Whisper MCP server
io.github.whisper-sec/whisperwhisper-secstreamable-httpv0.273.0Scanned
One routable IPv6 per AI agent, verifiable from the DNS root. Keyless tools need no signup.
42 tools: 1 can delete or cancel things, 33 change things and 8 only read.
- Reads private data · 0
- Reads text others write · 42
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Whisper MCP server can do
The Whisper MCP server is published by the GitHub account whisper-sec. It has 42 tools. It can delete or cancel things (1 tool: whisper_agents_revoke) and create or change data (33 tools: whisper_signup, whisper_verify, whisper_rdap, whisper_identify and 29 more). 8 tools only read.
42 tools bring in text other people can write (whisper_signup, whisper_verify, whisper_rdap and 39 more).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 18, 2026, version 0.273.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
42 tools
Deletes or cancels 1Claude Code: deny
whisper_agents_revokeThe revoke operation on the Whisper control plane, served as CALL whisper.agents({op:'revoke', args:{...}}).Reads text others write1 finding
Why it is in this group
- The name "whisper_agents_revoke" says "revoke": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "whisper_agents_revoke" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "whisper_agents_revoke" says "revoke": a word for removing or ending something.
Description, as the server wrote it The revoke operation on the Whisper control plane, served as CALL whisper.agents({op:'revoke', args:{...}}). Requires your Whisper API key. The identifier in the example is a placeholder for one of YOUR agents: list them with the "agents.list" skill and {"kind":"agents"}. Example call: {"skill":"agents.revoke","input":{"agent":"agent-a1f4c0b2d3e4f5a67"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Changes things 33Claude Code: ask
whisper_agents_agentThe agent operation on the Whisper control plane, served as CALL whisper.agents({op:'agent', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The agent operation on the Whisper control plane, served as CALL whisper.agents({op:'agent', args:{...}}). Requires your Whisper API key. The identifier in the example is a placeholder for one of YOUR agents: list them with the "agents.list" skill and {"kind":"agents"}. Add include:'tombstones' to read an agent that is gone: its newest lifecycle row says whether it was revoked, released, erased or reaped, when, by whom and why. Example call: {"skill":"agents.agent","input":{"agent":"agent-a1f4c0b2d3e4f5a67"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_agents_alertThe alert operation on the Whisper control plane, served as CALL whisper.agents({op:'alert', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The alert operation on the Whisper control plane, served as CALL whisper.agents({op:'alert', args:{...}}). Requires your Whisper API key. With no arguments it describes what you already have, so the example below runs as published. Example call: {"skill":"agents.alert","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_connectThe connect operation on the Whisper control plane, served as CALL whisper.agents({op:'connect', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The connect operation on the Whisper control plane, served as CALL whisper.agents({op:'connect', args:{...}}). Requires your Whisper API key. With no arguments it describes what you already have, so the example below runs as published. Example call: {"skill":"agents.connect","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_detectThe detect operation on the Whisper control plane, served as CALL whisper.agents({op:'detect', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The detect operation on the Whisper control plane, served as CALL whisper.agents({op:'detect', args:{...}}). Requires your Whisper API key. Example call: {"skill":"agents.detect","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_agents_disconnectThe disconnect operation on the Whisper control plane, served as CALL whisper.agents({op:'disconnect', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The disconnect operation on the Whisper control plane, served as CALL whisper.agents({op:'disconnect', args:{...}}). Requires your Whisper API key. With no arguments it describes what you already have, so the example below runs as published. Example call: {"skill":"agents.disconnect","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_domainThe domain operation on the Whisper control plane, served as CALL whisper.agents({op:'domain', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The domain operation on the Whisper control plane, served as CALL whisper.agents({op:'domain', args:{...}}). Requires your Whisper API key. Example call: {"skill":"agents.domain","input":{"name":"example.com"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_edgeThe edge operation on the Whisper control plane, served as CALL whisper.agents({op:'edge', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The edge operation on the Whisper control plane, served as CALL whisper.agents({op:'edge', args:{...}}). Requires your Whisper API key. Name the sub-op as sub: key mints a feed key for your edge servers (label optional), which reads only your own keyed edge planes and appears in that one answer only; key.list lists your feed keys; key.revoke revokes one by id; grant and ungrant add and remove the scope op:policy needs to set edge allow and deny lists. They are the account owner's: an agent or device key is refused. Example call: {"skill":"agents.edge","input":{"sub":"key.list"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_firewallThe firewall operation on the Whisper control plane, served as CALL whisper.agents({op:'firewall', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The firewall operation on the Whisper control plane, served as CALL whisper.agents({op:'firewall', args:{...