Any MCP client
GitHub Security Vuln Triage
Code agentRe-prioritizes GitHub Dependabot alerts by exploitability, files Jira tickets, alerts Slack
0Not yet rated, 0 reviews
Free
Phishing Email Analyzer
Static read-only phishing email analysis: deterministic 0-100 risk score, header + URL indicators, and an LLM-written explanation.
Works with
Claude (web & desktop)ChatGPT (Plus / Pro)CursorVS Code (Copilot)Claude CodeGemini CLIWindsurfClineContinueZedLM StudioGooseJetBrains AI AssistantWarpPostmanand more
Before you connect: what this agent would do
A preview derived from this agent’s definition — not a live run. Nothing runs and no key is sent until you connect. FindAgent runs it in an isolated sandbox on the hosted connection.
Credentials it will ask for (2)
- Anthropic API Key· optional
Only ever sent to: api.anthropic.com
- OpenAI API Key· optional
Only ever sent to: api.openai.com
Safety rails that guard it
- Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no agent can turn off.
Connect over MCP — runs anywhere
Phishing Email Analyzer runs on FindAgent and connects over MCP — no download, no local runtime. Add the server URL to any MCP-capable client.
1 · Choose your client
2 · Add the server URL
remote MCP
https://mcp.findagent.cloud/agents/phishing-email-analyzerChatGPT (Plus / Pro): Settings → Connectors → add a remote MCP server, then paste the URL and approve it.
You add this server inside your client and approve it once — that in-client step is a security check, so there's no one-click button for it.
Signing in: the first time you connect, your client opens a FindAgent sign-in page — approve once and you're connected. There's no API key or token to copy; access is tied to your FindAgent account.
What you'll need — and where to get it
You enter these when you connect. They're encrypted, only ever sent to the agent's allowed hosts, and never shared with the creator.
Anthropic API Key · optional
Optional. Enables the LLM-written explanation via Anthropic. Without a key (and no host sampling) the agent falls back to a deterministic template. The verdict and risk score are never changed by the LLM.Create a key on the Anthropic Console API keys page (console.anthropic.com → API keys).Paste the value as a single line.Only sent to: api.anthropic.comOpenAI API Key · optional
Optional. Enables the LLM-written explanation via OpenAI instead of Anthropic.Create a secret key on the OpenAI API keys page (platform.openai.com → API keys).Paste the value as a single line.Only sent to: api.openai.com
Related agents
CompareAny MCP client
AML Transaction Screener
Code agentDeterministic AML rule engine over Postgres transactions with SAR draft generation
0Not yet rated, 0 reviews
Free
Any MCP client
SIEM Alert Narrator
Code agentRead-only SIEM alert triage: deterministic correlation, noise suppression, and priority scoring, with an LLM-written analyst narrative.
0Not yet rated, 0 reviews
Free
More from @kata-team
Any MCP client
GA4 Anomaly Detector
Code agentDeterministic z-score/IQR anomaly detection on GA4 time-series, LLM-narrated alerts. Runs on mock or your own data; connector-ready.
2Not yet rated, 0 reviews
Free
Any MCP client
GA4 Site Blood Test
Code agentGA4 site-health blood test: a 0-100 score, critical findings by device, an LLM-written prescription, and B2B SaaS vendor matches.
1Not yet rated, 0 reviews
Free
Any MCP client
YouTube Analytics Narrator
Code agentTurns YouTube Analytics metrics into a deterministic performance narrative + recommendations
1Rated 5.0 out of 5, 1 review
Free