Loading…
Agent-payable web data over x402: 18 keyless services an AI agent pays per call using USDC on Base mainnet.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The mercury-x402 MCP server exposes 18 tools, focused primarily on database, web, and network capabilities. Its published description reads: "Agent-payable web data over x402: 18 keyless services an AI agent pays per call using USDC on Base mainnet". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates mercury-x402 F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check mercury-x402's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add mercury-x402 to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://network.mercury-hq.com/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
VERIFIABLE keyless web-read for autonomous agents. Every result ships a cryptographically SIGNED provenance receipt (EIP-191 over sha256(text)+url+status+time) — the wedge a free scraper structurally
TYPED structured extract for autonomous agents — URL + schema → a clean, type-safe JSON record. Where /buy/fetch returns page TEXT (and ?extract= returns string-only fields), THIS returns the schema-c
URL → clean, LLM-ready markdown (boilerplate/nav/ads stripped, headings + lists + links preserved) with a signed provenance receipt pinning the markdown to its source — the RAG-ingest primitive. Deter
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: fetch
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
primitive — NO API key, NO signup, NO account, NO monthly plan, the onRecommendationRemove side-channel parameters; constrain tool inputs.
tool: fetch
A tool description tries to alter the model’s use of another tool.
by itself instead of stopping to ask a human for a key. Give a ?url= and gRecommendationDescriptions must describe only their own tool.
tool: fetch
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
fetch VERIFIABLE keyless web-read for autonomous agents. Every result shipsRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: extract
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: extract
A tool description tries to alter the model’s use of another tool.
ord. Where /buy/fetch returns page TEXT (and ?extract= returns stringRecommendationDescriptions must describe only their own tool.
tool: extract
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ord. Where /buy/fetch returns page TEXT (and ?extract= returns string-only fields)RecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: markdown
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: markdown
A tool description tries to alter the model’s use of another tool.
dings + lists + links preserved) with a signed provenance receipt pinRecommendationDescriptions must describe only their own tool.
tool: metadata
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: links
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: robots
A tool description tries to alter the model’s use of another tool.
as it stood at fetch time. — $0.005/callRecommendationDescriptions must describe only their own tool.
tool: diff
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: notarize
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: headers
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: table
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: feed
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: availability
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: validate
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: validate
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: sitemap
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: sitemap
A tool description tries to alter the model’s use of another tool.
ist). Optional ?fetch=N (≤10) adds a HARD-BOUNDED same-domain livenesRecommendationDescriptions must describe only their own tool.
tool: dns
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: readability
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: readability
A tool description tries to alter the model’s use of another tool.
stinct from raw markdown. Deterministic (no LLM): same URL + same sourceRecommendationDescriptions must describe only their own tool.
tool: redirect
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: batch
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "batch"RecommendationScope tools to the minimum needed.
tool: dns
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "dns"RecommendationScope tools to the minimum needed.
tool: fetch
An unusually long description is a common injection-padding tactic.
description length 2169 charsRecommendationKeep descriptions concise.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
URL → one typed, SIGNED metadata record (JSON-LD + OpenGraph + Twitter-card + standard <meta> + canonical + title), by source. Deterministic, keyless, no LLM — the social-card/SEO/schema.org record an
URL → a SIGNED outbound/internal link graph: every <a href> as an absolute URL + anchor text, classified internal vs external against the page origin, grouped by origin with a third-party-origin histo
Domain → signed, timestamped per-AI-crawler allow/block audit from robots.txt + llms.txt + ai.txt (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Bytespider, …). Deterministic, no LLM. EU-AI-Act /
URL + prior content-hash (or prior text) -> refetch, deterministic change-proof: changed? + a NEW signed receipt binding fromHash->toHash. Stateless; receipts chain into a tamper-evident audit trail o
Notarize any content (inline ?content= or a fetched ?url=) into a signed, offline-verifiable provenance receipt — sha256 contentHash + witnessed timestamp, attested by Mercury's pinned key. Determinis
URL → a deterministic HTTP security-headers audit (HSTS, CSP, X-Frame, X-Content-Type, Referrer-Policy, Permissions-Policy + more) with a letter grade and concrete findings, wrapped in a signed, offli
URL in → the page's main HTML <table>(s) parsed into typed, header-keyed rows (JSON) + clean RFC-4180 CSV, with a signed provenance receipt over the exact extracted grid. Deterministic, keyless, no LL
RSS/Atom feed URL → a SIGNED, normalized item list [{title,link,published,summary}] unified across RSS 2.0/RDF + Atom 1.0: CDATA unwrapped, HTML stripped, entities decoded, dates → ISO-8601 (published
URL → a signed uptime/status probe: up/down, HTTP status + class, reachability reason, final URL after redirects, and a measured responseMs — wrapped in an offline-verifiable provenance receipt that m
URL (a JSON/API endpoint) + a JSON Schema in → a deterministic pass/fail with per-field errors (missing/wrong-type/enum/range/pattern), plus a signed provenance receipt binding the verdict to the exac
List of URLs (≤20) → clean content for each + ONE signed receipt committing to a MERKLE ROOT over every page's contentHash. Tamper-evident multi-page snapshot with per-page membership proofs (selectiv
Domain/URL → a SIGNED snapshot of the site's PUBLISHED sitemap: discovers the sitemap via robots.txt Sitemap: lines then /sitemap.xml fallback, parses <urlset> + <sitemapindex> (follows up to 5 child
Domain → a SIGNED, timestamped DNS snapshot (A, AAAA, MX, NS, TXT, CNAME, SOA), normalised + sorted into a byte-stable record set with an offline-verifiable provenance receipt — proving exactly what t
URL → a clean ARTICLE record { title, byline, publishedAt, article text } with boilerplate (nav/header/footer/sidebar/ads/share-bars/comment-forms) stripped via deterministic DOM density heuristics, p
URL → a SIGNED redirect/canonical resolution: the full hop chain [{url,status}] from the link you have to where it ACTUALLY lands, the final resolved URL + status, the page's <link rel=canonical>, hop