}}). Requires your Whisper API key. The identifier in the example is a placeholder for one of YOUR agents: list them with the "agents.list" skill and {"kind":"agents"}. Example call: {"skill":"agents.firewall","input":{"agent":"agent-a1f4c0b2d3e4f5a67"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_historyThe history operation on the Whisper control plane, served as CALL whisper.agents({op:'history', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The history operation on the Whisper control plane, served as CALL whisper.agents({op:'history', args:{...}}). Requires your Whisper API key. The identifier in the example is a placeholder for one of YOUR agents: list them with the "agents.list" skill and {"kind":"agents"}. Example call: {"skill":"agents.history","input":{"address":"2a04:2a01:f6d7:1ffe:a0be:ba8a:c355:bba1"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_agents_hostThe host operation on the Whisper control plane, served as CALL whisper.agents({op:'host', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The host operation on the Whisper control plane, served as CALL whisper.agents({op:'host', args:{...}}). Requires your Whisper API key. Example call: {"skill":"agents.host","input":{"name":"my-host","type":"TXT","value":"hello"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_identityThe identity operation on the Whisper control plane, served as CALL whisper.agents({op:'identity', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The identity operation on the Whisper control plane, served as CALL whisper.agents({op:'identity', args:{...}}). Requires your Whisper API key. With no arguments it describes what you already have, so the example below runs as published. Example call: {"skill":"agents.identity","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_agents_partnerThe partner operation on the Whisper control plane, served as CALL whisper.agents({op:'partner', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The partner operation on the Whisper control plane, served as CALL whisper.agents({op:'partner', args:{...}}). Requires your Whisper API key. It is gated on partner authority rather than on arguments: without it the call is refused whatever you pass. Example call: {"skill":"agents.partner","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_policyThe policy operation on the Whisper control plane, served as CALL whisper.agents({op:'policy', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The policy operation on the Whisper control plane, served as CALL whisper.agents({op:'policy', args:{...}}). Requires your Whisper API key. With no arguments it describes what you already have, so the example below runs as published. Example call: {"skill":"agents.policy","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_registerThe register operation on the Whisper control plane, served as CALL whisper.agents({op:'register', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The register operation on the Whisper control plane, served as CALL whisper.agents({op:'register', args:{...}}). Requires your Whisper API key. Example call: {"skill":"agents.register","input":{"label":"my-first-agent"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_renameThe rename operation on the Whisper control plane, served as CALL whisper.agents({op:'rename', args:{...}}).Reads text others writeNo findings
Why it is in this group
- The name "whisper_agents_rename" says "rename": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The rename operation on the Whisper control plane, served as CALL whisper.agents({op:'rename', args:{...}}). Requires your Whisper API key. The identifier in the example is a placeholder for one of YOUR agents: list them with the "agents.list" skill and {"kind":"agents"}. Example call: {"skill":"agents.rename","input":{"agent":"agent-a1f4c0b2d3e4f5a67","label":"renamed-agent"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_resolverThe resolver operation on the Whisper control plane, served as CALL whisper.agents({op:'resolver', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The resolver operation on the Whisper control plane, served as CALL whisper.agents({op:'resolver', args:{...}}). Requires your Whisper API key. With no arguments it describes what you already have, so the example below runs as published. Example call: {"skill":"agents.resolver","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_taskThe task operation on the Whisper control plane, served as CALL whisper.agents({op:'task', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The task operation on the Whisper control plane, served as CALL whisper.agents({op:'task', args:{...}}). Requires your Whisper API key. The identifier in the example is a placeholder for one of YOUR agents: list them with the "agents.list" skill and {"kind":"agents"}. Example call: {"skill":"agents.task","input":{"agent":"agent-a1f4c0b2d3e4f5a67"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_agents_tokenThe token operation on the Whisper control plane, served as CALL whisper.agents({op:'token', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The token operation on the Whisper control plane, served as CALL whisper.agents({op:'token', args:{...