inferring states from the HTML sample.check_ruleCheck class strings against this design system's prohibition rules. Returns violations with reasons and alternatives.check_htmlLint a full HTML/JSX source against melta-ui rules — the same checks as CI and the PostToolUse hook (class rules + html-attr rules + composition rules for HTML). Use this AFTER generating UI code to self-verify before presenting it. Response always includes coverage info (manual rules cannot be auto-checked).searchSearch across tokens and components by keyword. Matches against names, values, class strings, and descriptions. Returns up to 20 results (truncated flag when more matched).get_rulesGet melta-ui prohibition rules from rules.json (107 total). Use this to retrieve manual/contextual rules that check_rule cannot auto-detect. Supports filtering by category, severity, or detector.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
AI Act Radar
No confirmed install command for AI Act Radar yet — follow the setup steps linked from its listing page rather than a guessed package name.
Melta UI
{
"mcpServers": {
"melta-ui": {
"command": "npx",
"args": [
"-y",
"melta-ds-mcp"
]
}
}
}
Frequently asked questions
AI Act Radar is categorized under Legal and uses an install path we have not confirmed yet. Melta UI belongs to Legal and uses a local stdio subprocess. Pick AI Act Radar for legal work and Melta UI for legal.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. AI Act Radar has no confirmed install command yet — follow its own setup instructions.
AI Act Radar has no declared pricing — check the project's own site. Melta UI has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add ai-act-radar and melta-ui as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, AI Act Radar has a quality signal of 31/100 (Emerging) with 0 views, 0 installs and 0 GitHub stars. Melta UI has 69/100 (Great) with 4 views, 0 installs and 202 GitHub stars.