"Bambu Lab" matching MCP servers:

MCP server that lets an AI assistant perform scoped Okta identity operations with an out-of-band human-approval gate on destructive actions.

A research harness for measuring whether MCP clients preserve informed consent when tool definitions change after approval.

Enables guided security evaluation of a virtual lab machine, including network scanning, HTTP/TLS analysis, OWASP Top 10 assessment, and Markdown report generation, without performing exploitation.

Bee by HEOSSI is a governed MCP server exposing 14 tools for specialist intelligence, code, security, research, provenance, usage, tenant-scoped documents and memory, and Quantum Reasoning Lab workflows. Hosted calls are authenticated, plan- and policy-gated, and metered.

Enables enterprise-managed authorization for MCP on Azure App Service, with deployable Entra OAuth and a local EMA ID-JAG lab exposing whoami and authorization_model tools.

Enables users to statically analyze regular expressions for catastrophic-backtracking (ReDoS) risk through real AST parsing rather than executing the pattern, flagging nested quantifiers, ambiguous alternation, and backreferences. It also generates candidate proof-of-concept attack strings with a timeout-guarded test snippet and suggests JavaScript-safe rewrites.

An MCP server exposing scoped, read-only enterprise operations tools with fail-closed credential handling. It returns opaque approval IDs for mutations and requires a separate operator approval command to release one-time capabilities.

Enables users to audit Dockerfiles for container-security anti-patterns, including missing USER, baked-in secrets, curl | sh / wget | bash, unpinned base images, and ADD with remote URLs. It parses Dockerfile structure to return risk levels and actionable fixes.

Enables Entra-authorized monitoring and control of an EG4 inverter via MCP, with OBO delegation and safety gates.

Enables users to scan AI agent skills and configuration files for hidden Unicode instructions, prompt injection, download-and-execute payloads, exfiltration patterns, and overly broad permissions before installation. It provides static audit tools for skill files, agent configs, and revealing hidden text without executing or fetching the input.

Enables scanning arbitrary text and added lines in unified git diffs for accidentally committed credentials, using precise vendor-format matches and entropy-based detection. All detected secrets are redacted before results are returned, helping coding agents and developers catch leaks without exposing full values.

MCP server that gives AI agents secure, consent-based access to a single browser tab, supporting read-only snapshots, element interaction with per-action approval, and frozen multi-step plans, all audited.

Exposes common CTF and cybersecurity tools (crypto, forensics, malware analysis, steganography, reverse engineering, pwn, OSINT) so LLMs can help solve capture-the-flag challenges in a controlled lab environment.

A comprehensive MCP server for Apache Superset. Gives AI assistants full control over your Superset instance — dashboards, charts, datasets, SQL Lab, users, roles, RLS, and more — through 137 tools.

Enables auditing package.json files for real npm supply-chain attack mechanisms — typosquatted dependency names, malicious preinstall/install/postinstall scripts that pipe downloads into a shell or decode base64 payloads, and unpinned versions — plus live npm registry lookups that flag nonexistent, brand-new, deprecated, or typosquatted packages. It exposes dedicated tools for full manifest audits and single-name typosquat checks.

Provides permission gates and tamper-evident audit logging for AI agent tool executions, with declarative policies, consent ladders, and hash-chained verification.

Enables users to audit other MCP servers' tool definitions for agentic attack classes such as tool poisoning, sensitive-path references in metadata, and tool shadowing via invisible Unicode or homoglyphs. It can analyze a tools/list payload, check a single description string, or connect to a public remote MCP URL to fetch and audit its tool list.

Screens payee and bank-account change requests with seven checks, issues safe callback scripts, and requires a named owner to approve or block before any change proceeds.

Enables large language models to interact with Velociraptor DFIR through natural language, allowing queries and analysis of forensic data, artifacts, hunts, collections, and VQL results.

Authorized Android pentest lab, drivable by hand or by AI — Frida bypass chain, live traffic capture with automatic IDOR flagging, full MCP control plane, web dashboard.