"How to browse the internet" matching MCP servers:

Routes web requests from AI tools through Tor for anonymized fetching, with selective per-URL routing to bypass Tor-blocking sites.

Enables LLM agents to browse and triage vulnerability observations, manage products, branches and rules, import scan reports and SBOMs, run scans and background jobs, and generate VEX documents via SecObserve's REST API.

Lets AI agents check whether an EVM wallet address carries an EIP-7702 delegation across eight chains (Ethereum, Base, BNB Chain, Arbitrum, OP, Polygon, Gnosis, Unichain) and learn how to obtain a deeper paid report with delegate bytecode heuristics and risk levels. Read-only, never touching private keys or seed phrases.

qURL is the portal to the invisible internet -- expiring, scope-limited URLs that let AI agents reach services no one else can see.

MCP server for auditing infrastructure-as-code attack paths, finding multi-hop chains from public internet to sensitive resources.

Runs a regular expression on real engines — JavaScript (V8), Python (CPython re), PCRE2 and RE2 — reporting each engine's own compile errors with positions, every match with its groups and named groups, replacement results, and where the engines disagree. It also detects catastrophic backtracking (ReDoS), naming the at-risk part of the pattern, generating an attack string, and timing how long each engine actually takes on it.

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 AI assistants to raise, submit, approve, amend, and cancel purchase orders and onboard suppliers in ERPNext or SAP S/4HANA while enforcing procurement controls such as duplicate detection, budget limits, split-purchase checks, price tolerances, and segregation of duties.

Enables agents to query internet asset data through full FOFA DSL or structured conditions, with cursor-based pagination, field aggregation statistics, host/IP detail lookup, and account quota inspection. Adds multi-account rate-limit failover, local budget and size caps, and credential-safe diagnostics so large collection tasks can run reliably without exposing keys.

MCP server for Verigent's AI agent verification, enabling agents to verify themselves, check other agents' status, and browse the leaderboard.

A secure email gateway MCP server that protects AI agents from prompt injection attacks by scanning emails for malicious instructions before they reach the agent.

Checks how long ago a package version was published and returns the newest version older than a minimum age (3 days by default), so an agent avoids brand new releases when adding dependencies. Also checks lockfiles across 15 ecosystems; read-only.

A demonstration server that reveals security risks by accessing sensitive environment variables, illustrating how MCP tools can potentially leak user data without explicit consent.

Enables any MCP client to look up CVE intelligence — severity summaries, filtered searches, and full per-CVE detail fusing NVD, MITRE-CNA pre-NVD, CISA KEV, EPSS, and GitHub GHSA data — alongside a Shodan-derived internet-exposure footprint showing how many internet-facing services run a version mapping to a given CVE. It is free, keyless, and read-only, and distinguishes verified zeros from unassessed or failed lookups.

Enables an AI agent to create and control a persistent, visibly AI-labeled social identity owned by a locally held Ed25519 key, then browse the public agent registry, request and accept mutual connections, and exchange direct messages with connected accounts.

Enables AI assistants to read the free public ICHI API via MCP stdio, retrieving the current Internet Cyber Health Index, recent critical alerts, and source health with structured JSON results and graceful error reporting.

Enables AI agents to browse customers, bookings, and availability while any booking creation or cancellation stays gated behind a human-approved, single-use token cryptographically bound to the exact arguments. Runs over stdio or Streamable HTTP and enforces the read/write separation in host code with a full audit trail.

A read-only MCP server that lets an agent browse the HackerOne Hacker API using an authenticated hacker account, exposing programs, policies, scope, reports, and payments. It cannot create, update, or submit reports.

Enables checking IP addresses against the GreyNoise API to determine if they are internet background noise, known benign services, or potentially targeted threats.

Enables comprehensive security reconnaissance, vulnerability assessment, and threat intelligence gathering by integrating Shodan's API. It provides tools for searching internet-connected devices, performing DNS operations, and querying the Shodan exploit database.

AI agent identity, permissions, trust scores, and tamper-evident audit trails. 17 MCP tools: register agents (Ed25519 keypairs), check permissions (sub-5ms), emit audit events, verify trust scores (0-100), delegate credentials, ephemeral agents. IETF Internet-Draft filed. Works with LangChain, OpenAI, CrewAI, Stripe ACP. npx @vorim/mcp-server

Enables read-only access to Circle parental-control data, including family profiles and per-profile internet usage.

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

Enables AI coding agents to plan, policy-check, and cost-estimate Terraform changes while requiring human approval through Slack or CLI before any terraform apply can execute.

MCP server for AI agent identity — verify agents with Ed25519 signatures, check trust scores, sign and verify content, exchange encrypted messages. Built on the Agent Identity Protocol (AIP).

A local-first AWS security tool that uses graph theory to discover attack paths (e.g., Internet → Role → DB) and prioritize remediations. It allows agents to perform read-only security audits and generate Terraform fixes without data exfiltration.

Enables AI assistants to perform password security auditing using John the Ripper on a remote Kali system via SSH, supporting cracking, hash management, and session control.

Living off the Land intelligence for AI agents. GTFOBins, LOLBAS, LOOBins, LOLDrivers, LOLRMM, WADComs, LOLC2 and more — unified into a single MCP server.

Provides access to Shodan API functionality, enabling AI assistants to query information about internet-connected devices for cybersecurity research and threat intelligence.

Enables working with private files on a local machine from ChatGPT through OpenAI Secure MCP Tunnel without opening inbound ports or exposing the local server to the Internet, with tools for listing, reading, creating, modifying, deleting, backing up, and restoring authorized workspace files under strict permissions.