awesome-repositories.com
Blog
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectDespreCum realizăm clasamentulPresăServer MCP
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

10 repository-uri

Awesome GitHub RepositoriesModel Context Protocol Security

Security controls for interactions between models and external tools.

Distinguishing note: Focuses on protocol-level security for context sharing.

Explore 10 awesome GitHub repositories matching security & cryptography · Model Context Protocol Security. Refine with filters or upvote what's useful.

Awesome Model Context Protocol Security GitHub Repositories

Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
  • owasp/cheatsheetseriesAvatar OWASP

    OWASP/CheatSheetSeries

    32,298Vezi pe GitHub↗

    The OWASP Cheat Sheet Series is a comprehensive, community-driven repository of concise security best practices and defensive coding patterns. It serves as a centralized knowledge base for developers and security professionals, providing actionable guidance to secure applications across the entire software development lifecycle. The project covers a vast array of security domains, ranging from fundamental web application hardening and authentication protocols to specialized controls for modern infrastructure and artificial intelligence systems. What distinguishes this project is its decentral

    Ensures safe and authorized interaction between artificial intelligence models and external tools via context protocols.

    Pythonapplication-securityappsecbest-practices
    Vezi pe GitHub↗32,298
  • modelcontextprotocol/modelcontextprotocolAvatar modelcontextprotocol

    modelcontextprotocol/modelcontextprotocol

    8,458Vezi pe GitHub↗

    Model Context Protocol is a standardized framework for connecting large language models to external data sources and executable tools. It enables the creation of a universal interface where servers expose tools, resources, and prompts that can be discovered and utilized by various AI clients. The protocol utilizes a JSON-RPC message system that is transport-agnostic, supporting both standard input/output for local processes and HTTP with server-sent events for remote connections. It emphasizes security and control by delegating model sampling to the client to keep API keys secure from servers

    Generates content via a client to ensure API keys remain secure and are not exposed to servers.

    TypeScript
    Vezi pe GitHub↗8,458
  • superagent-ai/superagentAvatar superagent-ai

    superagent-ai/superagent

    6,631Vezi pe GitHub↗

    Superagent is an AI safety platform that protects applications from prompt injections, data leaks, and harmful outputs through built-in guardrails. It functions as a prompt injection detection system, data redaction tool, and red team testing tool, automatically removing personally identifiable information and protected health data from AI inputs and outputs while scanning image uploads with vision AI to detect visual prompt injection attacks before processing. The platform routes every prompt through a sequential pipeline of safety checks including injection detection, data redaction, and co

    Scans image uploads with vision AI to detect and block visual prompt injection attacks before processing.

    TypeScriptaianthropicguardrails
    Vezi pe GitHub↗6,631
  • crytic/slitherAvatar crytic

    crytic/slither

    6,141Vezi pe GitHub↗

    Trail of Bits wraps Model Context Protocol apps to defend against prompt injection via tool descriptions and ANSI terminal escape codes.

    Pythonethereumsoliditystatic-analysis
    Vezi pe GitHub↗6,141
  • microsoft/agent-governance-toolkitAvatar microsoft

    microsoft/agent-governance-toolkit

    4,522Vezi pe GitHub↗

    agent-governance-toolkit este un framework pentru aplicarea politicilor de securitate, gestionarea identităților zero-trust și sandboxing-ul execuției agenților AI autonomi. Acesta oferă un strat de guvernanță conceput pentru a controla comportamentul agenților prin utilizarea unui motor de politici de securitate, gestionarea identității criptografice și un sandbox de execuție la runtime. Proiectul se distinge printr-un sistem de inele de privilegii pe mai multe niveluri și o rețea de identitate criptografică care securizează comunicarea între entitățile autonome. Implementează un mecanism de scor de încredere bazat pe degradare pentru a urmări fiabilitatea entității și utilizează jurnale de audit hash-chained, rezistente la manipulare, pentru a menține un istoric verificabil al execuției. Toolkit-ul acoperă o gamă largă de arii de capabilități, inclusiv securitatea prompt-urilor pentru a apăra împotriva atacurilor de injecție, maparea automată a conformității cu standardele de reglementare și orchestrarea fluxului de lucru autonom folosind tipare de tip saga. De asemenea, dispune de monitorizarea flotei pentru urmărirea sănătății și a limitelor de cheltuieli, precum și sandboxing-ul execuției instrumentelor pentru a restricționa accesul neautorizat la resurse. O interfață de linie de comandă este furnizată pentru executarea semnalelor de control, validarea politicilor de guvernanță și gestionarea instalării extensiilor.

    Provides a deterministic pattern scanner to verify that defensive language is present in system prompts before deployment.

