@whisper-security/whisper-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 2 of 2 tools tried
Contacts while installing and starting: github.com, release-assets.githubusercontent.com
What it contacted
github.comrelease-assets.githubusercontent.com: a release file downloaded from GitHub
Hosts it looked up or connected to while installing and starting with no input, watched from outside its sandbox. The npm registry is left out. Says nothing about what its tools contact when called.
Starting it
npx -y @whisper-security/whisper-mcp@0.269.0
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
2 tools that take no input and look read-only were called once with nothing. 2 returned a result.
read_docs | Returned a result under 0.1 s · 11,003 characters |
list_workflows | Returned a result under 0.1 s · 18,091 characters |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
whisper_verify target
Verify whether an address or FQDN is a real Whisper agent and, if so, whose - running the full keyless trust chain (reverse-DNS + DANE-EE TLSA pin + DNSSEC + JWS identity doc). Returns the verdict as JSON. Use it to check any peer's claimed identity before trusting it. No API key needed.
whisper_rdap ip
Fetch the RDAP record for a Whisper IPv6 /128 (the IP-anchored registration object: who operates the agent identity, since when, under which tenant). Returns RDAP JSON. Use it to look up ownership/registration facts about an address. No API key needed.
whisper_identify v
Name the vendor and operator role behind a host or IP in one call. Resolves a host/IP to its canonical vendor, category and operator roles (DNS_OPERATOR / CDN / ORIGIN_AS / MAIL_RECEIVER) with a confidence band. No API key needed. Docs: https://www.whisper.security/docs/whisper-graph/procedures/identify
whisper_assess v
Get a labelled threat posture for a host or IP - malicious, benign, or unknown. Returns a posture label + severity band + sub-labels + coverage + evidence for an indicator; benign-allowlisted vs malicious-evidenced, never a bare score. No API key needed. Docs: https://www.whisper.security/docs/whisper-graph/procedures
whisper_explain v
Score an indicator against the threat feeds and explain exactly why. Threat-intel scorer: score + level + human explanation + the feeds it is listed in (feedId, weight, firstSeen/lastSeen). Two live forms: bare CALL explain($v) (full columns) and CALL whisper.explain($v) (restricted YIELD). No API key needed. Docs: https://www.whisper.security/docs/whisper-graph/procedures/explain
read_docs path, query
Read whisper.security documentation on demand - the canonical Cypher, schema, recipe, and reference guides. Three modes: no argument lists the available pages; {"query":"rpki"} searches pages by keyword; {"path":"reference/graph-schema"} fetches that page's markdown. Only indexed whisper.security/docs pages are served (path is index-relative, never a URL). No API key needed. Docs: https://www.whisper.security/docslist_workflows keyword, kind
List or search the gallery of ready-made investigations (workflows) and recipes you can run with run_workflow - so a multi-step investigation is ONE call instead of many hand-written queries. CALL THIS FIRST for attack-surface, footprint, recon, domain/ASN/IP/prefix profiling, DNS & email posture, BGP/RPKI health, and takeover checks. Returns each item's slug, kind (workflow|recipe), title, summary, its inputs, and its tunable params. Filter with keyword and/or kind. Listing needs no API key; running an entry with run_workflow does. Without a key, whisper_identify, whisper_assess and whisper_explain run as their own tools. Docs: https://www.whisper.security/docs
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Files it wrote
/tmp/ .cache/ whisper-mcp/ 0.269.0/ whisper /tmp/ .cache/ whisper-mcp/ 0.269.0/ whisper.sha256
Paths inside its sandbox, where its home folder is /tmp and its own folder cannot be written to.
Install facts
| License | MIT |
|---|---|
| Needs | node >=18 |
| Source | github.com/whisper-sec/whisper-cli |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-NHB4dDb3MSTTR43W+tK7YMEx9ZtkO6KR1ud1ml6myT+VMeaYnn/xJyGI3cdOC/vk92o0ZocOusUUHj0SHBvAMg== |
Versions reported
| Version | Run | Result | Tools |
|---|---|---|---|
| 0.269.0 | 2026-11-16 | Starts with no setup | 7 |
| 0.267.0 | 2026-11-12 | Starts with no setup | 7 |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40whisper-security/whisper-mcp)
New version out? Ask for a fresh report.