NOMOS
REMOTE · WWW.NOMOSPROTOCOL.COM
Ask a sealed authority whether an action may proceed. Answers are deterministic and citable.
Available components
Last scanned (20 hours ago)
Scores higher than 56% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2207 tokens (~315/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management47
- Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (12)
- TLS certificate
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Nov 26 0
- “ask_authority” reworded the description of “inputs” cosmetic
1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.
- 14 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Nov 26 0
- Tool “detect_contradictions” rewrote its description, which is the text the model reads security
- Schema quality: 1760 → 2210 ▼ functional
- New tool “ask_by_context” functional
- 11 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://www.nomosprotocol.com/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=*.nomosprotocol.com | CN=YR2,O=Let's Encrypt,C=US | 12 Oct 2026 | 10 Jan 2027 | RSA 2048 | SHA256-RSA | 64e142d677196bc718f629c64a86cb94eec |
| SANs: *.nomosprotocol.com, nomosprotocol.com | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of www.nomosprotocol.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| nomosprotocol.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| content-security-policy | default-src 'self';script-src 'self' 'nonce-RBouirHqPMXiTpIvGQ1s6w==';style-src 'self' 'unsafe-inline' https://fonts.googleapis.com;font-src 'self' https://fonts.gstatic.com;img-src 'self' data: blob:;connect-src 'self' https://nomosprotocol.com https://nomosprotocol.com https://www.nomosprotocol.com;frame-src 'none';object-src 'none';upgrade-insecure-requests;base-uri 'self';form-action 'self';frame-ancestors 'self';script-src-attr 'none' |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | no-referrer |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://www.nomosprotocol.com/api/mcp | Verified | 200 | |
| http (plaintext) | http://www.nomosprotocol.com/api/mcp | HTTPS enforced | 308 | https://www.nomosprotocol.com/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
ask_authority ~533
Query a published authority on the NOMOS Exchange marketplace — a different system from verify_decision's own sealed policies. Every public authority (e.g. eu-ai-act.nomos) is queryable with no key. Returns the authority's own verdict (AUTHORIZED/DENIED/ESCALATED), the exact rule and reason, and a permanent, cryptographically-bound transcript (query_id + url) — replayable evidence, not just a reply. Nothing is invented or paraphrased: the verdict is the authority's sealed rules evaluated against your inputs. The default response is a short, curated summary (verdict, matched rule, source citation when the artifact has one, transparency/completeness disclosures, transcript link) — not the full rule-by-rule evaluation trace. Set include_evaluation_trace: true to get that complete diagnostic record when you or the user actually need it.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Optional label for what this query represents, for the caller's own transcript record (e.g. "pre-deployment check"). Purely descriptive — does not affect the verdict. |
| acts_for | string | – | Optional organisation the agent acts for. Recorded as declared; when an Exchange key is used, the key's account is recorded instead. |
| agent_id | string | – | Optional stable name for the agent asking (e.g. "acme-credit-agent"). Recorded on the transcript and shown in the authority's public history as who relies on it. |
| authority | string | yes | The Exchange artifact's standard name — its short slug, optionally ".nomos"-suffixed (e.g. "eu-ai-act" or "eu-ai-act.nomos"), or its raw artifact ID. Browse the catalog at https://www.nomosprotocol.c… |
| exchange_api_key | string | – | Exchange API key (nxk_...). Optional for free/public queries. Required only for metered access to licensed (paid) authorities beyond their free allotment. |
| include_evaluation_trace | boolean | – | Set true to receive the full rule-by-rule evaluation trace (every rule checked, every missing field) instead of the default curated summary. Most callers never need this. |
| inputs | object | yes | Key/value facts to evaluate against the authority's rules (e.g. {"untargeted_facial_image_scraping": true}). Fields must match the authority's vocabulary — see the atlas endpoint or the artifact's ca… |
| purpose | string | – | Set "test" for test or evaluation queries: they are answered and sealed, but kept out of the authority's public history and counts. Defaults to production. |
