Hacker Bob public records MCP server
io.github.bobnetsec/hacker-bob-public-recordsbobnetsecstreamable-httpv1.0.0Scanned
Read-only public CVE records, capability metadata, and agent instructions from Hacker Bob.
22 tools: 2 can delete or cancel things, 3 change things and 17 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things. Govern them.
- 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 Hacker Bob public records MCP server can do
The Hacker Bob public records MCP server is published by the GitHub account bobnetsec. It has 22 tools. It can delete or cancel things (2 tools: launch_assessment and cancel_assessment) and create or change data (3 tools: begin_domain_authorization, check_domain_authorization and prepare_assessment). 17 tools only read.
3 tools bring in text other people can write (get_public_cve_record, check_domain_authorization and launch_assessment).
The fixed checks matched 2 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 16, 2026, version 1.0.0.
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.
22 tools
Deletes or cancels 2Claude Code: deny
cancel_assessmentCancel an eligible queued or running assessment and reconcile any refundable reserved credit.No findings
Why it is in this group
- The name "cancel_assessment" says "cancel": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Cancel an eligible queued or running assessment and reconcile any refundable reserved credit.
Annotations the server declares
- title: Cancel assessment
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
launch_assessmentConsume a recent human approval and submit the immutable assessment to Hacker Bob's managed queue.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 destructive (destructiveHint: true).
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 Consume a recent human approval and submit the immutable assessment to Hacker Bob's managed queue. The target is resolved only from the stored verified asset.
Annotations the server declares
- title: Submit approved assessment
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
Changes things 3Claude Code: ask
begin_domain_authorizationCreate a DNS TXT or HTTPS-file challenge proving control of a domain.1 finding
Why it is in this group
- The description's first verb is "create": a word for a change.
Findings
- Info
The input schema at properties.domain.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.domain.description: "...omain name only; no scheme, path, port, credentials, or wildcard."
Description, as the server wrote it Create a DNS TXT or HTTPS-file challenge proving control of a domain. This does not run an assessment.
Annotations the server declares
- title: Begin domain authorization
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_domain_authorizationCheck the previously issued DNS or HTTPS proof and update the asset authorization state.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 Check the previously issued DNS or HTTPS proof and update the asset authorization state.
Annotations the server declares
- title: Check domain authorization
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
prepare_assessmentCreate an immutable assessment for a verified stored asset and return a browser approval URL.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create an immutable assessment for a verified stored asset and return a browser approval URL. This never contacts the target.
Annotations the server declares
- title: Prepare assessment
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 17Show 17 read-only tools
get_assessmentReturn one assessment, its verified asset, current run state, and any pending human approval.No findings
Why it is in this group
- The name "get_assessment" says "get": a word for reading.
Description, as the server wrote it Return one assessment, its verified asset, current run state, and any pending human approval.
Annotations the server declares
- title: Get assessment
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_assetReturn one workspace asset and its current authorization state.No findings
Why it is in this group
- The name "get_asset" says "get": a word for reading.
Description, as the server wrote it Return one workspace asset and its current authorization state.
Annotations the server declares
- title: Get authorized asset
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_capabilitiesReturn current public boundaries and, when authenticated, workspace-specific tool reachability, scopes, and role requirements.No findings
Why it is in this group
- The name "get_capabilities" says "get": a word for reading.
Description, as the server wrote it Return current public boundaries and, when authenticated, workspace-specific tool reachability, scopes, and role requirements.
Annotations the server declares
- title: Get Hacker Bob capabilities
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_credit_summaryReturn available, reserved, and used assessment credits for the approved workspace.No findings
Why it is in this group
- The name "get_credit_summary" says "get": a word for reading.
Description, as the server wrote it Return available, reserved, and used assessment credits for the approved workspace.
Annotations the server declares
- title: Get credit summary
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_findingReturn one finding with evidence-safe lifecycle history and related asset metadata.No findings
Why it is in this group
- The name "get_finding" says "get": a word for reading.
Description, as the server wrote it Return one finding with evidence-safe lifecycle history and related asset metadata.
Annotations the server declares
- title: Get finding
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_my_accountReturn the authenticated account and the workspace bound to this agent connection.No findings
Why it is in this group
- The name "get_my_account" says "get": a word for reading.
Description, as the server wrote it Return the authenticated account and the workspace bound to this agent connection.
Annotations the server declares
- title: Get my Hacker Bob account
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_public_cve_recordReturn one cleared Hacker Bob CVE record by identifier, including its open-source project, publication status, and upstream public record URL when available.Reads text others writeNo findings
Why it is in this group
- The name "get_public_cve_record" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Return one cleared Hacker Bob CVE record by identifier, including its open-source project, publication status, and upstream public record URL when available.
Annotations the server declares
- title: Get one public CVE record
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_reportReturn one released, non-revoked workspace report.1 finding
Why it is in this group
- The name "get_report" says "get": a word for reading.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ort. Pending review material and access credentials are never returned."
Description, as the server wrote it Return one released, non-revoked workspace report. Pending review material and access credentials are never returned.
Annotations the server declares
- title: Get released report
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_workspaceReturn the approved workspace and current membership role.No findings
Why it is in this group
- The name "get_workspace" says "get": a word for reading.
Description, as the server wrote it Return the approved workspace and current membership role.
Annotations the server declares
- title: Get workspace
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_assessmentsList assessments and current run states in the approved workspace.No findings
Why it is in this group
- The name "list_assessments" says "list": a word for reading.
Description, as the server wrote it List assessments and current run states in the approved workspace.
Annotations the server declares
- title: List assessments
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_assetsList workspace assets and current ownership-authorization state without contacting a target.No findings
Why it is in this group
- The name "list_assets" says "list": a word for reading.
