Spurvik
NPM · SPURVIK-MCP-SERVER · 2 COMPONENTS
EU AI Act Art. 50 URL & C2PA checks, Art. 12/14 snippets, HMAC receipts, DPO questionnaire answers.
Available components
Last scanned (13 hours ago)
Scores higher than 44% of npm servers
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 2 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability62
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2810 tokens (~281/item across 10 items; 10 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 Management27
- Stability observed for 8 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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 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 (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
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.
- 21 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 18 Nov 26 +12
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → pass ▲ functional
- Package version: 1.0.8 → 1.0.9 functional
- 17 Nov 26 −24
- Known CVEs: pass → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Schema quality: 243 → 281 ▼ functional
- Schema quality: 1701 → 2344 ▼ functional
- Schema quality: 1701 → 1989 ▼ functional
- Dependency health: pass → unverified ▼ functional
- Stability: unverified → 0.13 ▲ functional
- Package version: 1.0.5 → 1.0.8 functional
- Package version: 1.0.5 → 1.0.7 functional
- Package version: 1.0.5 → 1.0.6 functional
- 13 Nov 26 68
First indexed and scored.
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 · Analysed npm/spurvik-mcp-server@1.0.9
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
spurvik_batch_scan_domains Batch-scan up to 10 domains for Art. 50(1) ~244
Scan 1 to 10 public domains or http(s) URLs (for example an agency's client sites) through console.spurvik.com for AI chat widgets and AI SDKs, and check each frontpage for a visible EU AI Act Article 50(1) notice. Every entry is checked first: if any entry is localhost, a private or reserved IP or an internal host, the whole batch is refused and nothing is sent. Returns JSON: totalDomains, gapsFound and one row per host with detectedWidgets, art50NoticeDetected, gap, reportUrl, a one-line badgeSnippet and statusShieldMarkdown, plus portfolioUrl and upgradeUrls (Team €79/mo, Done-For-You €199 once per site). At most 4 scans run at once, each with an 8-second timeout; a host the service cannot reach returns offlineFallback: true in its row. Heuristic: reads the HTML of one page per domain. Not legal advice.
| Name | Type | Req | Description |
|---|---|---|---|
| domains | array | yes | 1 to 10 public http(s) URLs or bare domains, for example ["stepnetwork.dk", "folk.app"]. Duplicate hosts are scanned once. |
No output schema declared.
No examples provided.
spurvik_check_image_c2pa_url Check an image URL for a C2PA manifest (CDN-strip check) ~325
C2PA JUMBF manifest & CDN-strip checker for one public https image URL (PNG, JPEG or WebP, up to 4 MB), ahead of EU AI Act Art. 50(2) machine-readable marking (applies from 2 December 2026). console.spurvik.com fetches the image once through its SSRF gate and reads the manifest in memory; nothing is stored. Returns JSON: status, mediaType, byteLength, fileName, c2pa { manifestFound, embedded, claimGenerator, signatureMatches, trustAnchor, validationCodes }, whether the URL goes through an image optimizer that strips C2PA (/_next/image, Cloudinary, imgix, Cloudflare /cdn-cgi/image/) with a fix, a visible "AI-generated" notice (<AIDisclosureLabel notice="generated" /> and badge.js data-notice="generated"), and links: the interactive checker, Pro (€19/mo) and Done-For-You (€199 once) with appUrl prefilled. Read-only: it never signs or adds a manifest. Only https on port 443, no credentials; localhost, .local, .internal and private or reserved IPs are refused before any request. 15-second timeout; 10 checks per minute per address, shared with console.spurvik.com/c2pa. Not legal advice.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Public https URL of a PNG, JPEG or WebP image up to 4 MB, for example https://example.com/hero.png. |
No output schema declared.
No examples provided.
spurvik_classify_ai_act_risk Map an AI use case to an EU AI Act risk tier ~290
Deterministic, zero-network mapping of one AI use case to an EU AI Act tier: prohibited_art5, high_risk_annex_iii, limited_transparency_art50 or minimal_risk. Returns JSON with the matched signals, obligations with dates, recommended Spurvik controls, interactiveClassifierUrl and upgradeUrls. The use-case text is matched against fixed patterns; it is not stored or echoed. Engineering mapping aid; not legal advice and not a decision under Article 6.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | – | Annex III area, or general (default): biometrics, critical_infrastructure, education, employment_hr, essential_services_credit, law_enforcement, migration_border, justice_democracy. |
| generatesSyntheticMedia | boolean | – | The system generates audio, images, video or text (Art. 50(2)). Inferred from useCase when omitted. |
| interactsWithHumans | boolean | – | People talk to or chat with the system (Art. 50(1)). Inferred from useCase when omitted. |
| makesAutomatedDecisionsAboutPeople | boolean | – | The system decides about, ranks or scores natural persons, or materially influences such decisions. Inferred from useCase when omitted. |
| useCase | string | yes | What the AI system does and for whom, in one or two sentences. Max 4000 characters. Not stored or echoed. |
No output schema declared.
