"A task involving critical or creative thinking" matching MCP servers:

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Enables MCP clients and agents to create, list, and update the status of to-do tasks, while restricting them to least-privilege operations.

Provides agent certification and trust verification tools for AI agents, enabling certification checks, trust score calculations, audit ticket issuance, and emergency kill switch activation through the A-SOC trust network.

767-2676.com provides tools to hash task schedule bytes and verify signed time and digest receipts for deadline, cancellation, expiry, and handoff checks. Try the free offline sample at https://767-2676.com/schedule/example; fresh signed witnesses cost $0.001 USDC and require payment authorization.

Enables AI agents to manage VPN infrastructure through provisioning, lifecycle control, traffic routing, and health monitoring.

Enables MCP clients to triage SOC alerts while enforcing a trust firewall across retrieval, memory, and privileged actions. It exposes tools for alerts, logs, memory, and alert actions, with defenses that refuse risky operations in the presence of attacker-controllable content.

Enables executing arbitrary Joern/CPGQL queries against a loaded Code Property Graph, loading source code in multiple languages (PHP, Java, JavaScript, Python, C/C++) to build new CPGs, and inspecting loaded projects and the active workspace. It communicates with a running Joern server over its synchronous HTTP query endpoint, so no state polling is required.

An MCP server that exposes tools for issuing scoped agent credentials, delegating narrower child credentials, handling approvals, revoking task trees, and retrieving audit trails and evidence packets.

MCP proxy that puts a deterministic gateway in front of any MCP server. Every critical tool argument (payee, amount, recipients) must resolve against a signed mandate or the user's own registries before a Cedar policy decides; step-ups are confirmed by the user through MCP elicitation, and every decision is a hash-chained receipt.

Investigate fraud directly from Claude, Cursor, or any MCP-compatible client. Analyze suspicious activity with clear, evidence-backed verdicts. Pivot from a single signup to every account sharing the same device, IP address, or email inbox. Check entities against a cross-operator abuse network, review linked accounts, and efficiently process your fraud review queue. Read-only by default, with no r

Verifies agent actions against mandates via a single tool, returning allow, deny, or requires_approval receipts without executing the actions.

Mandatory human approval gate for autonomous AI agents. Before any critical, irreversible, or financially significant action executes — file deletion, production deployment, financial transaction — the agent calls oracle_validate. A human receives a real-time Telegram notification with full context and taps Approve or Reject. The agent waits for the decision before proceeding.

Provides a human-approval tool for MCP-compatible agents, pausing execution until a human approves or edits the action, with every decision logged.

Enables AI agents to register proposed outbound or destructive actions, such as sending, deleting, publishing, paying or deploying, and block until a human approves or denies them out-of-band via a CLI. Requests default to fail-closed with a one-hour TTL and every request, decision and expiry is written to an append-only audit log.

Enables email address verification through a single MCP tool, returning whether an address is valid, invalid, or risky.

Enables agents to reuse a human-completed Chrome login session to open confirmed origins, read visible page text, and perform single click, fill, or key press actions without ever handling passwords or exposing cookies.

Enables AI agents to search, correlate, and monitor real-time vulnerability intelligence from NVD, CISA KEV, EPSS, and MITRE ATT&CK, including CVE details, critical CVE tracking, known exploited vulnerabilities, and exploitation probability scores.

AI agent identity and reputation registry. Ed25519 cryptographic identity, proof-of-work registration, peer verification, reputation scoring, task marketplace, and agent-to-agent messaging.

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.

Provides cached, structured snapshots of recent CVEs and GitHub Security Advisories, enabling AI agents to lookup CVEs, find vulnerabilities for a package by ecosystem, list recent critical CVEs, and get severity summaries.

Enables AI agents and developers to audit any URL or domain for seven critical OWASP HTTP security headers, returning an A+ to F grade plus actionable Nginx, Apache, Caddy, and Cloudflare remediation snippets. It also probes /.well-known/security.txt and /security.txt to surface responsible vulnerability disclosure contacts, bug bounty scopes, and PGP keys.

Enables AI agents to connect to Odoo ERP for safe read operations, guarded draft creation, and approval-gated critical mutations through a deterministic security firewall.

Order limits, human approval (terminal or Telegram), a kill switch and a hash-chained audit log in front of any broker or exchange MCP server. Verified profiles for Alpaca MCP and CCXT MCP.

Verifiable agent-to-agent task handoff with signed provenance chain.

A read-only Model Context Protocol server that exposes DefectDojo API v2 findings to AI agents, enabling vulnerability triage across products and drafting of self-contained tracker issues. It provides tools to list products, filter findings by severity, group critical findings by unique vulnerability, and fetch full finding details.

Provides deterministic intent routing and safety gating for multi-agent systems, enforcing P0 critical word detection, mutually exclusive hard rules (MX-1/2/3), and a permission matrix as pure functions via four MCP tools.