"Counter-Strike" matching MCP servers:

Enables management of Cobalt Strike red team operations through natural language commands, providing access to 200+ tools for beacon control, listener management, credential operations, and payload generation.

Protects AI agents from threats like prompt injection, jailbreaks, and SQL injection through a multi-layer scanning pipeline. It also enables PII redaction and rehydration to ensure data privacy during LLM interactions.

Enables deterministic request screening and, after native owner approval, fixed-target DeadBolt enforcement actions such as kill, deny, revoke, and evidence retrieval through local stdio MCP. Model analysis can advise but cannot approve actions.

Fleet-wide shared rate limiter for A2A + multi-MCP deployments, providing a shared counter with sliding window, concurrency grants, and signed enforcement attestations.

Enables vendors to run a declared check battery against their own MCP server, emit sealed Assay-format scorecards with evidence hashes and environment fingerprints, and have a local verifier re-run a random sample to issue counter-signed verification receipts.

Enables an agent to find a business by phone number, check availability, book and cancel appointments, and verify business-signed receipts against a sandbox registry and demo shops that run locally over stdio. Every registry record and receipt is signature-checked, and nothing real is booked because the shops live inside the server process.

Enables fraud analysis and management through Stripe's Radar system, allowing users to assess payment risk, create refunds, and access any Stripe API endpoint. Focuses on fraud detection with automated recommendations while providing full Stripe API access.