No examples provided.
spurvik_explain_receipt Explain an HMAC receipt ~191
Explain the fields of an HMAC provenance receipt JSON. If signingSecret is passed, or SPURVIK_SIGNING_SECRET is set, check the HMAC locally with `verifyProvenanceSignature`, which checks that the record's signed fields still match the HMAC-SHA-256 signature. It does not show that a notice was shown, that output is marked, or that your system meets the Act. The signing secret is not logged. Omit the secret to explain the fields without checking.
| Name | Type | Req | Description |
|---|---|---|---|
| receipt | string | yes | HMAC provenance receipt as JSON text. A provenance record, or the AI SDK metadata object with a record field. |
| signingSecret | string | – | Optional client-held signing secret. When set, or when SPURVIK_SIGNING_SECRET is set, the HMAC is checked locally. The value is not logged. Omit it to skip the check. |
No output schema declared.
No examples provided.
spurvik_find_unwrapped_calls Find unwrapped AI calls ~286
Heuristic static scan of one directory inside the workspace root for AI client calls that are not passed through withSpurvik, spurvikMiddleware, withSpurvikMastra, withSpurvikModel, withSpurvikModelProvider, withSpurvikLangGraph, or spurvikInterrupt. A StateGraph constructor is reported when the file does not call withSpurvikLangGraph. A bare interrupt() call is reported when the file does not call spurvikInterrupt or resolveLangGraphInterrupts. The scan reads .ts, .tsx, .js, .jsx, .mjs, .cjs, .mts, and .cts files. It does not read .md or .mdc files. Results are file:line. The line number is 1-based and counts every newline, including comments and strings. This is a heuristic, so it can miss a call or report one that is already wrapped. The scan does not change files and does not use the network. Paths that leave the workspace, including '..', are rejected. The scanner skips files named .env or .env.* (any case), including through symlinks and hard links.
| Name | Type | Req | Description |
|---|---|---|---|
| directory | string | yes | Directory inside the workspace root passed with --root or SPURVIK_MCP_ROOT. Relative paths are resolved from that root. '..' is rejected. |
No output schema declared.
No examples provided.
spurvik_generate_art50_badge Generate an Art. 50(1) badge ~291
Zero-network generator for an EU AI Act Article 50(1) notice in any of the 24 official EU languages: a one-line badge.js <script>, a Next.js <Script>, the WordPress plugin .zip, the Framer component and the shadcn/v0 registry item. Returns JSON. attribution defaults to true (Free) and shows a subtle "Art. 50 · Spurvik" link; attribution: false is white-label on Pro (€19/mo) or Done-For-You (€199 once). The language is inferred from a domain-like systemName when locale is omitted. Not legal advice.
| Name | Type | Req | Description |
|---|---|---|---|
| attribution | boolean | – | Show the "Art. 50 · Spurvik" trust link. Defaults to true. false is white-label (Pro or Done-For-You). |
| locale | string | – | One of the 24 official EU language codes: en, da, de, fr, es, nl, sv, pl, it, pt, fi, cs, bg, el, et, ga, hr, hu, lt, lv, mt, ro, sk, sl. |
| position | string | – | bottom-right (default), bottom-left or inline. |
| systemName | string | – | Product or assistant name, or the site domain. Defaults to Support Assistant. |
| theme | string | – | dark (default) or light. |
No output schema declared.
No examples provided.
spurvik_marking_hooks Marking hooks ~119
Explain how to plug your own Article 50(2) marking into marking.text or marking.media. Spurvik does not mark content. withSpurvik and spurvikMiddleware log the call and attach an HMAC receipt. A hook runs only when you supply one. The signed text trailer is an application-level binding you can opt into. It is not, by itself, an Article 50(2) machine-readable mark.
| Name | Type | Req | Description |
|---|---|---|---|
| surface | string | – | Which hook to explain: text, media, or both. Defaults to both. |
No output schema declared.
