"Setting up an MCP server in Kubernetes" matching MCP servers:

A personal work twin for any AI agent. It briefs agents on the guidance you have confirmed, checks consequential actions against explicit, expiring grants and asks otherwise, and turns your corrections into lessons only you can confirm.

Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.

Blocks AI coding assistants from installing non-existent packages and accessing non-existent files.

Enables an AI assistant to diagnose a broken application on a local Kubernetes cluster by inspecting pods, events, and logs, with server-side guardrails, least-privilege RBAC, and an audit log. It can also restart deployments in allowed namespaces only after a dry-run preview and host approval.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.

An MCP authorization server implementing OAuth2/OIDC flows, supporting dynamic client registration, PKCE, consent screens, and client ID metadata documents for MCP authorization.

MCP server for ai-scanner that enables AI agents to scan codebases for LLM usage, AI frameworks, and exposed secrets.

Authentik MCP provides seamless integration with Authentik's API, supporting both full-featured and diagnostic modes. These enable secure, automated user, group, and system management through MCP-compatible tools.

An MCP server that provides authorization middleware for AI agents using private data, enabling consent management on Aleo and local private inference with persistent policy storage.

Self-hostable MCP server for WhisperGraph — a graph of 7.39B nodes / 39B edges mapping DNS, BGP, GeoIP, WHOIS, and threat intelligence. Six read-only tools (Cypher query + schema introspection + threat assessment), six resources, eight investigation prompts. stdio and Streamable HTTP transports.

Enables AI agents to explain regex patterns in plain English and statically assess ReDoS risk before shipping, without executing the pattern or requiring an API key.

Lets an agent verify VSL settlement receipts entirely offline and produce signed triggers authorizing a settlement, with the signing key and endpoint fixed at start-up rather than passed in tool calls. When started with an endpoint and token, it can also request a receipt from an issuer, which is the only tool that touches the network.

One local gateway for all your MCP servers — shared by every AI coding tool (Claude, Cursor, VS Code, Codex). Set up each server once; keys stay in the OS keychain; lazy discovery keeps agent context small. Local-first, open source.

Enables an AI assistant to read Interactive Brokers account and market data and to prepare order drafts that the user approves inside IBKR, while blocking any order submission to live markets. An opt-in paper-trading mode additionally allows simulated orders to paper accounts only, with per-order confirmation and logging.

Zero-knowledge password manager with MCP credential gateway. BIP-39 seed phrase recovery, deterministic passwords, policy-gated AI agent access with scope, rate limits, time windows, and step-up approval. Supports 70+ API key providers with hash-chain audit trail.

Enables AI agents to classify IP addresses through the VPNDetection API with read-only tools that detect VPNs, residential and datacenter proxies, Tor nodes, relays, hosting providers and CDNs, in single or bulk lookups of up to 100 addresses. It also exposes which datasets an organisation is licensed for, along with their metadata and published checksums.

GhostHunt is an MCP server that scans your development machine for API keys, tokens, and credentials hiding in places you forgot to check.

Lets a coding agent lint a Dockerfile or Kubernetes manifest through the Shipshape API, returning an A–F grade, score, pass/fail status, and every finding with its line, fix, and reference. Catches issues like root in the final stage, unpinned base images, curl | sh, secrets in ENV/ARG, and Pod Security Standards, resources, and probes violations before handing work over.

A drop-in Model Context Protocol (MCP) server that lets an AI agent query PostgreSQL — read-only, enforced at the database level, with real SQL validation, timeouts, cost limits, OAuth 2.1, and an audit trail.

An MCP server that provides comprehensive data verification in China, including identity, business, vehicle, OCR, and risk assessment services.

An MCP server that exposes 43 domain tools behind 4 meta-tools, applying guardrails such as budgets, rate limits, schema validation, human-in-the-loop confirmation for mutations, PII redaction, and an append-only audit log while reducing context window usage.

Read-only attack-path tools for cloud and Kubernetes: list the reachable routes from internet exposure to sensitive assets, explain each hop and the evidence behind it, and simulate a fix before recommending it. Connects to a running PerspectiveGraph engine.

Enables an AI assistant to list, search, and read email over IMAP without marking messages as read, and to create and revise reply drafts that you review before sending. It runs with least privilege, keeping the app password in an OS keychain or password store and never sending, deleting, or moving anything.

An MCP server that lets an AI agent look up a RealHandles identity and cryptographically verify its signed proof.

Open source input firewall for AI agents, in beta, packaged as an MCP server. A local scanner checks text, code, PDFs, images, QR codes, audio and video against a pattern library and reports findings and incomplete scans.

Enables Claude to look up known vulnerabilities in a project's dependencies across OSV.dev, CVE.org, NVD, CISA KEV and EPSS, then rank the findings by real-world exploitation so the most urgent fixes surface first. It supports single-package checks, keyword CVE searches, and whole-lockfile scans, with upgrade-path reasoning.

Provides live CVE data from NVD and EPSS without API key, enabling AI assistants to look up CVSS scores, search vulnerabilities, and check product CVEs.

Enables deterministic, offline diagnosis of Kubernetes and container failures, generation of exact YAML/Dockerfile fixes, secret and PII redaction, and zero-trust policy checks for agent-proposed commands.

Identity infrastructure for the agent economy. Mint an agent ~handle in two free calls with no human account, then verify anyone and read inferred traits under the consent the person set in advance.

Enables AI assistants to statically lint and explain Kubernetes manifests, surfacing security, cross-resource, RBAC, and removed-API issues with line numbers and safe fixes without a cluster or kubectl. It also redacts secret values and supports Helm values review plus optional rendered-chart linting.