Bring Ai Guardrails
to Cursor
Learn how to connect Pangea (Security APIs) to Cursor and start using 40 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Pangea (Security APIs) MCP Server?
Integrate Pangea into your AI workflows to provide a robust security layer for LLM interactions and organizational data. This server provides a unified interface to Pangea's cloud-native security services.
Key Capabilities
- AI Security & Guarding — Use
ai_guard_textandai_guard_promptto detect prompt injections, PII, and malicious content before they reach your model or user. - Data Privacy — Automatically redact sensitive information from plain text or structured JSON objects using
redact_textandredact_structured. - Secure Auditing — Maintain a tamper-proof record of activities with
audit_logand perform natural language searches through your security history viaaudit_search. - Threat Intelligence — Check for embargoed locations with
embargo_ip_checkand scan files for threats withsanitize_file. - Identity & Access — Manage authentication flows, user sessions, and authorization tuples directly from your agent.
How it works
- Subscribe to this server
- Enter your Pangea Token and Domain from the Pangea Console
- Start securing your AI agents in Claude, Cursor, or any MCP-compatible client
Who is this for?
- Security Engineers — Automate audit log analysis and threat intelligence checks within your existing tools.
- AI Developers — Implement safety rails and PII redaction for LLM inputs and outputs without building custom middleware.
- Compliance Officers — Quickly search and verify audit trails using natural language queries.
Built-in capabilities (40)
Analyze and redact content in LLM inputs/outputs
Scan text for PII, malicious content, and prompt injections
Guard LLM chat completions with integrated logging and tracing
Create a single secure audit log entry
Create multiple secure audit log entries
Search the audit log using natural language queries
Paginate through audit search results
Finalize the flow and receive session tokens
Start a sign-up or sign-in flow
Update flow state (e.g., submit password, OTP)
List active user sessions
Invalidate sessions
Programmatically create a user
Check if a subject has permission for an action on a resource
List all resources a subject can access
Define relationships for AuthZ
Get WHOIS details for a domain
Check if an IP originates from an embargoed country
Check a 2-character ISO country code against embargo lists
Scan a file for malware
Retrieve reputation scores for domains, URLs, or file hashes
Retrieve location data for an IP
Detect if an IP is a proxy
Get reputation score and verdict for an IP
Detect if an IP is a VPN
Check if a password hash prefix appears in breach data
Redact specific fields in a JSON object using JSONPath
Redact sensitive data from plain text
Apply sanitization rules to a file and receive a cleaned version
Delete files or folders
Create folders in Secure Share
Download a file or retrieve metadata
List objects in a bucket or folder with filtering
Decrypt data previously redacted using FPE
Check if an email, phone, or username appears in known data breaches
Perform cryptographic decryption
Perform cryptographic encryption
Retrieve item details or secret values from Vault
Generate symmetric or asymmetric keys in Vault
Store a secret or token in Vault
Why Cursor?
Cursor's Agent mode turns Pangea (Security APIs) into an in-editor superpower. Ask Cursor to generate code using live data from Pangea (Security APIs) and it fetches, processes, and writes. all in a single agentic loop. 40 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
Pangea (Security APIs) in Cursor
Pangea (Security APIs) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Pangea (Security APIs) to Cursor through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Pangea (Security APIs) in Cursor
The Pangea (Security APIs) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 40 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Pangea (Security APIs) for Cursor
Every tool call from Cursor to the Pangea (Security APIs) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I protect my LLM from prompt injections or malicious content?
You can use the ai_guard_prompt tool to analyze LLM messages. It scans for prompt injections, PII, and other security risks, providing a safety score and redaction suggestions before the data is processed.
Can I search through my security logs using natural language?
Yes! The audit_search tool allows you to query your secure audit logs using natural language or structured queries, making it easy to find specific events without complex SQL.
How do I automatically redact PII from a block of text?
Use the redact_text tool. Simply provide the text, and Pangea will identify and mask sensitive information like emails, phone numbers, and names based on your configured rules.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Maileon
9 toolsManage email marketing contacts, mailings, and reporting via the Maileon REST API.
HeyGen
11 toolsAutomate AI video generation via HeyGen — manage avatars, videos, and templates directly from any AI agent.
DataForSEO
10 toolsManage SERP data via DataForSEO — track Google organic rankings, audit Maps nodes, monitor News publications, and research Amazon products directly from any AI agent.
Coassemble
8 toolsManage online training and LMS via Coassemble — track courses, monitor enrolments, and manage student groups directly from any AI agent.