"A resource for finding prompts" matching MCP servers:

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.

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

An MCP server that reads a file's embedded C2PA Content Credential to report whether it declares AI generation or a real-world capture, and checks whether that declaration's signature still verifies against the file's current bytes.

Offline MCP server that checks and scans your own AI prompts and outputs against a local compliance rule corpus. Returns rule ID, severity, citation, and remediation per finding — no API key, Apache 2.0.

PCI DSS v4.0.1 compliance scanner for Go payment services, delivered as an MCP server. Every finding maps to a specific PCI DSS requirement ID. Taint-aware cardholder data flow analysis with PCI SSC FAQ semantics, designed to complement broad SAST tools like Semgrep and CodeQL - not replace them.

Enables agents to perform a paid trust and liveness audit on any x402 resource URL, returning a verdict, trust score, deductions, terms, schema quality, catalog presence, and diff against the previous check.

Enables checking whether a crypto link is a phishing lookalike of a wallet, exchange or dapp by comparing it against official domains and flagging lookalike characters, typosquats, punycode and bait words, fully offline. An optional paid full check adds domain registration age, DNS, redirect tracing and a page scan for seed-phrase prompts and drainer code.

Enables local spend caps and Ed25519-signed provenance receipts for AI agent tool calls, allowing any MCP host to gate model usage and independently verify signed decisions without sending prompts or content.

Privacy-preserving AI gateway. Sanitises PII before prompts reach Anthropic / OpenAI / your LLM, then emits a signed cryptographic certificate per call (Ed25519 + RFC 3161 + Sigstore Rekor). EU GDPR + AI Act ready. Free tier 500/mo with BYOK.

Vet ClawHub skills before installing them; detects prompt-injection, exfiltration, and other security issues, outputting a risk score with per-finding evidence.

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

AI Bill of Materials compliance tracking and SBOM generation for AI/ML systems

Read selected local folders from ChatGPT on macOS, with per-folder read-only or read-write access and hash-checked, recoverable edits. Requires local installation and a private ChatGPT app. The Glama container is a synthetic evaluation demo; it does not connect to files on your Mac.

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.

Machine-readable detection lookups for SIEM enrichment and AI agents. Query 800+ LOLBAS and GTFOBins binaries plus process parent-child baselines — get risk levels, abuse categories, and MITRE ATT\&CK mappings without embedding data in prompts.

Provides security audit primitives for MCP servers, agent tool schemas, and system prompts, along with pentest utilities like JWT inspection and HTTP diffing.

A read-only MCP server that analyzes a supplied Terraform plan JSON file and returns resource identities, action/type/mode counts, and coverage warnings about proposed infrastructure changes. It never executes Terraform, applies changes, or connects to AWS, keeping analysis local and deterministic.

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

Zero-knowledge proof generation MCP server. AI agents can prove identity claims (Coinbase KYC, Country, Google OIDC, Google Workspace, Microsoft 365) without revealing personal data. Runs in AWS Nitro Enclave TEE with x402 USDC payments.

OS keychain secrets for AI coding agents, over MCP. Anchors credentials to the native vault (macOS Keychain, Linux Secret Service, Windows Credential Vault) and exposes them through 44 policy-governed tools: per-environment values, TTL, linked rotation, encrypted transfer bundles, redacted exec, and a tamper-evident audit log. Local-first, no cloud account.

Scans prompts for PII and masks or redacts sensitive data locally before sending to an LLM, supporting multiple anonymization modes.

MCP server that exposes OSSEC HIDS security monitoring capabilities as tools, resources, and prompts for AI assistants.

Enables MCP-capable assistants to run read-only AI governance inventory checks, assemble Decision Packs, and validate signed Agent Trust Passports against pinned upstream tooling, returning every result as non-authorizing with authority_effect NONE.

Enables Claude to answer business questions against a company's retail database — sales summaries, top customers, inventory alerts, customer profiles, and plain-English queries — through read-only SQL tools plus a schema resource and reporting prompt. Access is governed by OAuth 2.1 roles and scopes, column-level PII masking, a SQL guard, rate limits, and audit logging.

Provides real-time security risk assessment for AI coding prompts, analyzing potential dangers, blast radius, and complexity before code execution in Cursor.

Enables reviewing GitHub Actions workflows for outdated actions, deprecated Node runtimes, retired runners, deprecated commands, and security risks, with file, line, and fix for each finding.

EU AI Act Compliance - MCP server providing AI-powered tools and automation by MEOK AI Labs

Open-source AWS security scanner with Attack Chains, Breach Cost Estimation, and MCP Server. 47 checks across 15 AWS services. Every finding includes copy-paste remediation (CLI + Terraform) and a dollar-risk estimate with verified source. First free standalone AWS security MCP server - Prowler and Wiz require paid SaaS.

Protects AI agents from prompt injection and destructive actions while enabling self-improving prompts through a security pipeline.

Enables agents to send prompts to multiple hosted language models with prompts encrypted on the local machine to a verified GPU-TEE enclave key, returning answers with per-call costs and signed receipts. Also supports side-by-side model comparison, balance and spend checks, and on-demand enclave attestation verification.