"Using npx to run tools directly without requiring an API" matching MCP servers:

Your AI agent can't touch Stripe, Gmail, Slack or more, without your tap. mild.run intercepts every sensitive action and sends you a notification to approve or block — before anything executes. Agent never holds credentials.

A comprehensive suite of HTTP and API testing tools that enables AI agents to perform requests, check endpoint health, and decode JWTs. It also provides utilities for URL parsing and detailed security analysis of HTTP response headers.

Enables AI coding agents to inspect GitHub repositories and shell commands for download-and-execute payloads, obfuscation, typosquatted dependencies, autorun hooks, and fake-star signals before following or running them.

Enables AI agents to perform common utility tasks through a streamable HTTP MCP endpoint, including JSON inspection, regex testing, cron parsing, hashing, base64 encoding/decoding, URL analysis, color conversion, text diffing, CSV parsing, JWT decode/verification, Markdown-to-HTML rendering, and UUID/token generation without API keys.

A secure MCP server example that demonstrates how to deploy to Google Cloud Run with authentication and identity token protection. Serves as a tutorial template for building production-ready MCP servers in the cloud.

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.

Post-quantum readiness for AI coding agents: scans code for quantum-vulnerable cryptography (RSA/ECDH/ECDSA/DH) and returns NIST ML-KEM/ML-DSA/SLH-DSA (and hybrid) migration guidance, with fix verification and dependency checks. Content-based, advisory tools only; runs local (npx @quantakrypto/mcp) or as a hosted OAuth endpoint.

Enables AI agents to pay per call for live package-safety and GitHub merge-readiness trust signals via the x402 protocol.

Community MCP server for the Cymulate security validation platform. It exposes the full Cymulate REST API (337 endpoints) as 106 semantic tools for BAS, exposure validation, attack surface management, and platform administration.

Enables high-precision detection, anonymization, encryption and decryption of personally identifiable information (PII) in text using GPT-4o-based detection and advanced cryptographic methods. Supports both deterministic encryption for searchable data and format-preserving encryption for structured identifiers.

Wraps the Remnawave API to provide per-operation MCP tools with mutation safety and data redaction, enabling secure interaction with Remnawave panel.

A hosted Model Context Protocol server that lets AI agents triage review queues, investigate authors, tune policies and wordlists, respond to incidents, configure projects and webhooks, and report on moderation activity through a Moderation API account.

Enables MCP clients to use paid tools for secret scanning, agent-config auditing, and OG image rendering, with payments handled over the x402 protocol on Base.

Signed, offline-verifiable authorization for API-contract changes. Before a contract change (OpenAPI, GraphQL, Protobuf, AsyncAPI, MCP manifests) merges or deploys, the agent calls preflight_change_set; the decision is deterministic, signed, and verifiable without calling CodeRifts. Three tools: preflight_change_set, verify_receipt, get_decision_details. Only a granted change can proceed.

Enables AI agents to rehearse risky actions — SQL, shell, git, Terraform, cloud and SaaS operations — against simulations of the real system before executing them, so they can see the consequences first. Returns a consequence report with a safe, confirm or block verdict, blast radius, reversibility and evidence, without ever executing the action itself.

Enables voice and chat AI agents to invoke identity-gated tools without exposing caller identity to the model, starting with SMS link verification and customer registration. Tool calls rely on host-attached signed tokens to enforce verification levels and scopes before sensitive actions.

Enables MCP clients to count tokens and estimate costs, run BM25 search, compare model evaluations with paired bootstrap and McNemar tests, validate JSON Schema output, and scan for prompt injection and PII.

Enables users to check a site, e-mail, phone number, IBAN, or SIREN against public sources and receive sourced anti-scam signals in French. The same checks are available remotely over MCP and locally via stdio, sharing the HTTP API's key and quota.

Presents a plausible, tool-rich workspace surface — file reading, credential listing, command execution, database queries, and configuration retrieval — that returns only synthetic results while logging every connection, tool call, and argument received. It enables researchers to measure what MCP clients and agents actually do when handed dangerous-sounding tools, including whether they follow injected instructions or complete a retrieve-then-use credential chain.

Turns an OpenAPI specification into a broker-published slot of curated, LLM-ready tools that a human operator reviews, tests, and approves before anything goes live. The resulting tools are declarative and run under the broker's authorization, audit, execution limits, and secret handling.

Enables Claude to call any HTTPS API using vault-stored secrets without exposing credentials to the model, while enforcing per-secret host restrictions and approval for destructive actions.

Provides 9 utility APIs for AI agents covering DNS, email, IP, QR, WHOIS, URL health, headers, text extraction, and tech detection, with x402 micropayments on Base.

Dependency health checker for AI agent skills. Analyzes external endpoints for uptime, SSL validity, domain reputation, ownership changes, and abuse scores. Returns a 0-100 trust score per endpoint.

Enables guardrail and trust testing by exposing realistic malicious tool patterns such as shell execution, credential dumping, and data exfiltration, all without network access.

Enables AI agents to run passive, boundary, and gated active reconnaissance and web-security CLI tools (nmap, sqlmap, commix, httpx, ffuf, nikto, subfinder, and more) against authorized targets through a persistent, API-key-protected HTTP service. Scope gates, authorization windows, evidence capture, and a full audit trail are enforced in code so every tool call stays within the engagement's declared rules.

MCP server for inspecting email domains and addresses, providing objective domain-level email infrastructure answers such as MX, SPF, DMARC, MTA-STS, and disposable-domain evidence.

Site, email and agent safety — SPF/DKIM/DMARC, AI/SEO audit, page-change monitor, free hidden-AI scanner (7 MCP tools).

Enables MCP clients to discover and call Danske Bank public APIs through a hosted MCP server, adding OAuth/mTLS authentication and endpoint URL validation via a local call_endpoint tool.

Enables AI assistants to manage Namecheap domains, DNS, contacts, registrar locks, and view SSL certificates and pricing through safe read and configuration tools.

Enables querying MITRE ATT&CK and D3FEND data efficiently, providing techniques, detections, mitigations, actors, and countermeasures with token-aware summaries and paginated graph traversal.

Enables cryptographic operations including hashing, encoding/decoding, ID generation, password tools, and JWT inspection via MCP.

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 testing API authentication and authorization by probing endpoints with and without Authorization headers, suggesting auth test matrices for roles, and showing current test configuration.

Fork of @cyanheads toolkit MCP server. Added encoding functions, removed system network functions.

Enables AI coding agents to read GitHub issues and pull requests and to add comments only on allowlisted repositories, with every call recorded in an append-only redacted audit log.

Defense-grade cryptographic compliance and analysis tools for MCP, including FIPS 140-3 validation, CNSA 2.0 analysis, post-quantum readiness assessment, and classical cipher utilities.

Exposes typed inventory reads and order preparation over MCP, with capability scopes enforced by the server process rather than tool arguments. Stock is committed only through a separate operator approval surface, keeping approval outside the model's reach.

Enables scanning OpenAPI specifications for security gaps and generating security test checklists for APIs.

Local, read-only MCP server that provides verified access to bounded.tools' signed static API, including the Web-Build Conformance report and SPDX SBOM, with byte-for-byte verification against a Sigstore-signed manifest.

A Model Context Protocol server implementation that provides endpoints for wallet-based authentication, cluster management, and name registration services.