}}). Requires your Whisper API key. The identifier in the example is a placeholder for one of YOUR agents: list them with the "agents.list" skill and {"kind":"agents"}. Example call: {"skill":"agents.token","input":{"agent":"agent-a1f4c0b2d3e4f5a67"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_agents_traceThe trace operation on the Whisper control plane, served as CALL whisper.agents({op:'trace', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The trace operation on the Whisper control plane, served as CALL whisper.agents({op:'trace', args:{...}}). Requires your Whisper API key. Example call: {"skill":"agents.trace","input":{"dest":"203.0.113.7"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_agents_verifyThe verify operation on the Whisper control plane, served as CALL whisper.agents({op:'verify', args:{...}}).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The verify operation on the Whisper control plane, served as CALL whisper.agents({op:'verify', args:{...}}). Requires your Whisper API key. Example call: {"skill":"agents.verify","input":{"name":"example.com"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_assessAssess the risk/policy posture of one or more indicators.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Assess the risk/policy posture of one or more indicators. Answers without an API key. Example call: {"skill":"assess","input":"example.com"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_historyHistorical records for an indicator (incl.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Historical records for an indicator (incl. whois/bgp history). Answers without an API key. Example call: {"skill":"history","input":"example.com"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_identifyIdentify an indicator (domain, IP, hash, …) against the graph.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Identify an indicator (domain, IP, hash, …) against the graph. Answers without an API key. Example call: {"skill":"identify","input":"example.com"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_originsTrace the origins/provenance of an indicator.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Trace the origins/provenance of an indicator. Answers without an API key. Example call: {"skill":"origins","input":"example.com"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_pslPublic-suffix-list family (tld-plus-one, is-public-suffix, affiliation).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Public-suffix-list family (tld-plus-one, is-public-suffix, affiliation). A family verb: name the sub-verb as "sub" alongside the input. Sub-verbs: tldPlusOne, isPublicSuffix, affiliation.. Answers without an API key. Example call: {"skill":"psl","sub":"tldPlusOne","input":"a.b.example.co.uk"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_rdapThe public registration record for any address in Whisper's space, in RFC 9083 form: the handle, the agent's label, its country, and the entities behind it.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The public registration record for any address in Whisper's space, in RFC 9083 form: the handle, the agent's label, its country, and the entities behind it. The same document the RDAP service serves at /ip/{address}, which any RDAP client can already read. Answers without an API key. Example call: {"skill":"rdap","input":"2a04:2a01:b69a:6717:e3b0:51ff:3bf7:f478"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_signupStart or complete Whisper signup from an email address alone, and receive an API key that unlocks the provisioning and governance skills on this card.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "start": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Start or complete Whisper signup from an email address alone, and receive an API key that unlocks the provisioning and governance skills on this card. Send {"email":"..."} to start; a six-digit code arrives by email; send {"signup_id":"...","code":"123456"} to complete. No human step, no account needed first. Example call: {"skill":"signup","input":{"email":"agent@example.com"}}
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_submitSubmit an observation/claim into the graph.Reads text others writeNo findings
Why it is in this group
- The name "whisper_submit" says "submit": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Submit an observation/claim into the graph. Writes to the graph, so it needs your API key: an anonymous claim would not be attributable. Example call: {"skill":"submit","input":{"host":"example.com","claim":"benign"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
whisper_threatintelThreat-intelligence indicator family (candidate apex/CDN/hosting).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Threat-intelligence indicator family (candidate apex/CDN/hosting). A family verb: name the sub-verb as "sub" alongside the input. Sub-verbs: candidateCdnApex, candidateMultiTenantApex, candidateSharedHostingIp.. Answers without an API key. Example call: {"skill":"threatintel","sub":"candidateCdnApex","input":5}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_variantsEnumerate variants/permutations of an indicator.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Enumerate variants/permutations of an indicator. Answers without an API key. Example call: {"skill":"variants","input":"example.com"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_verifyIs this IPv6 address or hostname a real Whisper agent, and whose?Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Is this IPv6 address or hostname a real Whisper agent, and whose? Grades the full keyless trust chain: the reverse DNS record, the forward AAAA confirming it back to the same address, and the DANE-EE certificate pin published in DNSSEC-signed DNS. Returns is_whisper_agent with the evidence for the verdict either way, so a negative answer is an answer and not an error. Answers without an API key, and every leg of it is independently checkable from the DNS root with dig. Example call: {"skill":"verify","input":"2a04:2a01:b69a:6717:e3b0:51ff:3bf7:f478"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_walkWalk the graph from an indicator across its relationships.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Walk the graph from an indicator across its relationships. Answers without an API key. Example call: {"skill":"walk","input":"example.com"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_watchWatch an indicator for change/activity over time.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Watch an indicator for change/activity over time. Answers without an API key. Example call: {"skill":"watch","input":{"action":"list"}}