No examples provided.
spurvik_scan_live_url Scan a live URL for Art. 50(1) ~198
Scan one public page (bare domain or http(s) URL, for example stepnetwork.dk) through console.spurvik.com for AI chat widgets and AI SDKs, and check whether a visible EU AI Act Article 50(1) notice is present. Returns JSON: host, status, score, detected widgets and SDKs, a one-line badge.js fix, reportUrl, sandboxUrl, portfolioUrl, upgradeUrls, and statusShieldMarkdown (a live Art. 50 status shield you can offer to add to the project README.md). localhost, private or reserved IPs and internal hosts are refused before any request. 8-second timeout; when the scan service cannot be reached it returns offlineFallback: true with the links and the badge snippet. Heuristic: reads the HTML of one page. Not legal advice.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Public http(s) URL or bare domain, for example stepnetwork.dk. |
No output schema declared.
No examples provided.
spurvik_setup_snippet Spurvik setup snippet ~236
Return a setup snippet for openai, anthropic, google-genai, vercel-ai-sdk, mastra, openai-agents, or langgraph. Provider clients are wrapped with withSpurvik. The Vercel AI SDK snippet passes spurvikMiddleware to wrapLanguageModel. The Mastra snippet calls withSpurvikMastra. The OpenAI Agents snippet calls withSpurvikModelProvider. The LangGraph snippet calls withSpurvikLangGraph and spurvikInterrupt. The snippet is built from the installed spurvik exports. `riskTier` is a sample value. Set your own classification (as provider or deployer); Spurvik does not classify your use case. The SDK logs the call and attaches an HMAC receipt. It does not mark content.
| Name | Type | Req | Description |
|---|---|---|---|
| framework | string | yes | Provider or framework to wrap: openai, anthropic, google-genai, vercel-ai-sdk, mastra, openai-agents, or langgraph. |
| runtime | string | yes | Where the process runs: node, next, vercel, or supabase-edge. This chooses the flush call. |
No output schema declared.
No examples provided.
spurvik_vendor_questionnaire_answers Answer an EU AI Act vendor security questionnaire ~436
Zero-network, deterministic Markdown answers to the five EU AI Act questions enterprise buyers ask in vendor security questionnaires and DPO RFPs: Q1 Art. 50(1) notice and 2 Dec 2026 Art. 50(2) provenance, Q2 Art. 12 cryptographic event logging (keyed HMAC-SHA256 inputHash/outputHash, SHA-256 recordHash chained by prevLogHash), Q3 GDPR Art. 5(1)(c) zero-prompt minimisation and EU Frankfurt residency, Q4 Art. 14 deterministic human approval gates, Q5 audit retention, DPO evidence and Annex IV documentation. Answers match the chosen Spurvik plan: Free €0 (10,000 events/mo, 30 days), Pro €19/mo (250,000, 90 days, white-label badge, hosted approval queue, DPO engineering summary), Team €79/mo (2,000,000, 12 months, Annex IV draft, webhook export) or Done-For-You €199 once (24h install, signed DPO readiness report, 1 year of Pro). Every field is optional. Ends with links to the interactive questionnaire and signup. Review the wording against your own setup before you send it.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | – | Optional public hostname of the product, for example acme.eu. Prefills the report and signup links; a value that is not a public hostname is ignored and not echoed. |
| generatesMedia | boolean | – | The product generates synthetic images, audio or video (Art. 50(2)). Defaults to false. |
| hasHighRiskActions | boolean | – | Agents or tools can trigger refunds, emails, permission changes or deletions. Defaults to true. |
| plan | string | – | Spurvik plan the answers describe: free, pro (default), team or concierge (Done-For-You). |
| provider | string | – | Model provider or agent framework: openai (default), anthropic, google-genai, vercel-ai-sdk, langgraph, openai-agents, mastra or custom. |
No output schema declared.
No examples provided.
How do I install the Spurvik MCP server?
Spurvik runs locally as an npm package, launched with npx -y spurvik-mcp-server --root .. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
npm · spurvik-mcp-server
claude mcp add spurvik-spurvik-mcp-server -- npx -y spurvik-mcp-server --root .
What is the Spurvik MCP server?
Spurvik is an MCP server listed in the public MCP registry as io.github.spurvik/spurvik-mcp-server. EU AI Act Art. 50 URL & C2PA checks, Art. 12/14 snippets, HMAC receipts, DPO questionnaire answers. This page covers its npm package (spurvik-mcp-server).
Is the Spurvik MCP server safe to use?
Spurvik scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 Spurvik MCP server expose?
Spurvik exposes 10 tools: spurvik_setup_snippet, spurvik_find_unwrapped_calls, spurvik_explain_receipt, spurvik_marking_hooks, spurvik_scan_live_url, and 5 more. Their descriptions and schemas cost roughly 2,616 tokens of context every time the server is loaded.
Is the Spurvik MCP server still maintained?
Spurvik 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 licence is the Spurvik MCP server under?
Spurvik declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Spurvik MCP server?
VerifyMCP ran 16 checks on Spurvik, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.