MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Rust 代码安全审计引擎:跨文件污点追踪 + CPG 数据流分析产出可验证证据链,通过 MCP 让 LLM 基于证据完成漏洞判定。Rust code security audit engine: cross-file taint tracking and CPG data-flow analysis produce verifiable evidence chains; MCP lets LLMs make evidence-based vulnerability verdicts.
Apache-2.0 ★ 10 -
Security-first local LLM swarm over MCP with signed peer discovery, fail-closed validation, audit trails, and Docker-based PoC nodes.
pypi Apache-2.0 -
mcp-security-toolkitgithub.com/x0base/mcp-security-toolkitupdated this year
13 atomic MCP tools for AppSec and AI Security: recon, MCP audit, prompt-injection audit, OWASP LLM Top 10
go MIT -
LLM Security Gateway — AI application firewall, prompt injection risk analysis & sovereign audit runtime.
Apache-2.0 -
MCP server for SiteLint Auditor - WCAG and SiteLint accessibility, SEO, performance, and security audits via LLM
npm MPL-2.0 -
High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules across 20 programming languages, plus AI agent skill, MCP server config, prompt template, and LLM model security auditing.
npm MIT -
Security-focused MCP server mediating LLM access to IMAP mailboxes under strict, auditable policy.
GPL-3.0 ★ 3 -
Kubernetes security audit agent - declarative kagent agent with MCP tools and privacy-preserving pseudonymization via LLM proxy
Apache-2.0 ★ 1 -
httptoolkit-mcpgithub.com/NinjaScout77/httptoolkit-mcpupdated this year
MCP server that lets LLMs drive HTTPToolkit for automated API security testing — replay, mutation, and audit on captured mobile, desktop, and CLI traffic
MIT ★ 2 -
Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.
npm NOASSERTION ★ 15 -
Claude Code security plugin and agentskills.io skill pack for securing LLM agents: threat modelling, config audits, prompt injection review, MCP server review, incident lookup, security evals, Semgrep rules, guard hooks and an incident-database MCP server.
MIT -
qualys-cli-mcpactive
Model Context Protocol (MCP) server giving any LLM secure, audited access to the Qualys Cloud Platform (VM, PM, WAS, TotalCloud, Container Security, CSAM, and more).
pypi MIT -
agent-sec-scannersgithub.com/AUAggy/agent-sec-scannersupdated this year
Security scanners for AI workloads on one shared audit engine. Home of bedrock-security-mcp (AWS Bedrock auditor, MCP + CLI) and @miaggy/core. Findings map to OWASP LLM Top 10, OWASP Agentic Top 10, NIST AI RMF, MITRE ATLAS.
npm -
@ninjascout77/httptoolkit-mcpupdated this year
MCP server for LLM-driven security testing via HTTPToolkit — capture analysis, mutation-based replay, audit trails for mobile and electron app pentesting
npm MIT -
mcp-noctuagithub.com/NeveuGregor/mcp-noctuaupdated this year
MCP server exposing a sandboxed pentest toolbox (sqlmap, nuclei, ffuf, httpx, naabu, katana…) to an LLM orchestrator, for authorized security audits
NOASSERTION -
Local-first AI security auditor for your own apps: SAST scanners + LLM roles find vulnerabilities with evidence, keep an append-only audit history, and hand verified fix tasks to AI coding agents via MCP. Rust + SQLite, single binary.
MIT -
zero-ai-gatewaygithub.com/vishtechie07/zero-ai-gatewayupdated this year
Zero-Trust AI Gateway: Dual-pass PII redaction (Regex + LLM), real-time security monitoring with Kafka/WebSockets, and MCP-powered compliance auditing for enterprise AI safety.
MIT -
FHIR-MCP is an open-source MCP (Model Context Protocol) server that enables LLMs to securely interact with FHIR servers and HL7 terminology services. It provides a comprehensive toolset for healthcare interoperability with built-in PHI protection, audit logging, and token-efficient operations.
