"OpenRouter thinking or reasoning capabilities" matching MCP servers:

A Model Context Protocol (MCP) server for interacting with Joe Sandbox Cloud. This server exposes rich analysis and IOC extraction capabilities from Joe Sandbox and integrates cleanly into any MCP-compatible application (e.g. Claude Desktop, Glama, or custom LLM agents).

Lets AI assistants work on sensitive files by reasoning over schemas and masked output while deterministic local code handles raw data, never exposing real values to the model.

Enables AI agents to verify trust scores, search certified capabilities, compare side-by-side, and submit experience reports through Fidensa's certification authority.

Enables AI agents to create cryptographically verifiable receipts of their delegated work, with capabilities for multi-party approval and offline verification.

Portable, read-only MCP server for Nous Portal capabilities, providing configuration status, route derivation, and OAuth device code authentication without invoking paid tools.

MCP server that exposes OSSEC HIDS security monitoring capabilities as tools, resources, and prompts for AI assistants.

MCP server for Precogly threat modeling, enabling users to integrate threat modeling capabilities into AI assistants.

Provides sensitive word detection and filtering capabilities for LLMs, supporting multiple categories and real-time lexicon updates.

An MCP server that provides safeguard capabilities to protect against prompt injection and unsafe tool calls.

Transparent Go proxy that intercepts, signs, rate-limits, redacts, and audits all MCP JSON-RPC tool calls without modifying client or server. Stores to JSONL or SQLite with HMAC-SHA256 signatures.

A Model Context Protocol server that provides network packet capture and analysis capabilities through Wireshark/tshark integration, enabling AI assistants to perform network security analysis and troubleshooting.

Connects autonomous AI agents and IDEs to the Delentia Sovereign Edge Network, providing deterministic security gating, structured reasoning, context compression, and swarm coordination tools.

Enables Claude to interact with Okta's user management system, providing capabilities to retrieve user details, list users with filtering options, and manage user groups.

Enables interaction with the AssemblyLine 4 malware analysis platform, allowing file submissions, URL analysis, and search capabilities via natural language.

OmniGlyph is a local-first MCP server that gives AI agents deterministic Unicode, domain-term, security-scan, and output-guardrail checks before reasoning over text or delivering generated output.

A server that provides access to Baidu Cloud's content moderation capabilities for detecting unsafe content, allowing applications like Cursor to check text for security risks.

An MCP server that provides deepfake detection capabilities, allowing clients to analyze images for authenticity via Proofly's API.

Exposes Nmap network scanning capabilities through a Model Context Protocol (MCP) server, allowing users to perform various types of network scans including vulnerability assessment, service detection, and OS fingerprinting.

A Node.js server implementing Model Context Protocol (MCP) that enables natural language interaction with Binalyze AIR's digital forensics and incident response capabilities.

An AI-powered penetration testing reasoning engine that provides automated attack path planning, step-by-step guidance for CTFs/HTB challenges, and tool recommendations using Beam Search and MCTS algorithms.