- DETECTION
- ENFORCEMENT
- ANALYSIS
- HUMAN
Short answer
How can I block API attackers using my AI?
You tell your AI to find active threats, and it uses Salt Security to identify the specific actors and issue block commands to your WAF. This turns a manual security investigation into a conversational workflow. You get immediate protection without jumping between consoles.
Where every action lands.
Security outcomes
Your AI moves between detection and enforcement.
DETECTION
Identify active threats
The AI pulls live data on ongoing attacks. You see exactly who is targeting your APIs right now.
ENFORCEMENT
Issue WAF blockades
Your AI sends immediate commands to block malicious IPs. This stops the attack at the edge.
ANALYSIS
Review attack patterns
The AI examines the specifics of recent hits. You get a clear picture of the attacker's methods.
HUMAN
Manual oversight
You decide when to escalate or change block rules. The AI follows your lead on high-stakes decisions.
The workflow
What your AI does when an attack starts.
The AI handles the heavy lifting of data retrieval and command execution.
Scan for threats
The AI looks for active malicious activity currently hitting your endpoints.
get_attacksIdentify actors
Once a threat is found, the AI pulls the specific identity and footprint of the attacker.
get_attackersExecute blockade
You tell the AI to stop the threat, and it sends the block command to your WAF.
block_attackerVerify protection
The AI checks the attack logs again to ensure the actor is no longer active.
get_attacks
Try it
Copy these to start.
Use these prompts to trigger the Salt Security tools.
Starting points
These are basic commands. Swap out the specific attack IDs or IP addresses as needed.
Salt Security Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_HEqpwxZCJGloy9SZRikbBjYA9GqrD7wwt82MwMIn/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Salt Security capabilities are ready to use.
{
"mcpServers": {
"salt-security-mcp": {
"url": "https://edge.vinkius.com/vk_preview_HEqpwxZCJGloy9SZRikbBjYA9GqrD7wwt82MwMIn/mcp"
}
}
}Show me all active API attacks happening right now.
Who are the specific attackers involved in the latest attack?
Block the attacker responsible for the recent credential stuffing attempt.
List all attackers that have targeted my /v1/login endpoint today.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Salt Security once, then ask.
One connection gives your AI access to your security data. Your credentials stay encrypted and secure on our end.
Connect Salt Security to your AIFAQ
How the task behaves
- 01
Can the AI block attackers automatically without me asking?
No. The AI only issues block commands when you explicitly tell it to do so.
- 02
Does the AI change my WAF configuration settings?
No. It only uses the specific tool to block an attacker; it cannot modify your broader WAF rules or policies.
- 03
Can I see the history of blocked attackers?
Yes, by asking the AI to retrieve attack data through the connector.
- 04
Will the AI delete any of my existing security logs?
No. The tools only allow for reading data and issuing blocks. There is no tool to delete logs.
- 05
Can the AI identify the specific IP address of an attacker?
Yes, it can retrieve attacker details to help you identify their footprint.
More questions about Salt Security? The Connector page answers them. See everything the Salt Security Connector can do
Connect Salt Security to Claude, Cursor, ChatGPT & more
