"ROS" matching MCP servers:

Enables Grok Bot Chiefs of Staff on separate user accounts to pair with owner approval, exchange addressed task proposals and availability windows, manage asymmetric capability grants, and revoke access through a hosted mailbox service. It runs as a standard MCP stdio client that authenticates with an owner's agent credential and supports contacts listing, message submission, cursor-based inbox polling, and idempotent retries.

Deterministic <1µs in-band execution governance gateway and W3C DID security guardrail for AI Agent MCP tool calls.

Provides read-only access to PostgreSQL databases via MCP, enforcing least-privilege roles, row-level security, masked views, and SQL AST guardrails to prevent data leakage and unauthorized operations, enabling AI agents to safely query sensitive production data.

Enables MCP access to multi-tenant PostgreSQL data where tenant isolation is enforced by row-level security instead of application-layer filters, removing the need for per-handler tenant checks and service-role keys on the request path.

A ready-to-deploy MCP server with in-process agent verification via KYA-OS Checkpoint, enabling secure tool access for verified agents.

Provides read-only access to VeriLock document metadata and cryptographic evidence, enabling clients to list, retrieve, verify, and audit documents through the Model Context Protocol.

Security scanning for AI coding tools (Claude Code, Cursor, Windsurf) including secrets detection, MCP config vulnerabilities, agent instruction checks, threat modeling, prompt injection testing, pre-commit security checks, and dependency vulnerability scanning.

MCP server for verifying high-impact decisions with Trust OS.

Enables technicians to discover, audit, and configure MikroTik RouterOS routers over SSH, with dry-run change plans, automatic rollback, and local handling of credentials and keys.

MCP server for iOS reverse engineering, enabling static analysis of IPA/Mach-O binaries and dynamic instrumentation via Frida for tasks like IAP interception and FairPlay decryption.

MCP Blast-Radius Auditor — statically extract what an MCP server can touch and detect declaration divergences against manifest.json. Stdio MCP (mcp-blast-radius) plus CI gate (mcp-blast-radius-gate). pip install mcp-blast-radius==0.2.0

Enables assessing and comparing domains for email spoofing risk by evaluating SPF, DMARC, MX, and DKIM records from public DNS, providing A-F grades and concrete remediation steps.

Governance kernel for AI agents — policy enforcement, code safety verification, multi-model hallucination detection (CMVK), trust attestation (IATP), and immutable audit trails. Works with Claude Desktop, Cursor, and any MCP client.

Enables AI coding agents to read an allowlisted monday.com board and propose changes, while writes require a frozen column contract and human approval before being committed. The monday API token never leaves the server.

Deployable MCP server with Google OAuth for remote connections, enabling authenticated tool access via Cloudflare Workers.

Enables interaction with HashiCorp Vault for secret management operations including reading, writing, listing, and deleting secrets through the Model Context Protocol.

Enables MCP clients to interact with Palo Alto Networks firewalls and Panorama, providing tools to retrieve address objects, security zones, policies, and system information.

Enables AI agents to trade on Binance through a governed MCP proxy that enforces configurable policies, requires a recorded rationale before orders, detects prompt injection, logs all actions in a tamper-evident audit trail, and blocks execution until a human approves.