MCP.Market

Rightis MCP server

online · 100% uptime
by Backers-Shawn·io.github.Backers-Shawn/rightis·v1.0.0

Identity-rights registry lookups before AI generation: is a face, voice or persona registered?

A91/100grade A
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Rightis yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Rightis tools (3)

write = sends, deletes, buys or posts
  • registry_infoFree

    How Rightis works for AI services: what the public lookup answers, how to get a partner key for licensing, usage logging and persona policy, and where the machine-readable signals live. Call it first when you are unsure how to use the registry.

  • rights_lookupFree

    Check whether a person or character is registered with Rightis by rights_id (BR-XXXX-XXXX-XXXX) and which AI uses they allow, require approval for, or refuse. do_not_train=true means their data must not be used for training. Call this before generating a likeness, voice or persona of a real person.

  • rights_searchFree

    Find registered identities by display name (Korean or English). Returns rights_id and the public permission summary for each match. Use it when you only have a name, before asking for a rights_id.

Public scan report

scanner v0.1.10 · 2026-10-09 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1432ms20/20
  • Tool poisoning3 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Rightis compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 85% of 48,255 servers
Tools
3
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
253 ms
faster than 55% of 30,031 servers

What its tools let an agent do: 3 read

Install Rightis in Claude Code, Cursor or VS Code

claude mcp add --transport http rightis https://rightis.org/api/public-mcp/mcp
Add to Cursor

What the publisher says

From the Rightis repository's README, as published. We do not edit it. Read it on GitHub

rightis-js

Use this before your code generates a real person's face, voice or persona. Image, video and voice models, face swap, voice cloning, AI avatars and chat personas of real people or registered characters: ask Rightis first, on the server, before the generation call.

Rightis is a public registry of identity rights. People and rights holders register a likeness and say which AI uses they allow, want to approve, or refuse. This repository is the JavaScript SDK and CLI.

30-second quickstart

npm install @rightis/sdk
npx rightis check BR-XXXX-XXXX-XXXX --use "instagram ad" --asset face --public
import { Rightis } from '@rightis/sdk';

const rightis = new Rightis(); // server only; reads RIGHTIS_SECRET_KEY, keyless without it
const result = await rightis.rights.check({
  rights_id: 'BR-XXXX-XXXX-XXXX',
  use_type: 'instagram ad',
  ai_methods: ['image_generation'],
  asset_types: ['face'],
  territory: ['US'],
});
console.log(result.decision, result.next_action.type, result.next_action.url);

Read next_action, not just decision:

A failed lookup is not "not registered": on any RightisError, do not generate. The SDK deliberately ships no boolean that turns a decision into "go ahead".

Only have a name? rightis.rights.search('name') returns listed registrations with their Rights ID. No match is not clearance.

For AI coding assistants

.claude/skills/rightis/SKILL.md in your project (or ~/.claude/skills/rightis/).

  • Claude Code skill: skills/rightis/SKILL.md. Copy it to

.cursor/rules/ in your project.

  • Cursor rule: .cursor/rules/rightis.mdc. Copy it to

own AGENTS.md or CLAUDE.md.

  • Codex and other agents: AGENTS.md, including a snippet to paste into your

rightssearch, registryinfo).

  • Keyless MCP server: https://rightis.org/api/public-mcp/mcp (rights_lookup,

Links

  • Developers: https://rightis.org/en/developers
  • Guide, generating real people: https://rightis.org/en/developers/guides/real-person-likeness
  • SDK reference: packages/sdk/README.md
  • CLI reference: packages/cli/README.md

Sandbox

npx rightis login                                   # browser sign-in (OAuth with PKCE)
npx rightis init                                    # sandbox key into .env.local, plus an example file
npx rightis people                                  # the sandbox sample people
npx rightis check BR-SANDBOX-... --use "social media ad" --asset face
node --env-file=.env.local rightis-example.mjs      # the same check from code

Develop

pnpm install
pnpm -r build
pnpm -r test
pnpm -r typecheck

Node 20 or later. Point the SDK and CLI at a local server with RIGHTISAPIURL=http://localhost:3000 (or --base-url).

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Rightis: common questions

Is Rightis MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Rightis safety report
How do I install Rightis?
It runs remotely at rightis.org. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Rightis need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Rightis maintained?
The last commit was 26 days ago (2026-10-09). The latest release is v1.0.0.
Is Rightis up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Rightis compare with other MCP servers?
safety score 91/100 (higher than 85% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.