Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| io.github.purinzan/gx3-cli-mcp agentthink/gx-trace Lets AI agents and users analyze Mitsubishi MELSEC .gx3 projects directly, tracing coil conditions, checking device references, comparing program changes, and inspecting ladder logic without opening GX Works3. | |
| skill2mcp agenttic-ai-dev/skill2mcp Converts SKILL.md documents into MCP-ready tool definitions and generates a deployable MCP server package. | |
| Agent-Town agenttown/agent-town A neutral verification court for AI tools that ranks MCP servers by executing them against ground truth and recording results. Enables agents to consult execution records, contribute verdicts, and challenge claims. | |
| AgentVeil Protocol agentveil-protocol/agentveil-sdk Trust, identity, and reputation infrastructure for AI agents. Register agents with W3C DID (Ed25519), check EigenTrust reputation scores, submit peer attestations, search agents by capability, and verify IPFS-anchored audit trails. 11 tools | |
| Weather MCP Server agentventure/mcp_server_python_getting_started An MCP server that provides weather information and alerts for US locations using the National Weather Service API, enabling retrieval of weather forecasts and active weather alerts. | |
| AgentVerus MCP Server agentverus/mcp-server Security scanning for AI agent skills exposed as MCP tools, enabling skill analysis from ClawHub, GitHub, skills.sh, or raw URLs. | |
| AgentWall agentwall/agentwall Policy-enforcing MCP proxy that blocks dangerous tool calls before they execute. Protects credentials, filesystem, shell, and databases across Claude Desktop, Cursor, Windsurf, and OpenClaw. | |
| agentguard agentwares/okgate Enforces policy controls for AI agents, including spend limits, action approvals, kill switch, scoped credentials, dry-run diffs, loop prevention, and auditable hash-chained logs. | |
| Agentware MCP agentwaresh/mcp Enables MCP clients to browse and purchase agent packages and pay per call for model inference on Robinhood Chain using USDG, with no account or API key required. | |
| AWP MCP Server agentwebprotocol/mcp-server Provides tools for AI assistants to access the Agent Web Protocol (AWP) specification, validate agent.json files, and generate protocol-compliant configurations. It enables developers to integrate the AWP standard into their websites throug | |
| Skillyard MCP Server agentwik-labs/skillyard Enables AI agents to search, retrieve, and read skill files from a registry, exposing each skill as an MCP prompt and resource over HTTP or through a stdio bridge. | |
| Exa MCP Server agentwings/exa-mcp-server Connects AI assistants to Exa AI's search capabilities, including specialized code search across GitHub repos, documentation, and Stack Overflow, plus web search, company research, and deep research tools for comprehensive information retri | |
| turbopuffer-mcp agentwings/turbopuffer-mcp Enables interaction with the Turbopuffer vector database, providing tools for managing namespaces, schema configuration, and performing advanced vector queries. It supports secure DAuth-style authentication and covers both v1 and v2 Turbopu | |
| IAC Memory MCP Server agentwong/iac-memory-mcp-server A custom Memory MCP Server that acts as a cache for Infrastructure-as-Code information, allowing users to store, summarize, and manage notes with a custom URI scheme and simple resource handling. | |
| IaC Memory MCP Server agentwong/iac-memory-mcp-server-project Enhances Claude AI with persistent memory storage for Infrastructure-as-Code components, supporting version tracking and relationship mapping for Terraform and Ansible resources. | |
| Knowledge Graph Memory Server agentwong/optimized-memory-mcp-server A persistent memory implementation using a local knowledge graph that lets Claude remember information about users across conversations. | |
| Optimized Memory MCP Server V2 agentwong/optimized-memory-mcp-serverv2 A Python-based server that implements the Model Context Protocol to interface with Claude Desktop as an MCP client, supporting interaction through efficient memory management. | |
| Multi-agent Communication Protocol Server agentworkshop/mcp A standardized interface for agent-to-agent communication that enables composability, supports streaming, and implements server-sent events (SSE) for real-time interaction. | |
| Mailchimp MCP Server agentx-ai/mailchimp-mcp A Model Context Protocol server that provides read-only access to Mailchimp's Marketing API for comprehensive email marketing data retrieval. | |
| Yahoo Finance MCP Server agentx-ai/yahoo-finance-server Enables AI assistants to access Yahoo Finance data including stock information, news, price history, options, and earnings via MCP tools. | |
| YouTube DLP MCP Server agentx-ai/youtube-dlp-server Enables AI assistants to extract YouTube video metadata, subtitles, and top comments without downloading videos. | |
| AgentScout MCP Server agentx402-ai/agentscout Enables web content extraction, reading, crawling, and pricing via MCP tools, with pay-per-fetch in USDC on Base using x402. | |
| AgentZone MCP agentzonemkp/agentzone-mcp Enables LLMs to search, discover, and interact with over 37,000 verified on-chain AI agents through the AgentZone platform. Users can filter agents by capability and trust score, access network analytics, and manage agent registrations or p | |
| bolt ageofaitech/bolt Enables AI agents to invoke 100+ pre-installed penetration testing tools (e.g., nmap, nuclei, sqlmap) inside a Dockerized Kali Linux environment via MCP, supporting single-turn execution for reconnaissance, scanning, exploitation, and secur | |
| MCP-demo ageorgiev-bg/mcp-demo MCP server that demonstrates PostgreSQL database interaction, providing a tool to retrieve user data from a users table. | |
| glpi-mcp-server ageugyn/glpi-mcp-server Connects AI assistants to GLPI IT Service Management, enabling ticket management, asset search, and ITIL processes via natural language. | |