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Only reads 8Show 8 read-only tools
whisper_agents_listThe list operation on the Whisper control plane, served as CALL whisper.agents({op:'list', args:{...}}).Reads text others writeNo findings
Why it is in this group
- The name "whisper_agents_list" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The list operation on the Whisper control plane, served as CALL whisper.agents({op:'list', args:{...}}). Requires your Whisper API key. Add include:'tombstones' to list the agents that are gone as well, paged, each with its lifecycle state (never 'active'), actor and reason. Example call: {"skill":"agents.list","input":{"kind":"agents"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_agents_logsThe logs operation on the Whisper control plane, served as CALL whisper.agents({op:'logs', args:{...}}).Reads text others writeNo findings
Why it is in this group
- The name "whisper_agents_logs" says "log": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The logs operation on the Whisper control plane, served as CALL whisper.agents({op:'logs', args:{...}}). Requires your Whisper API key. With no arguments it describes what you already have, so the example below runs as published. Example call: {"skill":"agents.logs","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_agents_lookupsThe lookups operation on the Whisper control plane, served as CALL whisper.agents({op:'lookups', args:{...}}).Reads text others writeNo findings
Why it is in this group
- The name "whisper_agents_lookups" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The lookups operation on the Whisper control plane, served as CALL whisper.agents({op:'lookups', args:{...}}). Requires your Whisper API key. With no arguments it describes what you already have, so the example below runs as published. Example call: {"skill":"agents.lookups","input":{}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_assetResolve an asset and its catalog of attributes.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "resolve": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Resolve an asset and its catalog of attributes. Answers without an API key. Example call: {"skill":"asset","input":"example.com"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_explainExplain a verdict - the evidence and reasoning behind it.Reads text others writeNo findings
Why it is in this group
- The name "whisper_explain" says "explain": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Explain a verdict - the evidence and reasoning behind it. Answers without an API key. Example call: {"skill":"explain","input":"example.com"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_lookupTlsFingerprintLook up a TLS (JA3/JA4) fingerprint in the graph.Reads text others writeNo findings
Why it is in this group
- The name "whisper_lookupTlsFingerprint" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Look up a TLS (JA3/JA4) fingerprint in the graph. Answers without an API key. Example call: {"skill":"lookupTlsFingerprint","input":"ja3:771,4865-4866-4867"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_lookupTorRelayLook up Tor relay metadata for an address.Reads text others writeNo findings
Why it is in this group
- The name "whisper_lookupTorRelay" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Look up Tor relay metadata for an address. Answers without an API key. Example call: {"skill":"lookupTorRelay","input":"185.220.101.1"}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
whisper_topAsnsByPrefixCountTop ASNs ranked by announced-prefix count.Reads text others writeNo findings
Why it is in this group
- The name "whisper_topAsnsByPrefixCount" says "count": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Top ASNs ranked by announced-prefix count. Answers without an API key. Example call: {"skill":"topAsnsByPrefixCount","input":10}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write42
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:12 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 34
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://whisper.online/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://whisper.online
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 34 tools that change things (1 destructive, 33 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://whisper.online/mcp: tools/list returned 42 tools to an anonymous client, including whisper_agents_revoke (destructive), whisper_signup (write), whisper_verify (write), whisper_rdap (write), whisper_identify (write) and 29 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 33 to 34
- Nov 6, 2026
- Tools that change things, listed without credentials: 12 to 33
- RFC 9728 protected resource metadata: none to https://whisper.online/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://whisper.online
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
Findings
Matches of fixed checks, with the text they matched.
