{"id":"com.vulntel/mcp","slug":"com-vulntel-mcp","title":"vulntel","description":"Free hosted CVE intel for bug-bounty agents: CVE fact-check, attack approaches from paid H1 reports","version":"1.2.0","publisher":{"kind":"domain","id":"vulntel.com","label":"vulntel.com","url":"https://vulntel.com"},"website":"https://vulntel.com","repository":"https://github.com/rozetyp/vulntel-mcp","remotes":[{"type":"streamable-http","url":"https://mcp.vulntel.com/mcp","headers":[{"description":"Optional bearer token. Without one, nine of the 13 tools run 25 times a day per network (the answers say how many calls are left). A free key from https://vulntel.com/signup lifts that to 60 calls a minute and adds observe, new_in_scope, assist_submission and search_public_code: send Bearer <your-key>.","isSecret":true,"name":"Authorization"}]}],"packages":[],"published":"2026-11-03","updated":"2026-11-03","status":"online","auth":"","latency_ms":1156,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"enrich_cve","title":"Enrich a CVE","description":"Full intelligence for a single CVE: CVSS, KEV status, EPSS, CISA SSVC\n(exploitation/automatable/technical_impact), P1-P4 priority with rationale,\naffected products/versions, Debian/Ubuntu/Alpine fixed builds per release\n(`distro_fixes`), and (live) public-exploit signal.\n\nFor a LIST (a scan's findings, a vulnerability review): pass `cve_ids` (up to 50) instead\nand get one compact card per CVE with","read_only":true},{"name":"check_technology","title":"CVEs for a product and version","description":"Find vulnerabilities affecting a product across NVD (CPE) and OSV\n(package ecosystems), de-duplicated and ranked by priority/EPSS/CVSS.\n\nDistinct products that share a name are kept distinct. If one name maps to\nseveral VENDORS' unrelated products (e.g. \"Sentry\" → sentry, mobileiron,\napache; \"Envoy\" → envoyproxy, enphase), the result is flagged `ambiguous`\nwith `distinct_vendors` — pass `vendor=` ","read_only":true},{"name":"hunt_plan","title":"Rank a recon'd stack into a dig order","description":"Turn a recon'd stack into a ranked dig-order for a pentest or bug-bounty hunt.\n\nFor each discovered component, returns its top high-risk CVEs (KEV / CISA-SSVC-\nactive / high-EPSS first) AND its `recurring_loci` — the bug classes (CWE) this\nproduct family repeatedly fails at, ranked by real in-the-wild exploitation —\ni.e. WHERE to look first and WHAT shape to expect. Components are ordered by\ntheir","read_only":true},{"name":"observe","title":"Scan a host's exposed stack","description":"Scan a host's exposed stack and join it to the CVE corpus — the recon workhorse.\nFingerprints the homepage + JS bundles (recovering the backend identity and API endpoints\nhomepage detection misses on SPAs), then ranks against live KEV / SSVC-active / high-EPSS\ninto a dig-order. Fetches only public pages.\n\nNON-BLOCKING: a scan takes ~1-4 min, so observe() never waits on it. A recent scan (<24h)\nret","read_only":true},{"name":"search_vulns","title":"Search CVEs by concept, keyword or seed CVE","description":"Search the CVE corpus — one entry point, three retrieval modes picked from your arguments:\n\n  - query=  a concept / technique / weakness (e.g. \"SSO SAML assertion replay\",\n            \"deserialization gadget chain\", \"server-side request forgery cloud metadata\").\n            By default it FUSES full-text keyword search AND semantic mechanism-search, so you\n            don't have to guess whether yo","read_only":true},{"name":"find_attack_approaches","title":"Find attack approaches from disclosed bounty reports","description":"Find how bugs *like this* were actually FOUND — retrieve real disclosed bug-bounty\nreport mechanic-cards whose approach is closest (by mechanism) to your query or a seed CVE.\n\nThe \"what approach worked on a bug like this, on which program, and what did it pay\" layer:\ngrounded in real publicly-disclosed, paid HackerOne reports, each distilled to a transferable\nmechanic (bug_class / source / sink / ","read_only":true},{"name":"find_continuations","title":"Next moves from a hunt position","description":"When you're STUCK mid-hunt: describe your POSITION — the attacker state/capabilities you hold,\nstripped of product names — and get the CONTINUATIONS that worked from positions like it, matched\nagainst the full disclosed-report BODIES (the concrete step/payload/precondition), not just the\ndistilled card. This is the \"I have a messy pile of capabilities, what are my legal moves?\" layer.\n\nposition: a","read_only":true},{"name":"assist_submission","title":"Strengthen a bug-bounty submission","description":"Submission & escalation co-pilot for a bug-bounty finding. Paste your DRAFT finding (and what you\nalready tried / couldn't achieve) and get a grounded brief built from the closest REAL disclosed reports:\n(1) precedent & validity — is this an accepted class, with citable reports (ammunition if it was\ndisputed/closed); (2) what's novel/stronger about yours — what to lead with; (3) an escalation play","read_only":true},{"name":"program_outcome_prior","title":"What lands on a bounty program","description":"At the START of an engagement on a bug-bounty PROGRAM, get a grounded prior over what bug\nclasses have historically LANDED there — to decide what to look at first and what to skip.\n\nBuilt from real HackerOne disclosed reports: the class distribution for this program, each with\nLIFT over the global base-rate, sample size, and cited example reports; plus `lands_rarely` — the\nclasses that land broadl","read_only":true},{"name":"new_in_scope","title":"What newly entered bug-bounty scope","description":"Find FRESH attack surface: bounty-eligible assets that entered a public bug-bounty program's scope in the\nlast `days` (HackerOne, Bugcrowd, Intigriti, YesWeHack, mirrored daily), the least-hunted surface there is.\n\nRaw scope additions are mostly not new (in one week 57 of 80 were re-added after a removal), so each asset is\nchecked against its program's own scope history: you get `new_asset` (never","read_only":true},{"name":"verify_cve_claim","title":"Fact-check a CVE claim","description":"Fact-check a claim about a CVE against the corpus — catch hallucinations\nbefore they ship. Verifies: does the CVE exist; does it affect the claimed\nproduct at the claimed version; is the severity right; is it actually\nKEV-exploited. Returns per-assertion verdicts (supported / refuted /\nunverifiable) with cited evidence.\n\nUse it to check what another agent (or a draft report) asserted, e.g.\n\"Spring","read_only":true},{"name":"corpus_stats","title":"Corpus size and freshness","description":"Corpus size and data freshness (CVE / KEV / EPSS counts and latest timestamps).","read_only":true},{"name":"search_public_code","title":"Find public copies of a code string","description":"Search public repositories for an exact code string; return WHERE it appears.\n\nUse it to hunt vendored / copy-pasted copies of known-vulnerable code: search a\ndistinctive symbol or short fragment from the vulnerable function (a function name, a\nconstant, one call), then FETCH AND READ the hits to judge which copies are still\nunpatched, reachable, or just fossils/forks. Returns RAW search results o","read_only":true}],"server_info":{"name":"vulntel","version":"1.2.0"},"category":"security","tags":["developer","agents","analytics"],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-11-03","stars":0,"badges":["new"],"sponsor":null,"page":"https://agentsindex.org/agents/com-vulntel-mcp/"}