- READ
- INSPECT
- UPDATE
- HUMAN
Short answer
How can I triage security findings with my AI?
Your AI pulls live Semgrep findings and lets you inspect the specific code context for each vulnerability. You can then tell your agent to update the status of any finding to keep your dashboard current. Here is how it works.
Triage outcomes.
Where your findings land.
The AI moves data between your chat and Semgrep to keep your security posture updated.
READ
Live scan data
The AI pulls your current Semgrep findings into the chat. You get a real-time view of what's broken in your code.
INSPECT
Deep vulnerability context
Your agent looks up the exact details and location of a specific finding. This helps you decide if a hit is a real threat or a false positive.
UPDATE
Status management
Tell your AI to change the status of a finding. It syncs that change back to Semgrep immediately.
HUMAN
Final decision making
The AI handles the data fetching and status updates, but you decide which vulnerabilities actually matter.
The workflow
What your AI does when findings arrive.
The AI acts as the bridge between your security scans and your decision making.
Fetch scan results
The AI pulls a list of all current security issues from your Semgrep account.
list_findingsAnalyze specific hits
Once you pick a finding, the AI pulls the specific metadata and code context.
get_finding_detailsUpdate the dashboard
After you review a finding, the AI pushes the new status back to the platform.
update_finding_statusVerify the fix
You can ask the AI to check the latest findings list to ensure a status change was successful.
list_findings
Try it
Copy these to start.
Use these prompts to begin triaging your security issues.
Starting points
These are just ways to kick off a conversation. Swap out the repo names or finding IDs for your own.
Semgrep Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_419UaVAC33VwJmeeVBLCqRf2d8eEEPrGrsnPeNVU/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 — Semgrep capabilities are ready to use.
{
"mcpServers": {
"semgrep-mcp": {
"url": "https://edge.vinkius.com/vk_preview_419UaVAC33VwJmeeVBLCqRf2d8eEEPrGrsnPeNVU/mcp"
}
}
}List all the current Semgrep findings for my main repository.
Get the details for finding ID 12345 and tell me if it looks like a real risk.
Mark finding ID 67890 as 'fixed' in Semgrep.
Show me all the high-severity findings currently active in my Semgrep account.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Semgrep once, then ask.
Just link your Semgrep account to Vinkius. Your credentials stay encrypted and you can start chatting with your security data immediately.
Connect Semgrep to your AIFAQ
How this task behaves.
- 01
Can the AI fix the code for me?
No. The AI can pull the code context and update the status of a finding, but it cannot write or commit code changes to your repository.
- 02
Will the AI delete my findings?
No. The tools only allow the AI to update the status of a finding. It cannot delete findings from your Semgrep dashboard.
- 03
Can I use this with any AI client?
Yes, as long as the client supports the Model Context Protocol (MCP).
- 04
Does the AI see all my code?
The AI only sees the specific finding details and code snippets that it requests through the Semgrep tools to answer your questions.
- 05
Can the AI create new scan rules?
No. This MCP is designed for triaging existing findings, not for managing or creating Semgrep rules.
More questions about Semgrep? See everything the Semgrep Connector can do
Connect Semgrep to Claude, Cursor, ChatGPT & more