| Name | Type | Req | Description |
|---|---|---|---|
| expected_fields | array | – | Present only when ESCALATED for lack of data — the fields this authority still needs |
| matched_rule_id | string|null | – | ID of the rule that determined the verdict — null when AUTHORIZED with no matching rule |
| matched_rule_name | string|null | – | Human-readable name/description of the matched rule — use this for display, not matched_rule_id |
| open_higher_priority_count | number | – | 0 means every relevant fact was known when this was sealed; >0 means facts were still missing above the matched rule |
| open_higher_priority_rules | array | – | The actual rules behind open_higher_priority_count (capped to 20) — use this to answer "which ones?" instead of guessing. Each has the rule name, what it would do if it matched, and exactly which inp… |
| query_id | string | – | Permanent transcript ID — reopen any time at the returned url |
| response_source | string | – | Provenance label — this is a sealed NOMOS verdict, not Claude's own reasoning. Preserve or restate this distinction when relaying the answer. |
| rules_evaluated | array | – | Only present when include_evaluation_trace was true |
| rules_evaluated_count | number | – | Total rules checked during evaluation — the size of the full trace, whether or not it was returned |
| source_reference | object|null | – | Citation for the matched rule, when the source document's structure was captured at extraction time. Names where the rule TEXT was extracted from (e.g. "Article 5"), not a legal claim about what it c… |
| url | string | – | Path to the permanent, shareable transcript for this query |
| verdict | string | – | The authority's own verdict |
| verdict_description | string | – | Human-readable reason — the exact rule and its consequence |
No examples provided.
ask_by_context ~416
Ask whether an action is allowed WITHOUT choosing the law yourself (NOMOS-SPEC-014). Describe where the act happens and who it involves; NOMOS works out from its signed registrar log which laws govern it, asks every one, and combines strictly: any deny denies, a yes needs every law. Prefer this over ask_authority whenever you do not already know which law applies: naming one law leaves out the others. Each law's own answer is a permanent, signed transcript (members[].query_id). If a fact that decides which law applies is missing, the answer is INSUFFICIENT_DATA with open_facts naming it: ask the user, never guess. A place the registrar does not cover is answered INSUFFICIENT_DATA, never as permission; say so plainly. Relay `coverage`: the registrar lists only its own laws, so other law may also apply.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Optional label for what is being done (e.g. "share_customer_data_with_analytics_vendor"), recorded on each transcript. |
| acts_for | string | – | Optional organisation the agent acts for. |
| agent_id | string | – | Optional stable name for the agent asking, recorded on each transcript. |
| context | object | yes | The facts that decide which law applies. Codes: EU (an EU member state), QA (Qatar), AE (the UAE outside free zones with their own data law), DIFC, ADGM, QFC, US, SA, and so on. |
| exchange_api_key | string | – | Exchange API key (nxk_...). Optional; needed only for licensed (paid) authorities. |
| inputs | object | – | Facts about the action itself, evaluated by every law that applies (e.g. {"processing_fair_and_transparent": true}). A law that needs a fact you did not give holds the answer open and names it. |
| purpose | string | – | Set "test" for test or evaluation queries: answered and sealed, but kept out of public history and counts. |
| Name | Type | Req | Description |
|---|---|---|---|
| answered_under | array | – | The laws the answer was computed under |
| authorized | boolean | – | True only when every applicable law authorizes; never true over an empty set of laws |
| coverage | string | – | What the answer covers; relay it to the user |
| deciding_authorities | array | – | The laws that decided the verdict |
| escalations | array | – | Each law that requires approval, with its escalation |
| members | array | – | Each law's own answer, with its permanent transcript (query_id) |
| mode | string | – | "resolution": the laws were worked out from the context, not chosen by the caller |
| open_facts | array | – | Facts to supply when the answer is held open |
| reason | string | – | Why, in words |
| resolution | object | – | How the laws were resolved (status, applicable, missing, proof with the log head consulted) |
| verdict | string | – | The strict combination of every applicable law's verdict |
No examples provided.