MIT -
Blob-Beadsgithub.com/sdheer/Blob-Beadsupdated this year
Temporal Vault MCP: A local-first, security-hardened state management server for agentic workflows. Implements Content-Addressable Storage (CAS), Zstandard compression, and AES-256-GCM encryption to provide an auditable, "time-traveling" memory layer for LLM agents.
MIT -
firesharkgithub.com/HendrikReh/firesharkupdated this year
Rust packet analyzer for LLMs and humans — 11-protocol dissection, 9-command CLI, 21-tool MCP server for AI-driven security audits, Wireshark-style display filters, stream tracking, and optional tshark backend
Apache-2.0 ★ 1 -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
mcp-siber-security-auditstale
MCP server for security code audit with auto-fix capabilities
npm MIT -
cloud-audit-mcpgithub.com/badchars/cloud-audit-mcpupdated this year
Cloud security audit tools for AI agents — AWS, Azure, GCP misconfiguration detection via MCP. 38 tools, 60+ checks. The agent finds vulns, not you.
MIT ★ 23 -
mceptiongithub.com/mception/mceptionupdated this year
MCP server that audits other MCP servers for security risks
pypi MIT -
MCP server that exposes security tools to agents behind policy gates, sandboxing and an audit trail.
MIT -
MCP server security auditor — tool poisoning, ASCII smuggling detection, prompt injection, OWASP Agentic Top 10. First OSS tool for MCP security.
AGPL-3.0 ★ 2 -
agent-security-mcpgithub.com/mdfifty50-boop/agent-security-mcpupdated this year
MCP server providing security scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows
npm -
LLM distillation detection & model fingerprinting via statistical forensics — behavioral probing, stylistic signatures & representation similarity. CLI + MCP ready.
MIT ★ 2 -
Minimal, auditable Model Context Protocol server for safe LLM-to-system interaction
cargo MIT -
Security auditor for AI agents and MCP servers — config analysis, prompt injection testing, tool probing, data flow tracing
npm MIT -
MCP-Security-with-Permissions-and-Elicitationgithub.com/LeelaissakAttota/MCP-Security-with-Permissions-and-Elicitationupdated this year
Secure MCP (Model Context Protocol) server with role-based permission management, elicitation-based user approval workflows, and full audit logging — built with FastMCP, Python & Gradio
★ 1 -
Authorization, delegation and audit for AI agent actions over MCP: a policy on every tool call, short-lived agent tokens, human approvals and a tamper-evident audit log.
npm Apache-2.0 ★ 2 -
Open-source firewall for AI agents: centrally managed egress control, full traffic visibility (TLS inspection) and audit for fleets of LLM agents. Rust gateway, Nuxt console, CLI & MCP.
Apache-2.0 -
governedmemorygithub.com/Metaworkers-ai/governedmemoryupdated this year
Open-source governed memory for AI agents: prompt-injection-resistant writes, purpose-bound retrieval, provenance, and tamper-evident audit.
pypi MIT ★ 10 -
guardianshieldgithub.com/sparkvibe-io/guardianshieldupdated this year
Universal AI security layer - MCP server for code scanning, PII detection, prompt injection defense, secret detection, and audit logging
pypi Apache-2.0 -
One scored audit of everything you ship: code, sites, apps, APIs, containers, IaC, cloud and mobile. CLI, CI and MCP for AI agents.
npm MIT ★ 1 -
Governance layer for AI coding agents — model routing, security scanning, tamper-evident audit trail, JIT permissions. MCP server, 142 tools, 83 skill packs, 14 agent hosts, MIT licensed.
