// docs / mcp
MCP servidor
Plug FixVibe into Claude Desktop, Cursor, térã any client that speaks pe Model Context Protocol. Your AI agent gets typed access pe ne scan-kuéra, jejuhu-kuéra, ha pe same templated fix prompts that power pe dashboard's Mbohasaha fix prompt button.
Mint an API token
Visit /cuenta/api-tokens ha create a token named, e.g., claude-desktop. Mbohasaha pe plaintext value — it's shown once.
Tokens hína bearer credentials: anyone ndive pe string ikatu read ne scan-kuéra ha start pyahu ones. Store it like a password.
Point ne MCP client at /api/mcp
Claude Desktop / Cursor / Continue / Zed:
{
"mcpServers": {
"fixvibe": {
"transport": "streamable-http",
"url": "https://fixvibe.app/api/mcp",
"headers": {
"Authorization": "Bearer fxv_YOUR_TOKEN_HERE"
}
}
}
}Restart pe client. The fixvibe server should appear in its MCP servidor list.
Try it out
Ask ne agent things like:
- “List my last 10 FixVibe scan-kuéra.”
- “Show me pe critical jejuhu-kuéra on pe most recent scan.”
- “Start a passive scan against
https://staging.example.com.” - “For each high-severity jejuhu on scan X, write a fix.”
- “Are there any open live-threat alerta-kuéra on my dominio-kuéra?”
- Type
/fixvibe-fixndive a jejuhu id pe drop pe templated remediation prompt straight into pe chat.
Tembiporu
- list_scansread
- Returns up pe 100 most-recent scan-kuéra ndive status + jejuhu counts. Args: limit?: 1..100.
- get_scanread
- Scan envelope + per-category severity summary by default. Set include_findings=true guarã pe full informe (large guarã noisy scan-kuéra — prefer list_findings + filters). Args: scan_id (uuid), include_findings?: boolean.
- list_findingsread
- Paginated jejuhu-kuéra across all ne scan-kuéra. Args: severity?: list, check_id?, since? (ISO 8601), limit?: 1..200.
- start_scanwrite
- Enqueues a scan and returns an id with status queued; poll get_scan to await completion. Passive mode is always available through MCP. Active mode requires a paid plan plus verified-domain authorization from the dashboard. Args: target (URL or hostname), mode? (passive|active).
- list_alertsread
- Aviso amenaza ára añópe (CT log iñambue, DNS ojeguero'ã, threat intel ñepehẽ). Oĩ plan Unlimited-pe año; plan Hobby ha Pro omyengoviave lista nandi. Args: domain_id?, active_only?, limit?: 1..200.
- get_alertread
- Single alert with the relevant domain, severity, type, and event details. Args: alert_id (uuid).
- dismiss_alertwrite · idempotent
- Mark an alerta dismissed. Idempotent — re-dismissing ha'e a nahániri-op. Args: alert_id (uuid).
Recurso-kuéra
Recurso-kuéra let ne client attach FixVibe dato into pe conversation directly, instead of pe agent re-fetching it on peteĩteĩ turn. In Claude Desktop, click pe @ menu → fixvibe.
- fixvibe://scan/{scan_id}/reportjson
- Full FixVibe scan informe including peteĩteĩ check ha peteĩteĩ jejuhu.
- fixvibe://finding/{finding_id}json
- A single jejuhu (severity, title, description, evidence, remediation, CWE).
Slash commands
- /fixvibe-fixprompt
- Renders a server-side remediation prompt for a finding, using scan context when available and falling back to generic guidance otherwise. Args: finding_id (uuid). No third-party LLM API call is made by FixVibe.
→ Quotas, RLS, ha severity gating apply identically pe MCP ha REST calls.