    Python
    Vezi pe GitHub↗4,522
  • opensquilla/opensquillaAvatar opensquilla

    opensquilla/opensquilla

    4,211Vezi pe GitHub↗

    OpenSquilla este un framework de orchestrare pentru agenți LLM, conceput pentru a coordona fluxuri de lucru AI în mai mulți pași și execuția de instrumente folosind grafuri aciclice direcționate. Acesta funcționează ca un sistem centralizat pentru gestionarea pachetelor de competențe specializate și executarea secvențelor complexe de raționament. Proiectul se distinge printr-un gateway de rutare care direcționează sarcinile către diferiți furnizori AI în funcție de complexitate, cost și performanță. Utilizează un sistem de memorie AI pe mai multe niveluri care organizează cunoștințele de lucru, episodice și semantice folosind embedding-uri locale și SQLite, alături de un sandbox de execuție securizat care izolează codul generat de agenți prin profiluri de permisiuni bazate pe risc. Platforma acoperă o gamă largă de capabilități, inclusiv implementarea pe mai multe canale către platforme web și de mesagerie, programarea automată a sarcinilor prin cron și un bridge Model Context Protocol pentru conectarea la instrumente externe. De asemenea, oferă instrumente cuprinzătoare de monitorizare și observabilitate pentru urmărirea costurilor per token, auditarea deciziilor runtime și gestionarea unui catalog de competențe reutilizabile. Sistemul include utilitare CLI pentru inițializarea spațiului de lucru și gestionarea ciclului de viață al competențelor.

    Deno AI Agent escapes metadata and tool results using XML to close common prompt injection attack vectors.

    Pythonagentaiai-agents
    Vezi pe GitHub↗4,211
  • atmosphere/atmosphereAvatar Atmosphere

    Atmosphere/atmosphere

    3,780Vezi pe GitHub↗

    Atmosphere is a Java-based framework for building and coordinating AI agents. It provides a real-time transport layer for streaming data via WebSockets, SSE, gRPC, and WebTransport, alongside a multi-agent orchestration framework for managing agent fleets through sequential, parallel, and graph-based execution workflows. The project features a durable workflow engine that persists agent state as snapshots, allowing long-running tasks to survive system restarts and incorporate human-in-the-loop approvals. It also implements Model Context Protocol servers to expose tools, resources, and prompt

    Uses confinement blocks prepended to system prompts to ensure agents adhere to defined security boundaries.

    Javaacpagentic-aiembabel
    Vezi pe GitHub↗3,780
  • cyberalbsecop/awesome_gpt_super_promptingAvatar CyberAlbSecOP

    CyberAlbSecOP/Awesome_GPT_Super_Prompting

    3,654Vezi pe GitHub↗

    This repository is a collection of specialized toolsets and libraries for large language model prompt engineering and security testing. It provides a library of advanced templates and frameworks designed to optimize the quality and specificity of model responses. The project includes resources for red teaming and security research, featuring a repository of prompts designed to bypass safety filters and operational constraints. It also provides techniques for system prompt extraction to reveal the internal instructions and configurations of AI personas. The collection covers a broader surface

    Provides security controls and prompt-based rules to defend against malicious prompt injection attacks.

    HTMLadversarial-machine-learningagentai
    Vezi pe GitHub↗3,654
  • verazuo/jailbreak_llmsAvatar verazuo

    verazuo/jailbreak_llms

    3,563Vezi pe GitHub↗

    This project is a comprehensive ecosystem of frameworks, toolkits, and datasets designed to evaluate model vulnerabilities and analyze jailbreak patterns. It serves as an adversarial testing framework and research toolkit for measuring the effectiveness of safety guardrails in large language models. The system includes a library of real-world prompt injection datasets harvested from social media to study bypass strategies. It provides specialized tools for semantic attack analysis and prompt visualization, allowing for the mapping of relationships between adversarial prompts to discover commo

    Ships a library of real-world prompt injection datasets harvested from social media to study bypass strategies.

    Jupyter Notebookchatgptjailbreakjailbreaking
    Vezi pe GitHub↗3,563
  • harishsg993010/damn-vulnerable-mcp-serverAvatar harishsg993010

    harishsg993010/damn-vulnerable-MCP-server

    1,306Vezi pe GitHub↗

    This project is an educational and research platform designed to simulate security vulnerabilities within AI-integrated systems and Model Context Protocol implementations. It provides a controlled environment where users can practice identifying and mitigating common attack vectors, such as prompt injection and unauthorized code execution, by interacting with intentionally insecure tools and protocol configurations. The platform distinguishes itself by offering a dedicated laboratory for auditing Model Context Protocol integrations. It exposes server-side functions as discoverable tools and p

    Provides a dedicated laboratory for auditing the security posture of Model Context Protocol implementations and tool interactions.

    Python
    Vezi pe GitHub↗1,306
  1. Home
  2. Security & Cryptography
  3. Model Context Protocol Security

Explorează sub-etichetele

  • Prompt Injection Defenses3 sub-tag-uriSecurity controls that protect LLM applications from prompt injection via tool descriptions and terminal escape codes. **Distinct from Model Context Protocol Security:** Distinct from Model Context Protocol Security: focuses on defending against prompt injection attacks specifically, not general protocol-level security.
  • Resource Access RestrictionsControls that limit interaction with sensitive endpoints or resources using specific authorization flows. **Distinct from Model Context Protocol Security:** Focuses on the granular restriction of specific endpoints within the protocol rather than general protocol security
  • Secure Generation FlowsGeneration of model content through a client to isolate API keys from the server. **Distinct from Model Context Protocol Security:** Focuses on the architectural flow of routing generation through a client for key security, not just protocol security.