detect_contradictions ~200
Analyze policy documents (and optional behavioral decision logs) to detect contradictions, hidden rules, and gaps between declared policy and observed behavior. Stateless — no artifact is created and nothing is persisted. Returns contradictions of three types: rule_collision (two rules that apply to the same case with different decisions where the policy does not settle it soundly, each with that case and what the policy would do), ghost_term (an undefined standard such as "reasonable" in a rule's own text), and layer_divergence (a policy rule and a rule of practice that one case meets with different decisions); with behavioral logs, policy_gaps measured from the decisions.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | – | NOMOS API key (nmk_live_...). |
| behavioral_logs | array | – | Optional historical decision records. Enables layer_divergence detection — surfaces behavioral patterns that deviate from written policy. |
| documents | array | yes | Policy documents to analyze for contradictions. |
| Name | Type | Req | Description |
|---|---|---|---|
| contradictions | array | – | List of detected contradictions |
| hidden_rules | array | – | Rules inferred from behavior not in written policy |
| summary | string | – | Plain-language summary of findings |
| total_contradictions | number | – | Total contradictions found |
No examples provided.
find_authority ~207
Find which published authorities on the NOMOS Exchange govern something you are about to do, from a plain description (e.g. "deploy a recruitment model in the EU"). No name needed. Returns the matching authorities ranked, and for each the facts it reads that match your description (what to pass to ask_authority as inputs) and its most relevant rules with where they come from in the source. Also returns authorities others have requested that are not listed yet. Matches by words and by meaning (a small multilingual model on the server, so questions in Arabic and other languages work); it only chooses what to ask, never a verdict. Call this before ask_authority when you do not know the authority's name.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | yes | What you are about to do, in plain words. |
| jurisdiction | string | – | Optional jurisdiction tag to restrict to, e.g. "EU" or "AE". |
| limit | number | – | Maximum authorities to return (default 10). |
| Name | Type | Req | Description |
|---|---|---|---|
| matches | array | – | – |
| next | string | – | – |
| places | array | – | Jurisdictions the description names (e.g. AE for Dubai). An authority that covers none of them is not returned. |
| requested | array | – | Requested, not yet listed. |
| search | object | – | How the search ran: method "hybrid" (meaning and words) or "keyword", and the model used for meaning. |
No examples provided.
generate_governance ~257
Convert one or more policy documents into a sealed NOMOS governance artifact (.nomos). Extracts executable rules using Claude, detects contradictions between rules, computes an Autonomy Readiness Index (ARI) score (0–1), and cryptographically seals the result. Returns an artifact_id you can use with verify_decision immediately. Optionally accepts historical behavioral decision logs to add a behavioral evidence layer and reach CERTIFIED confidence tier.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | – | NOMOS API key (nmk_live_...). |
| behavioral_logs | array | – | Optional historical decision records (CSV rows as objects) for behavioral triangulation. Minimum 10 rows recommended. |
| documents | array | yes | Policy documents to extract rules from. Each item must have filename and content (plain text). |
| domain | string | – | Industry or domain hint (e.g. "lending", "hr", "e-commerce", "healthcare", "insurance"). Improves extraction accuracy. |
| name | string | yes | Human-readable name for the governance artifact (e.g. "Loan Approval Policy v2", "HR Leave Rules"). |
| organization | string | yes | Name of the organization this artifact governs (e.g. "Acme Bank", "HealthCorp"). |
| Name | Type | Req | Description |
|---|---|---|---|
| ari_score | number | – | Autonomy Readiness Index 0–1 (≥0.60 autonomous, ≥0.30 bounded, <0.30 human-governed) |
| artifact_id | string | – | Unique ID for the sealed artifact — use this with verify_decision |
| autonomy_band | string | – | Recommended deployment mode |
| confidence_tier | string | – | Artifact confidence tier |
| contradictions | number | – | Number of contradictions detected |
| rules_extracted | number | – | Number of executable rules extracted |
| seal_hash | string | – | SHA-256 cryptographic seal of the artifact |
No examples provided.
