Agents

Set up the cve.now MCP server for me. cve.now is a free, public CVE feed: no login, no API key.

- Server name: cve-now
- Transport: Streamable HTTP
- URL: https://mcp.cve.now/mcp

Add it the way you normally add MCP servers (your CLI command or your MCP config file), then confirm it connects and lists its two tools, search and execute. To finish, use them to run the cve.get operation on one recent CVE and summarize it for me.

cve.list

The newest CVEs and advisories, narrowed by priority slice, vendor, technology, ecosystem or fix status

cve.get

One CVE by id

early-warning.list

Early warnings

early-warning.get

One early warning by id: an SZB- id (a breach shares its SZB- id; use breach.get for one)

breach.list

Breaches and ransomware attacks, newest first

breach.get

One breach by id: an SZB- id

vendor.list

The vendors cve.now follows, with their CVE counts

vendor.get

One vendor by id: the vendor's slug

package.list

The packages that have advisories

package.get

One package by id: <ecosystem>/<name>, such as npm/lodash or npm/@babel/core

tech.list

The technologies cve.now follows

tech.get

One tech by id: the technology's slug

entities.search

Search cve.now's whole catalog of vulnerabilities and early warnings

feed.read

The items a /feed subscriber gets, as JSON Feed, newest first

stack.check

Check exact package versions against cve.now's synced vulnerability catalog

leaderboard.get

Get the cve.now Index

feedback.send

Send a private note to the cve.now team

Get vulnerability by CVE, GHSA or OSV id

GET /api/v1/entries/<id>

Read vulnerability feed

GET /api/v1/entries?name=<feed> (or tech, ecosystem, vendor, fix)

Check dependencies

POST /api/v1/check

Send private feedback to the cve.now team

POST /api/v1/feedback

Get worst-CVE leaderboard (the cve.now Index)

GET /api/v1/leaderboard

Search vulnerabilities

GET /api/v1/search

Get a package's vulnerability history

GET /api/v1/packages/<ecosystem>/<name>

Every entry, newest first

GET /api/v1/entries

Upload a lockfile for stack.check or a stack feed

POST /api/v1/stacks

Sync and coverage status

GET /api/v1/status

Public usage counts

GET /api/v1/stats

curl -L https://cve.now/api/v1/entries/CVE-2021-44228

llms.txt · llms-full.txt · openapi.json · Entry schema · agent.json · mcp.json · Agent skill

Something wrong or missing? Run the feedback.send operation, POST /api/v1/feedback, or the form on the About page.

The MCP server lists exactly two tools that never change: search finds an operation and execute runs one. Every capability is an operation (cve.get, feed.read, stack.check, entities.search, <type>.list and <type>.get, with a REST twin each), so a new one never changes the tool list. The old tools (get_vulnerability, list_feed, check_stack and the rest) stay callable and are no longer listed: deprecated since 2026-11-11, removed from these docs on 2027-01-10.

Every entity type has a REST list and get in one shape (https://cve.now/openapi.json lists them): /api/v1/cves, /early-warnings, /breaches, /vendors, /packages and /tech answer { items, next_cursor, total? } and take the type's own filters, q on a catalog type, limit (1 to 200, default 30) and cursor. A parameter that is unknown or does not apply is a 400 (V7); a missing id is a 404 { error: "not_found", type, id }.

type (cve, early-warning, breach, package) is on every object: each entry, each row of /api/v1/entries and /api/v1/entries/<id>, and get_package. /api/v1/entries also reads type=cve|early-warning|breach, and serves its rows as items beside the old key entries, which stays. An entry copy the CDN holds from before this change gains type and url as the copies are rewritten.

kind is on every entry: /api/v1/entries/<id>, each row of /api/v1/entries and each search result carry vulnerability, breach, ransomware, malicious-package or outage. In a search result kind used to name the advisory database (cve, ghsa, osv...) and now names the entry's kind.

The entry schema is published at https://cve.now/schemas/entry.json, the same schema get_vulnerability declares as its outputSchema.

Every vulnerability entry names what its affected products are: vendors (the slug of /vendors/<slug>), products, packages and tech (the slug of /feed?tech=<slug> and the rule it matched on).

Search is one search, the same on cve.now and down.guide. type: (and the type parameter) takes entity types: cve, early-warning, breach, vendor, package and tech (early_warning, early warnings and breaches together, and all still work). date: is the shared name for published:, and filter:critical|kev|epss picks the priority slice. The response's items hold the matching entries and the vendors, technologies and packages the query names, each tagged with its type and an exact name match first; entries holds the entries alone, as before. facets gains type and confidence.

Confidence is labeled Confirmed, Corroborated or Unverified everywhere; the breaches tab that read Reported, not confirmed is Corroborated (?show=reported still selects it).

category: (search)

Now kind:: vulnerability, breach, ransomware, malicious-package or outage

kind:cve, kind:ghsa, kind:malicious, kind:ecosystem and kind:osv (search)

Now kind:vulnerability, or the kind of early warning: kind: now takes entry kinds

type (each result in `entries`; `items[].type` is the entity type)

Now kind

category (each search result)

Now kind