Description, as the server wrote it List workspace assets and current ownership-authorization state without contacting a target.
Annotations the server declares
- title: List authorized assets
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_audit_eventsList recent workspace audit events with optional actor, action, and time filters.No findings
Why it is in this group
- The name "list_audit_events" says "list": a word for reading.
Description, as the server wrote it List recent workspace audit events with optional actor, action, and time filters.
Annotations the server declares
- title: List audit events
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_findingsList workspace findings with optional lifecycle and severity filters.No findings
Why it is in this group
- The name "list_findings" says "list": a word for reading.
Description, as the server wrote it List workspace findings with optional lifecycle and severity filters.
Annotations the server declares
- title: List findings
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_public_cve_recordsList cleared public Hacker Bob Common Vulnerabilities and Exposures records with cursor pagination and optional project or publication-status filters.No findings
Why it is in this group
- The name "list_public_cve_records" says "list": a word for reading.
Description, as the server wrote it List cleared public Hacker Bob Common Vulnerabilities and Exposures records with cursor pagination and optional project or publication-status filters.
Annotations the server declares
- title: List public CVE records
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_reportsList non-revoked reports released to the approved workspace.No findings
Why it is in this group
- The name "list_reports" says "list": a word for reading.
Description, as the server wrote it List non-revoked reports released to the approved workspace.
Annotations the server declares
- title: List released reports
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_workspacesList active Hacker Bob workspaces available to the authenticated account.No findings
Why it is in this group
- The name "list_workspaces" says "list": a word for reading.
Description, as the server wrote it List active Hacker Bob workspaces available to the authenticated account. The connection remains bound to its approved workspace.
Annotations the server declares
- title: List my workspaces
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_public_cve_recordsSearch cleared public Hacker Bob CVE records by CVE identifier, open-source project name, or publication status without contacting any assessment target.No findings
Why it is in this group
- The name "search_public_cve_records" says "search": a word for reading.
Description, as the server wrote it Search cleared public Hacker Bob CVE records by CVE identifier, open-source project name, or publication status without contacting any assessment target.
Annotations the server declares
- title: Search public CVE records
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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 write3
- 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, 19:02 UTC, unchanged since Oct 22, 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
- 5
- Protocol version
- 2025-11-25
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://hackerbob.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://content-giraffe-538.convex.site/api/auth
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (2 destructive, 3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://hackerbob.ai/mcp: tools/list returned 22 tools to an anonymous client, including launch_assessment (destructive), cancel_assessment (destructive), begin_domain_authorization (write), check_domain_authorization (write), prepare_assessment (write)
Findings
Matches of fixed checks, with the text they matched.
The input schema at properties.domain.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.domain.description: "...omain name only; no scheme, path, port, credentials, or wildcard."
- Infoget_report
The description mentions "credentials".
What this check looks forMatched text
description: "...ort. Pending review material and access credentials are never returned."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http hacker-bob-public-records https://hackerbob.ai/mcpclaude mcp add --transport http hacker-bob-public-records https://hackerbob.ai/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__hacker-bob-public-records__list_public_cve_records",
"mcp__hacker-bob-public-records__get_public_cve_record",
"mcp__hacker-bob-public-records__search_public_cve_records",
"mcp__hacker-bob-public-records__get_capabilities",
"mcp__hacker-bob-public-records__get_my_account",
"mcp__hacker-bob-public-records__list_workspaces",
"mcp__hacker-bob-public-records__get_workspace",
"mcp__hacker-bob-public-records__list_assets",
"mcp__hacker-bob-public-records__get_asset",
"mcp__hacker-bob-public-records__list_assessments",
"mcp__hacker-bob-public-records__get_assessment",
"mcp__hacker-bob-public-records__list_findings",
"mcp__hacker-bob-public-records__get_finding",
"mcp__hacker-bob-public-records__list_reports",
"mcp__hacker-bob-public-records__get_report",
"mcp__hacker-bob-public-records__get_credit_summary",
"mcp__hacker-bob-public-records__list_audit_events"
],
"ask": [
"mcp__hacker-bob-public-records__begin_domain_authorization",
"mcp__hacker-bob-public-records__check_domain_authorization",
"mcp__hacker-bob-public-records__prepare_assessment"
],
"deny": [
"mcp__hacker-bob-public-records__launch_assessment",
"mcp__hacker-bob-public-records__cancel_assessment"
]
}
}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 hacker-bob-public-records. Review it before you use it.
Capability tags behind 3 rules
- mcp__hacker-bob-public-records__get_public_cve_record untrusted-input
- mcp__hacker-bob-public-records__check_domain_authorization untrusted-input
- mcp__hacker-bob-public-records__launch_assessment 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.bobnetsec/hacker-bob-public-records/verify?hash=010ec241e7d9e7e58c4302e93eeccd00d0a95b417e681712601c224af6def3d2" | jq -e '.changed == false'Pinned hash 010ec241e7d9, from Nov 16, 2026, 12:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.bobnetsec/hacker-bob-public-records/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.bobnetsec/hacker-bob-public-records)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:24 UTC.
Hacker Bob public records MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Hacker Bob public records MCP server safe?
- No scan can promise that. What its definitions show: 22 tools, 5 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Hacker Bob public records MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: launch_assessment and cancel_assessment.
Can the Hacker Bob public records 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 Hacker Bob public records MCP server have?
- 22 tools: 2 destructive, 3 write, 17 read. launch_assessment, cancel_assessment, begin_domain_authorization, check_domain_authorization, prepare_assessment, list_public_cve_records, get_public_cve_record, search_public_cve_records and 14 more.
Does the Hacker Bob public records MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Hacker Bob public records MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Hacker Bob public records MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.