request_authority ~149
Ask for an authority (a law, regulation, standard or policy) to be added to the NOMOS Exchange when find_authority finds nothing. Requests are public and ranked by how many asked; they decide what is compiled next. Repeated requests from one caller count once. This never creates an authority: only its issuer, or NOMOS compiling the public text, can.
| Name | Type | Req | Description |
|---|---|---|---|
| jurisdiction | string | – | Optional jurisdiction, e.g. "AE". |
| source_url | string | – | Optional link to the official text. |
| title | string | yes | The authority by its usual name, e.g. "UAE Personal Data Protection Law (Federal Decree-Law 45/2021)". |
| Name | Type | Req | Description |
|---|---|---|---|
| counted | boolean | – | – |
| id | number | – | – |
| note | string | – | – |
| requests | number | – | – |
| status | string | – | – |
| title | string | – | – |
No examples provided.
verify_decision ~445
Check whether an AI decision is allowed, denied, or needs escalation according to a sealed NOMOS governance artifact. Always returns `allowed` (boolean) — that field is safe to read regardless of which artifact type answered. The rest of the shape genuinely differs by artifact type, because it proxies two different underlying endpoints: pub_ demo artifacts return a flat shape (`outcome`: auto_approved/auto_rejected/escalated, `rule_applied`, `rule_reference`, flat `confidence` and `audit_hash`); your own sealed artifacts from Studio return a nested shape (`verdict`: approved/rejected/escalated, a nested `rule` object, and nested `confidence`/`audit`/`performance` objects). See outputSchema for both exact shapes — do not assume one without checking which kind of artifact_id was passed. Use artifact IDs starting with pub_ for public demo artifacts that require no API key: pub_lending_v1 (loan approval), pub_refund_v1 (refund policy), pub_fraud_v1 (fraud detection), pub_hr_leave_v1 (HR leave approval), pub_kyc_v1 (KYC/identity).
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | – | NOMOS API key (nmk_live_...). Not required for pub_ artifacts. |
| artifact_id | string | yes | Sealed artifact ID to evaluate against. Use pub_lending_v1, pub_refund_v1, pub_fraud_v1, pub_hr_leave_v1, or pub_kyc_v1 for public demos. Use your own artifact ID from Studio for custom governance. |
| decision | string | yes | The action or decision being checked, as a verb phrase (e.g. "approve_loan", "process_refund", "approve_leave"). Should match an action defined in the artifact. |
| domain_id | number | – | Your NOMOS domain ID. Required for custom artifacts created in Studio. Not needed for pub_ artifacts. |
| inputs | object | yes | Key/value input fields for rule evaluation (e.g. {"amount": 5000, "credit_score": 720}). Fields must match the artifact's declared data contract. |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the NOMOS MCP server?
NOMOS is a hosted endpoint at https://www.nomosprotocol.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · www.nomosprotocol.com
claude mcp add --transport http com-nomosprotocol-nomos 'https://www.nomosprotocol.com/api/mcp'
What is the NOMOS MCP server?
NOMOS is an MCP server listed in the public MCP registry as com.nomosprotocol/nomos. Ask a sealed authority whether an action may proceed. Answers are deterministic and citable. This page covers its hosted endpoint (https://www.nomosprotocol.com/api/mcp).
Is the NOMOS MCP server safe to use?
NOMOS scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the NOMOS MCP server expose?
NOMOS exposes 7 tools: verify_decision, generate_governance, detect_contradictions, ask_authority, ask_by_context, and 2 more. Their descriptions and schemas cost roughly 2,207 tokens of context every time the server is loaded.
Does the NOMOS MCP server require authentication?
No. We connected to NOMOS without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the NOMOS MCP server still maintained?
NOMOS is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the NOMOS MCP server?
VerifyMCP ran 12 checks on NOMOS, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about NOMOS: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.