Security & Testing
hackerbob.ai
Provides access to public Common Vulnerabilities and Exposures (CVE) records for security research.
ENDPOINT 1
https://hackerbob.ai/mcp
MCP server metadata
- Name
- hacker-bob
- Version
- 1.0.0
Public tools read cleared CVE records. Authenticated workspace tools require OAuth or device authorization. Assessment launch always requires human approval of the exact prepared run.
Known tools 22
list_public_cve_recordsList cleared public Hacker Bob Common Vulnerabilities and Exposures records with cursor pagination and optional project or publication-status filters.
Inferred read-onlyget_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.
Inferred read-onlysearch_public_cve_recordsSearch cleared public Hacker Bob CVE records by CVE identifier, open-source project name, or publication status without contacting any assessment target.
Inferred read-onlyget_capabilitiesReturn current public boundaries and, when authenticated, workspace-specific tool reachability, scopes, and role requirements.
Inferred read-onlyget_my_accountReturn the authenticated account and the workspace bound to this agent connection.
Inferred read-onlylist_workspacesList active Hacker Bob workspaces available to the authenticated account.
Inferred read-onlylist_assetsList workspace assets and current ownership-authorization state without contacting a target.
Inferred read-onlybegin_domain_authorizationCreate a DNS TXT or HTTPS-file challenge proving control of a domain.
Potential side effectscheck_domain_authorizationCheck the previously issued DNS or HTTPS proof and update the asset authorization state.
Potential side effectslist_assessmentsList assessments and current run states in the approved workspace.
Inferred read-onlyget_assessmentReturn one assessment, its verified asset, current run state, and any pending human approval.
Inferred read-onlyprepare_assessmentCreate an immutable assessment for a verified stored asset and return a browser approval URL.
Potential side effectslaunch_assessmentConsume a recent human approval and submit the immutable assessment to Hacker Bob's managed queue.
Inferred read-onlycancel_assessmentCancel an eligible queued or running assessment and reconcile any refundable reserved credit.
Inferred read-onlylist_findingsList workspace findings with optional lifecycle and severity filters.
Inferred read-onlyget_findingReturn one finding with evidence-safe lifecycle history and related asset metadata.
Inferred read-onlyget_credit_summaryReturn available, reserved, and used assessment credits for the approved workspace.
Inferred read-onlylist_audit_eventsList recent workspace audit events with optional actor, action, and time filters.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.hacker-bob]
url = "https://hackerbob.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"hacker-bob": {
"type": "http",
"url": "https://hackerbob.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: hacker-bob
Remote MCP URL: https://hackerbob.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"hacker-bob": {
"url": "https://hackerbob.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"hacker-bob": {
"type": "http",
"url": "https://hackerbob.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "hacker-bob",
"transport": "streamable-http",
"url": "https://hackerbob.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.