安全 MCP 服务器

Signed, independently-recomputable safety scores for the MCP servers, packages, and tools an agent connects to: a 0–100 score plus an…

Offline MCP server: explains shell commands token-by-token and flags destructive ones for AI agents.

iptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.

Anonymize PII & redact text (GDPR): Czech + 35-lang NER, morphology, translation, spellcheck

Historical AWS analysis CLI; not a current Cyntrisec product.

Query Microsoft Patch Tuesday security updates (MSRC) with EPSS and CISA KEV enrichment

Mint, resolve, audit, and rotate scope-limited expiring access links (qURLs) for AI agents.

Give an agent a verifiable identity, and check another agent's before dealing with it.

Passport, mandate, fail-closed action gate and tamper-evident journal for AI agents.

Visual CVE audit dashboard for npm, Python, Go, and Rust. Scan from Claude/Cursor, opens a browser UI for human review…

Solvitor MCP server provides tools to access reverse engineering tools that help developers extract IDL files from closed-source Solana…

55 tools for verified public data lookups — CVE/SBOM security audits, licence compliance, patents, federal contracts, NPI provider…

Security co-pilot for AI agents. Scan for vulnerabilities, audit MCP servers, verify governance.

Rust infrastructure diagnostics MCP server for AI agents: DNS checks, TLS certificate chain inspection, email security, global DNS…

MCP server for Malcolm (Zeek/Suricata/Arkime/OpenSearch): threat-hunting access for AI agents

Security, cost, and health governance proxy for MCP infrastructure

MCP server for Thales CDSP CAKM integration, enabling secure key management, cryptographic operations, and compliance monitoring through…

MCP server for Thales CipherTrust Manager RestFul Data Protection service.

PCI DSS v4.0.1 compliance scanner for Go payment services, delivered as an MCP server

11-scanner SAST/DAST MCP server with closed-loop remediation, SBOM/SARIF, and CI integrations

Compiler-precise code property graph for C, Python, and TypeScript, navigable over MCP.

VMware compliance scanning (CIS, vSphere SCG, GB/T 22239, PCI-DSS) with drift detection.

Runtime governance for MCP tool calls. Blocks prompt injection and capability abuse before tool results reach your agent.

Identity and credential governance broker for MCP servers. Issues scoped, short-lived credentials per agent to stop credential…

EU AI Act compliance scanner for Python AI agents. 14 tools across 6 articles.

Third-party certifying proxy — sign any HTTP call (AI agents, webhooks, microservices) with an independent Ed25519 signature, RFC 3161…

Verify a photo's capture time and provenance: C2PA validation, EXIF/XMP, and pixel forensics.

Static preflight safety gate for MCP servers — scan configs before you run them. Never executes.

Solana token safety oracle for AI agents and trading bots. Byte-level SPL mint analysis, honeypot detection, freeze/mint authority checks,…

Pseudonymizes PII before your LLM and returns a cryptographically signed receipt per response.

Ed25519 identity for AI agents. Verify seals, sign documents, gate actions with approvals.

Scan, fix, verify and monitor DNS: SPF, DMARC, DKIM, propagation, health, expiry. Validated fixes.

Local GitHub Actions/CI maintenance check (action pinning, token perms). Not a full security audit.

Authorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.

Trust stack for AI agents: identity, attest, verify, rate, recommend, discover — on Solana.

Honeypot probe data: IP reputation, scanners, CVE probing, TLS and SSH fingerprints.

MCP stdio interceptor (`@jamjet/mcp-shim`) that applies one YAML policy file (block / require_approval / audit / budget cap) to…

Ed25519-signed consent receipts and programmable policy engine for AI agents. Spending caps, action whitelists, escalation thresholds, and…

Local byte-wrangling toolbox: encoding (hex/Base64/Base32/Base58/Base45…), cryptographic + CRC hashing, base conversion, and CSPRNG…

Base bytecode capability observations, proxy resolution, gas, DEX, and transfer telemetry.

Give your AI hands. Identity and credential vault gateway for autonomous agents. Ed25519 cryptographic identity (not OAuth), AES-256-GCM…

Zero-Trust PII & secrets sanitizer. Locally scrubs data in-memory before sending context to LLMs.

Administer Keycloak via its Admin REST API: users, roles, clients, groups, IdP, events.

Security scanner for MCP servers. Detects backdoors, exfiltration code, obfuscation, dangerous code execution, prompt injection, and…

MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via…

DNS and email security: check SPF, DKIM, DMARC, DNSSEC, DANE and build the records. 45 tools.

PII sanitization layer for autonomous AI agent pipelines. Detects and redacts emails, phone numbers, national IDs, private keys, and…

Sigma detection rule writing, validation, and conversion (Splunk/Elastic/Kibana/Wazuh) via 3 MCP tools (`draft_rule`, `validate_rule`,…

Headless IDA Pro binary analysis via MCP. Multi-session concurrency with Go orchestration and Python workers. Supports Il2CppDumper and…

URL intelligence for AI agents and developers. 16 tools, 25 signal weights, 20 free checks.

MCP policy proxy: enforces a code of conduct across connectors before the upstream is called.

Trust layer for AI agents: identity, guard, redact, escrow, and x402 payments.

Security intelligence for AI agents: password breach checks (900M+ HIBP hashes), email/domain/IP/URL reputation, prompt injection…

Stdio + HTTP MCP gateway: SSRF-hardened web_fetch, web_search, metis_verify, market_search.

ARGUS-3 stdio MCP with WARDEN firewall: argus_ask, argus_status, argus_capabilities.

Cryptographic provenance, bilateral blind reputation scoring, and tamper-evident logging for AI agent interactions. 7 interlocking trust…

Runtime policy enforcement for AI agents. Evaluate actions against organization policies before execution, with observe and enforce modes.

Supply-chain gate for agent skills and MCP servers — scans tool definitions for poisoned instructions, pins vetted servers by content hash…

Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.

Trust scoring for MCP servers, AI skills & npm packages — 15 signals + safety scanning.