Mcp Security Python Packages

hol-guard

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

plugin-scanner

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

agent-audit-kit

Static scanner for MCP-connected AI agent pipelines. 388 rules across 14 categories, 14 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, public CVE-to-rule ledger.

soma-governance

Deterministic governance and guardrails for autonomous AI coding agents. Features AST verification, evidence-based rule execution, and native MCP support for Antigravity and Claude Code.

skilltotal

Claude Code plugin that scans a package before the agent runs npx, npm install, pip install, uvx or claude mcp add. Malicious indicators block the install. High-risk packages need your approval. The scan runs on your machine and never executes the code or calls an LLM. Every finding cites a file and line. Also a CLI, GitHub Action and MCP server.

assay-it

Open evidence profile for MCP tool actions. Enforce configured tool-call policies and record decisions and observations in offline-verifiable bundles. Optional Linux kernel controls. No hosted backend required.

mcp-testing

Comprehensive MCP testing framework - test performance, security and compliance in one CLI

mcp-hangar

MCP policy enforcement plane — deterministic policy on every Model Context Protocol call: identity, RFC 8707 audience binding, tool schema digest pinning, full audit trail. Python, self-hosted, MIT.

chock

Governance-as-code for AI coding agents: author a policy once, enforce it on every agent (Claude, Copilot, Cursor, Codex) via git hooks, CI, and native controls.

sunglasses

Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,569 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.

agent-security-harness

AI agent security harness, adversarial testing: 640 executable tests in the v4.26.1 release, across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loop, skill supply chain. Four target shapes: a verdict must be able to be wrong AND to be right. OWASP Agentic v1.1 T1-T17, AIUC-1 19/20 (2026-Q1/Q2 set), NIST AI 800-2.

pyatr

Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.

authmcp-gateway

🔐 Secure authentication proxy for MCP servers with JWT auth, real-time monitoring, and admin dashboard. Production-ready Docker deployment.

emilia-verify

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.

armorer-guard

Public SDKs and integration contracts for Armorer Guard.

sourcerykit

Python SDK for accurate and verifiable agent tool use. Agents verify that answers came from the right source and were not changed. Downstream agents detect 100% of errors and retry to achieve a 50% jump in answer accuracy.

agentlock

An adversarially benchmarked reference implementation for pre-action AI agent authorization. Provenance-based gating for LLM agent tool calls: deny-by-default permissions, parameter lineage, signed receipts, audit logging.

integration-automation-patterns

Enterprise integration patterns: idempotent event processing, saga orchestration, transactional outbox, and webhook validation for reliable system-of-record sync

x190

Fail your CI when an MCP endpoint serves its tool list without a token. Runtime probe and GitHub Action that also checks RFC 9728 OAuth posture and emits an HMAC-signed receipt of what was observed. Single file, stdlib only.

agent-discover-scanner

The industry-standard Agentic Identity & Inventory Scanner. Automatically inventory autonomous agents (LangChain, AutoGen, CrewAI, PydanticAI) using static analysis, network heuristics, and eBPF. Foundational tool for AIBOM compliance and AgentOps governance.

varden

Runtime security, governance and policy enforcement for AI agents

mcp-airlock

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

agentseal

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

agentconfigguard

Preflight security scanner for AI agents and MCP — detect risky permissions, secrets, prompt injection, and unsafe tool configurations before runtime.