The server marks "whisper_agents_revoke" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "whisper_agents_revoke" says "revoke": a word for removing or ending something.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 33 -> 34.View diff
- Tools that change things, listed without credentials: 33 to 34
Tools1 added.+1 addedView diff
- Added:whisper_agents_edgeChanges things
Tools2 changed.~2 changedView diff
- Changed:whisper_agents_agentChanges thingsdescription
- Changed:whisper_agents_listOnly readsdescription
PostureRemote posture changed. Tools that change things, listed without credentials: 12 -> 33; RFC 9728 protected resource metadata: none -> https://whisper.online/.well-known/oauth-protected-resource/mcp; Authorization servers: none -> https://wh…View diff
- Tools that change things, listed without credentials: 12 to 33
- RFC 9728 protected resource metadata: none to https://whisper.online/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://whisper.online
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
Tools24 added.+24 addedView diff
- Added:whisper_agents_agentChanges things
- Added:whisper_agents_alertChanges things
- Added:whisper_agents_connectChanges things
- Added:whisper_agents_detectChanges things
- Added:whisper_agents_disconnectChanges things
- Added:whisper_agents_domainChanges things
- Added:whisper_agents_firewallChanges things
- Added:whisper_agents_historyChanges things
- Added:whisper_agents_hostChanges things
- Added:whisper_agents_identityChanges things
- Added:whisper_agents_listOnly reads
- Added:whisper_agents_logsOnly reads
- Added:whisper_agents_lookupsOnly reads
- Added:whisper_agents_partnerChanges things
- Added:whisper_agents_policyChanges things
- Added:whisper_agents_registerChanges things
- Added:whisper_agents_renameChanges things
- Added:whisper_agents_resolverChanges things
- Added:whisper_agents_revokeDeletes or cancels
- Added:whisper_agents_taskChanges things
- Added:whisper_agents_tokenChanges things
- Added:whisper_agents_traceChanges things
- Added:whisper_agents_verifyChanges things
- Added:whisper_submitChanges things
Install
Pinned to version 0.273.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http whisper https://whisper.online/mcpclaude mcp add --transport http whisper https://whisper.online/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__whisper__whisper_explain",
"mcp__whisper__whisper_lookupTlsFingerprint",
"mcp__whisper__whisper_lookupTorRelay",
"mcp__whisper__whisper_asset",
"mcp__whisper__whisper_topAsnsByPrefixCount",
"mcp__whisper__whisper_agents_list",
"mcp__whisper__whisper_agents_logs",
"mcp__whisper__whisper_agents_lookups"
],
"ask": [
"mcp__whisper__whisper_signup",
"mcp__whisper__whisper_verify",
"mcp__whisper__whisper_rdap",
"mcp__whisper__whisper_identify",
"mcp__whisper__whisper_assess",
"mcp__whisper__whisper_walk",
"mcp__whisper__whisper_watch",
"mcp__whisper__whisper_submit",
"mcp__whisper__whisper_variants",
"mcp__whisper__whisper_origins",
"mcp__whisper__whisper_history",
"mcp__whisper__whisper_threatintel",
"mcp__whisper__whisper_psl",
"mcp__whisper__whisper_agents_agent",
"mcp__whisper__whisper_agents_alert",
"mcp__whisper__whisper_agents_connect",
"mcp__whisper__whisper_agents_detect",
"mcp__whisper__whisper_agents_disconnect",
"mcp__whisper__whisper_agents_domain",
"mcp__whisper__whisper_agents_edge",
"mcp__whisper__whisper_agents_firewall",
"mcp__whisper__whisper_agents_history",
"mcp__whisper__whisper_agents_host",
"mcp__whisper__whisper_agents_identity",
"mcp__whisper__whisper_agents_partner",
"mcp__whisper__whisper_agents_policy",
"mcp__whisper__whisper_agents_register",
"mcp__whisper__whisper_agents_rename",
"mcp__whisper__whisper_agents_resolver",
"mcp__whisper__whisper_agents_task",
"mcp__whisper__whisper_agents_token",
"mcp__whisper__whisper_agents_trace",
"mcp__whisper__whisper_agents_verify"
],
"deny": [
"mcp__whisper__whisper_agents_revoke"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as whisper. Review it before you use it.
