MCP.Market

Lunara Intelligence MCP server

online · 100% uptime
by lunarasociety.com·com.lunarasociety/intelligence·v1.0.0
No reviews yet

EU AI Act and SB 942 obligations for AI systems: each date, the article setting it, signed sources

B77/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Lunara Intelligence yet.

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

Lunara Intelligence tools (5, 1 write)

write = sends, deletes, buys or posts
  • lunara_applicabilitywrite actionFree

    Runs Lunara's published applicability model against a description of an AI deployment and returns which obligations reach it, which do not, and why. Answer only what you actually know — every input accepts "unsure", and an unsure is never resolved in the direction that manufactures an obligation. The model can and does conclude that nothing binds the asker.

  • lunara_citeFree

    Returns a citation block for one obligation: status, effective date, instrument, article, penalty, primary source, amending act, evidence classification and the time the tense was computed. Use this when you are about to state a regulatory date or requirement to someone, so the claim carries its source.

  • lunara_integrityFree

    Reports whether the documents this server fetched carry a valid Ed25519 signature from Lunara Society, and returns the digests and key material needed to check that independently. Use it when the answer matters enough that the provenance of the source does: a corpus served from a mirror, a cache or a snapshot is not covered by the transport security of the original fetch, and this is what covers it instead.

  • lunara_obligationsFree

    The regulatory obligations Lunara Society tracks, with tense computed at the moment of the call. Each carries the instrument, the article that sets the date, a link to primary law, and any amending act. Use this to answer "what is in force", "what is coming", or "what does instrument X require" rather than recalling dates from training data — several of these have been amended, one of them five days before it would have applied.

  • lunara_verifyFree

    Checks whether a business carries Lunara Shield certification. Returns verified, not_registered or revoked. IMPORTANT: not_registered is not a negative signal about the business — it means the verification process has not been completed, which is true of most organisations. Do not present it as a warning. Reading the registry is free and unauthenticated by design.

Public scan report

scanner v0.1.10 · 2026-10-12 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 791ms20/20
  • Tool poisoning5 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identitynamespace and repository owner differ; website matches verified namespace5/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Lunara Intelligence compares

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

Safety score
77/100
higher than 50% of 48,255 servers
Tools
5
the typical server has 7
Tools that change things
20%
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
240 ms
faster than 57% of 30,031 servers

What its tools let an agent do: 4 read · 1 change

Install Lunara Intelligence in Claude Code, Cursor or VS Code

claude mcp add --transport http intelligence https://luiqtimzcsoqnizybifs.supabase.co/functions/v1/lunara-mcp
Add to Cursor

What the publisher says

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

Lunara Society

Constitutional governance authority for the autonomous economy.

Lunara Society is the trust infrastructure layer between AI systems and the business world — the same way HTTPS became mandatory for web security, Lunara is becoming mandatory for AI-to-business trust.

What We Do

  • Shield Certification — Human-reviewed business identity and governance verification
  • Compliance Intelligence — Risk scoring for EU AI Act Article 50 and California SB 942
  • Public Registry — Free, open API for real-time entity verification
  • Constitutional Framework — Seven pillars of AI governance (CC BY 4.0)

Deadlines

Not restated here. No page on this site states a date; they live in one table that computes tense at the moment of reading, and are published at corpus/obligations.json.

The nearest one is worth naming anyway because most published summaries get it wrong: machine-readable marking under Article 50(2) falls due for generative systems already on the market on 2 December 2026 — the Omnibus grants four months, not six. See /marking.html, and the correction we published for having carried February ourselves.

Lunara Intelligence — the regulatory corpus

Every obligation this institution tracks, machine-readable, each carrying the instrument, the article that sets the date, and a link to primary law.

curl https://lunarasociety.com/corpus/obligations.json

No tense is stored. A static document does not know when it is being read, so it states application dates and callers compute "in force" against the moment of the call. The corpus is generated from a single obligation table in lunara-clock.js and the deploy fails while the two disagree — two hand-maintained tables mean two answers, which is the failure that produced our first published correction.

MCP server

POST JSON-RPC to https://luiqtimzcsoqnizybifs.supabase.co/functions/v1/lunara-mcp
(the npm package @lunara/mcp is written and tested but not published yet)

Four tools: lunaraobligations, lunaraapplicability, lunaracite, lunaraverify. Node 18+, zero dependencies, no key, no account.

It ships no bundled copy of the corpus and does not answer when the authority is unreachable. A cached table is how a server keeps confidently serving a date that was amended months ago. Source: mcp/server.mjs — one file, readable in full by whoever is deciding whether to trust it.

Registry API — free & open

curl -X POST https://luiqtimzcsoqnizybifs.supabase.co/functions/v1/lunara-registry/shieldRegistryLookup \
  -H "Content-Type: application/json" \
  -d '{"domain": "example.com"}'

No authentication required. Full spec: openapi.yaml

AI Discovery Files

Shortened. The full README is on GitHub.

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

Lunara Intelligence: common questions

Is Lunara Intelligence MCP server safe?
Mostly: it is graded B (77/100). Read the Lunara Intelligence safety report
How do I install Lunara Intelligence?
It runs remotely at luiqtimzcsoqnizybifs.supabase.co. 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 Lunara Intelligence need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Lunara Intelligence maintained?
The last commit was 23 days ago (2026-10-12). The latest release is v1.0.0.
Is Lunara Intelligence up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Lunara Intelligence compare with other MCP servers?
safety score 77/100 (higher than 50% of 48,255 servers); tools 5 (the typical server has 7); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.