MIT -
See what your AI agents actually did, then scan what they could do. MCP security from logs, no proxy. Offline, one binary.
npm Apache-2.0 -
Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.
npm MIT -
The trust and intelligence layer between AI agents and your database. Read-only by architecture, semantic knowledge graph + audit log, MCP-native.
pypi Apache-2.0 ★ 12 -
gax-cligithub.com/0sparsh2/gaxupdated this year
Governed execution layer for agent shell commands — capability-gated, audited, MCP-compatible
pypi MIT -
Audit-grade flight recorder for AI agents: policy on every MCP tool call, a signed hash-chained log, and OSCAL evidence
pypi MIT -
Secure MCP server for PostgreSQL & Oracle: AST-based SQL guard, row-level policy, PII masking (Turkish recognisers + Presidio), hash-chained audit
MIT -
Security-first MCP server for SendGrid — recipient allowlists, send caps, review-mode, audit log, no silent BCC. Hardened against the postmark-mcp incident class.
pypi MIT -
mcp-openclawgithub.com/romainsantoli-web/mcp-openclawupdated this year
—
pypi -
Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.
npm Apache-2.0 ★ 31 -
drheaderplus-mcpupdated this year
MCP server for DrHeaderPlus security header auditing
pypi MIT -
@seekingdata/mcpactive
MCP server for the seekingdata API: typed tools for live, fully sourced market data (crypto, FX, equities, commodities, macro, and more) plus Sightline security assessments - consult audit findings, re-audit diffs, and request scoped re-audits of a verifi
npm UNLICENSED -
Deterministic AST + neuro-symbolic verifier for AI-generated Rust, Python, TS, JS & Solidity. Catches slopsquatted imports, cutoff-drift APIs & async traps in <15ms. Ships with the Top-100 Evil AI Benchmark & stdio MCP server.
MIT -
scrypto-audit-kitgithub.com/bigdevxrd/scrypto-audit-kitupdated this year
Pre-audit toolkit for Scrypto blueprints on Radix: deterministic static analysis, an LLM checklist pass, machine-readable reports, an MCP server, and on-chain attestation.
pypi Apache-2.0 -
Security-hardened MCP server for terminal access: deny-by-default policy engine, shell=False sandboxed execution, cwd jail, secret redaction, fail-closed audit log.
MIT -
MCP server — CloakLLM tools for Claude Desktop and MCP clients
pypi MIT -
midasgithub.com/omarkhandji-commits/midasupdated this year
Self-hosted AI agent for safe LLM workflows: approvals, receipts, budget controls, local dashboard, CLI, Ollama, and MCP.
MIT ★ 1 -
agentsgategithub.com/agentsgate/agentsgateupdated this year
Undo for AI agents: an MCP proxy that checkpoints every tool call before it runs, so a bad `DROP TABLE` or `rm -rf` rolls back in seconds. Risk scoring, human-in-the-loop approval, tamper-evident audit log, dashboard, and MCP servers for PostgreSQL/MySQL/SQLite. Local-first, MIT, TypeScript, Node 20+.
npm MIT -
sentricore-agent-securitygithub.com/Pothan0/sentricore-agent-securityupdated this year
Security gateway for AI agents on REST and MCP: prompt-injection defense, tool governance, human-in-the-loop escalation, tamper-evident audit logs.
-
An MCP server, a policy-gated client, and the security layer between them — two processes, two mcp majors, 222 tests
MIT -
Self-hosted governance layer between AI assistants and your real data. Deterministic PII masking, allow/deny policy, hash-chained audit, offline-verifiable Ed25519 receipts per access when a receipt sink is configured, coverage reconciliation against the DB's own query counters to surface gateway bypasses, and conformance vectors. MCP-native. MIT.
npm MIT ★ 3 -
Local IntentLedger + MCP stdio proxy: propose, approve/deny, hash-chained ledger. Optional HMAC seals.
pypi MIT -
mcp-anvilgithub.com/aiinfradecoded/mcp-anvilupdated this year
Local MCP daemon with a dashboard, REST/WebSocket API, and 64 built-in tools — plus scaffold, audit, and inspect for your own Model Context Protocol servers.
pypi Commercial — see LICENSE.md -
@ormai/mcpgithub.com/neul-labs/ormaiupdated this year
Model Context Protocol server for OrmAI — expose database tools to AI agents via MCP
npm MIT