Local MCP capabilities provider for Expo
OffSeq Threat Radar is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Live CVE, CISA KEV and exploit intelligence, SBOM scans, patch prioritization and IOC checks.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http offseq-threat-radar-mcp https://radar.offseq.com/mcp --header 'X-API-Key: ${X_API_KEY}'
# 2 — ask your agent for something these tools do
# search_threats, get_threat, match_packages and 9 more
It needs X_API_KEY (Radar API key (tr_ followed by 64 hex characters), from Console > Settings at https://radar.offseq.com/console): this sends it in the X-API-Key header from your environment, so export it first — its endpoint answers 401 without it.
OffSeq Threat Radar costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads X_API_KEY (Radar API key (tr_ followed by 64 hex characters), from Console > Settings at https://radar.offseq.com/console) from your environment each time it connects and sends it in the X-API-Key header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx X_API_KEY … and open a new terminal (Windows).
claude mcp add --scope user --transport http offseq-threat-radar-mcp https://radar.offseq.com/mcp --header 'X-API-Key: ${X_API_KEY}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: X-API-Key header — Radar API key (tr_ followed by 64 hex characters), from Console > Settings at https://radar.offseq.com/console. You set it in your own client’s config, on your machine — this marketplace never holds it.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search OffSeq Radar's vulnerability and threat corpus (CVE records, CISA KEV, ENISA EUVD, EPSS, public exploits, news). Combine filters to answer questions like "exploited Fortinet CVEs this month" or "critical CVEs with rising EPSS". Results carry priority, KEV, EPSS, exploit maturity and EUVD signals. Use get_threat for one record in full.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Free text over title, description, CVE id, product, vendor, tags. |
| cveId | string | no | Exact CVE id, e.g. CVE-2024-3400. |
| vendor | string | no | — |
| product | string | no | — |
| purl | string | no | Package URL coordinate (versionless), e.g. pkg:npm/lodash. For version-aware matching use match_packages. |
| severity | array | no | — |
| kev | no | CISA KEV: listed, not listed, past due date, due date ahead, due within 14 days. | |
| euvdExploited | boolean | no | Listed as exploited by ENISA EUVD. |
| exploitedNotInKev | boolean | no | Exploited per ENISA EUVD or OffSeq Mirage but not in CISA KEV. |
| publicExploit | boolean | no | Public exploit or proof of concept exists. |
| exploitMaturity | array | no | — |
| epssRising | boolean | no | EPSS rose by at least 0.05 over 7 days. |
| ransomware | boolean | no | Known ransomware campaign use (CISA KEV). |
| minPriority | integer/string | no | Priority score 0..100, or a band: critical, high, medium, low. |
| minCvss | number | no | — |
| minEpss | number | no | — |
| days | integer | no | Ingested within the last N days. |
| publishedAfter | string | no | ISO date. |
| publishedBefore | string | no | ISO date. |
| sort | no | Default -publishedDate (newest). priority = highest priority first; epss_rising = largest 7-day EPSS rise. |
One vulnerability or threat record by CVE id (e.g. CVE-2024-3400) or Radar slug, resolved to the authoritative record: CVSS, priority with its factors, CISA KEV, EPSS with 30-day history, exploit maturity and sources, ENISA EUVD, OffSeq Mirage, source consensus, affected versions and remediation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | CVE id or the slug from a radar.offseq.com/threat/<slug> URL. |
Check installed packages against known vulnerabilities with ecosystem-native version comparison (distro backports included). Each package is a purl with version (pkg:npm/lodash@4.17.20, pkg:deb/debian/openssl@3.0.11-1~deb12u2?distro=bookworm), or name + ecosystem + version, or a CPE. Returns per package the matches, the smallest fixing version (upgradeTo) and CVEs with no fix (unfixed).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| packages | array | yes | At most your plan's batch size. |
| strict | boolean | no | true returns only version-confirmed matches. |
Scan a whole SBOM or lockfile for vulnerable dependencies, riskiest first, with upgrade advice per package. Formats: cyclonedx-json, spdx-json, package-lock, composer-lock, cyclonedx-xml, spdx-tag-value, yarn-lock, pnpm-lock, cargo-lock, uv-lock, poetry-lock, gemfile-lock, go-mod, go-sum, purl-list, requirements. Pass the file text as content and its filename so the format is detected. failOn eval
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | yes | The file's text. |
| filename | string | no | e.g. package-lock.json, requirements.txt, bom.cdx.json. |
| format | no | — | |
| failOn | no | — |
Rank 2 to 50 CVEs into a patch order using Radar's priority score (CVSS, EPSS, CISA KEV, ransomware, exploit maturity, exploited but not in CISA KEV). Each row says why it ranks above the next; patterns group CVEs sharing a product, vendor or weakness.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cveIds | array | yes | — |
Look up indicators of compromise (IP addresses, domains, URLs, file hashes) in the indicators Radar extracted from threat reports. Matching is a case-insensitive substring match per indicator type; up to 5 threats per indicator.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| indicators | array | yes | — |
What changed across the vulnerability landscape in a window: CISA KEV additions, exploitation not in KEV (ENISA EUVD, OffSeq Mirage), new public exploits, EPSS risers and new critical CVEs, plus CVEs that several of those name (multiSignal). Each panel cites its source and as-of time.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| window | no | Default 7d. |
Your "What changed" feed: new signals (KEV listing, EPSS jump, exploit published, EUVD exploited, fix available...) on CVEs you starred or that affect your monitored hosts, plus decisions that went stale, expired or are due for review. Newest first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since | string | no | ISO date; default the last 30 days. |
| limit | integer | no | — |
Hosts in your Radar inventory (registered by the threat-finder CLI) with each host's cached finding summary and an account-wide aggregate. Use list_host_findings for one host's findings.
Takes no parameters.
Current vulnerability findings for one of your hosts, riskiest first, with exposure, KEV, EPSS, fix versions and any decision you recorded. Get hostId from list_hosts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hostId | string | yes | — |
| confirmedOnly | boolean | no | Only version-confirmed findings. |
| limit | integer | no | Default 50. |
Your decision ledger: what you decided per CVE (patch_now, defer, accept, not_affected, mitigated), the assumptions behind it, and whether it still holds (active, review_due, expired, stale when a signal broke an assumption).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | array | no | — |
| verdict | array | no | — |
| cveId | string | no | — |
| hostId | string | no | — |
| page | integer | no | — |
| limit | integer | no | — |
Record a decision about a CVE in your ledger. Radar re-checks the assumptions as signals change and flags the decision stale when one breaks. Verdicts: patch_now, defer (needs until), accept, not_affected and mitigated (take a VEX justification). Assumptions that do not hold today are rejected. Confirm the verdict with the user before calling; this writes to their account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cveId | string | yes | — |
| verdict | yes | — | |
| justification | no | — | |
| note | string | no | — |
| until | string | no | ISO date in the future; required for defer. |
| scope | no | cve (account-wide, default) or host. | |
| hostId | string | no | — |
| assetKey | string | no | — |
| assumptions | array | no | — |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install OffSeq Threat Radar or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_threats | no tags | |
| get_threat | no tags | |
| match_packages | no tags | |
| scan_sbom | no tags | |
| prioritize_cves | no tags | |
| check_iocs | no tags | |
| get_landscape | no tags | |
| list_changes | no tags | |
| list_hosts | no tags | |
| list_host_findings | no tags | |
| list_decisions | no tags | |
| record_decision | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish OffSeq Threat Radar can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.