Capability tags behind 42 rules
- mcp__whisper__whisper_signup untrusted-input
- mcp__whisper__whisper_verify untrusted-input
- mcp__whisper__whisper_rdap untrusted-input
- mcp__whisper__whisper_identify untrusted-input
- mcp__whisper__whisper_assess untrusted-input
- mcp__whisper__whisper_walk untrusted-input
- mcp__whisper__whisper_watch untrusted-input
- mcp__whisper__whisper_submit untrusted-input
- mcp__whisper__whisper_explain untrusted-input
- mcp__whisper__whisper_variants untrusted-input
- mcp__whisper__whisper_origins untrusted-input
- mcp__whisper__whisper_history untrusted-input
- mcp__whisper__whisper_lookupTlsFingerprint untrusted-input
- mcp__whisper__whisper_lookupTorRelay untrusted-input
- mcp__whisper__whisper_asset untrusted-input
- mcp__whisper__whisper_threatintel untrusted-input
- mcp__whisper__whisper_psl untrusted-input
- mcp__whisper__whisper_topAsnsByPrefixCount untrusted-input
- mcp__whisper__whisper_agents_agent untrusted-input
- mcp__whisper__whisper_agents_alert untrusted-input
- mcp__whisper__whisper_agents_connect untrusted-input
- mcp__whisper__whisper_agents_detect untrusted-input
- mcp__whisper__whisper_agents_disconnect untrusted-input
- mcp__whisper__whisper_agents_domain untrusted-input
- mcp__whisper__whisper_agents_edge untrusted-input
- mcp__whisper__whisper_agents_firewall untrusted-input
- mcp__whisper__whisper_agents_history untrusted-input
- mcp__whisper__whisper_agents_host untrusted-input
- mcp__whisper__whisper_agents_identity untrusted-input
- mcp__whisper__whisper_agents_list untrusted-input
- mcp__whisper__whisper_agents_logs untrusted-input
- mcp__whisper__whisper_agents_lookups untrusted-input
- mcp__whisper__whisper_agents_partner untrusted-input
- mcp__whisper__whisper_agents_policy untrusted-input
- mcp__whisper__whisper_agents_register untrusted-input
- mcp__whisper__whisper_agents_rename untrusted-input
- mcp__whisper__whisper_agents_resolver untrusted-input
- mcp__whisper__whisper_agents_revoke untrusted-input
- mcp__whisper__whisper_agents_task untrusted-input
- mcp__whisper__whisper_agents_token untrusted-input
- mcp__whisper__whisper_agents_trace untrusted-input
- mcp__whisper__whisper_agents_verify untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.whisper-sec/whisper/verify?hash=90c57a8e1873ce74cac40ee923f5b436edd235a96663cd1f3c1db0cec0233c77" | jq -e '.changed == false'Pinned hash 90c57a8e1873, from Nov 18, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.whisper-sec/whisper/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.whisper-sec/whisper)Source: MCP Registry · repository. Synced Nov 18, 2026, 13:18 UTC.
Whisper MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Whisper MCP server safe?
- No scan can promise that. What its definitions show: 42 tools, 34 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Whisper MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: whisper_agents_revoke.
Can the Whisper MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Whisper MCP server have?
- 42 tools: 1 destructive, 33 write, 8 read. whisper_agents_revoke, whisper_signup, whisper_verify, whisper_rdap, whisper_identify, whisper_assess, whisper_walk, whisper_watch and 34 more.
Does the Whisper MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Whisper MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Whisper MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.