| Telegram Bot MCP Server aggeentik/telegram-bot-mcp Enables AI assistants to publish, edit, search, and manage messages in Telegram channels via a set of MCP tools. | |
| Market Regime Oracle aggreyeric/bnb-ai-trading-agent Classifies BTC market into 5 regimes (Risk-On, Range-Bound, Risk-Off, Capitulation, Euphoria) with target exposure and posture, enabling risk management decisions. | |
| Market Regime Oracle aggreyeric/bnb-regime-oracle Fuses five market signals into a five-state regime classifier to determine market conditions and recommend trading postures for risk management. | |
| groundcheck-mcp aghasalim/groundcheck-mcp MCP server for grounding verification (exact quotes, citations, code output, repo patterns, arithmetic) using no LLM in the verification path. | |
| urssaf-vigilance-mcp aghulas/urssaf-vigilance-mcp Enables verifying French Urssaf vigilance certificates through the official "Attestations Vérification Code Sécurité" API, extracting data from received PDFs, cross-checking fields against expected contractors, computing validity end dates, | |
| kala aghyksa/kala Enables logging, listing, updating, deleting, and summarizing timesheet entries, starting and stopping timers, checking timer status, and exporting time data through natural language, backed by a local SQLite database. | |
| agi-bar agi-bar/agi-bar-skill Enables AI agents to browse activities, calendars, and drink menus; register or cancel; initiate paid signups and venue bookings with payment completed by the user in WeChat; and manage events they host or collaborate on using a personal ke | |
| PHP2Shell Scanner & WordPress-to-Next.js Converter MCP Server agi-ceo/php2shell-wordpress-to-nextjs-mcp Enables AI coding agents to audit websites for PHP runtime vulnerabilities, compile a live Zero-PHP Next.js App Router replacement preview from a WordPress/PHP site, and retrieve remediation guidance. | |
| a2a-board-engine agicoffe/a2a-board-engine An ultra-rational A2A protocol for zero-token edge pre-filtering and FEP-driven deadlock prevention. Uses Cloudflare Vectorize (384d cosine similarity) with a 24h deposit model, restricting bargaining to a 4-rally limit before forcing HTTP | |
| a2a-fep-consensus agicoffe/a2a-fep-consensus Short Description (概要):
An MCP server providing FEP (Free Energy Principle) matrix-pruning tools (resolve_fep_consensus) for multi-agent deadlock resolution and syntax-locked A2A consensus. | |
| break-attention-fixation agicoffe/break_attention_fixation Non-Transformer 3D bitspace phase-shift tool for breaking LLM attention loops, local minima, and contextual fixation using Beethoven Sonata dynamics. | |
| my-topology-engine agicoffe/my-topology-engine A deterministic MCP server that executes 10-step topology pipelines on Cloudflare Workers, providing structured progress snapshots and adaptive JSON templates for AI agents. | |
| quantum-jitter-labyrinth agicoffe/quantum-jitter-labyrinth Short Description (概要):
An MCP server providing quantum-inspired entropy injection and topological graph-search tools (explore_quantum_labyrinth) to help LLM agents escape decision-space local minima. | |
| solana-402-agent-wallet agicoffe/solana-402-agent-wallet An open-source, zero-dependency Model Context Protocol (MCP) server and HTTP 402 payment gateway built for Cloudflare Workers and Node.js.
This project enables AI agents (Claude Desktop, Cursor, etc.) to natively discover, negotiate, and a | |
| solana-402-merchant-template agicoffe/sorana-402-merchant-template An open-source, zero-dependency Model Context Protocol (MCP) server and HTTP 402 payment gateway template built for Cloudflare Workers and Node.js.
This repository provides an automated store API on Solana (USDC) alongside a native MCP Ser | |
| AI Code Toolkit agiflow/aicode-toolkit Enables AI coding agents to generate standardized code using scaffolding templates, enforce architectural patterns, and validate outputs programmatically. Supports creating projects from boilerplates and adding features to existing codebase | |
| OpenSkill agiflow/openskill An MCP server that makes Anthropic Skills universally accessible across coding agents, enabling sandboxed execution of skills in Docker containers with skill management and MCP tools. | |
| MCP Secure Local Server agileandy/mcp-secure-server A security-focused Model Context Protocol server that enables controlled local tool execution through strict network firewalls, filesystem protections, and rate-limiting policies. It features a plugin-based architecture for progressive tool | |
| tcgen-st-test-mcp agileautomationtechnologies/tcgen-st-test-mcp Provides offline semantic validation for TcGen Structured Text (ST) review bundles by normalizing ST code, generating STruC++ tests from JSON specs, and executing them via the strucpp CLI. | |
| mcp-fiscal-brasil agileconecta/rtc-mcp_fiscal Enables AI assistants and automation tools to query and analyze Brazilian fiscal data, including CNPJ, Simples Nacional, NF-e, NFS-e, SPED, eSocial, tax regime comparison, and supplier risk assessment without requiring API keys. | |
| Agile Luminary MCP Server agileluminary/mcp-agile-luminary A Model Context Protocol server that connects AI clients to the Agile Luminary project management system, allowing users to retrieve project details, work assignments, and product information within AI conversations. | |
| a6-crm-mcp-server agilesix/a6-crm-mcp-server A remote MCP server deployable to Cloudflare Workers with built-in Google OAuth authentication, providing tools like addition and serving as a reference for OAuth integration. | |
| CommonGrants Grant Seeker agilesix/cg-mcp-grant-seeker An MCP server that searches grant opportunities across multiple CommonGrants-compliant APIs from a single set of tools. | |
| USASpending MCP Server agilesix/usaspending-mcp-nextjs Enables research of federal contract awards and competitive landscape analysis using the USASpending.gov API. Supports searching for contracts, analyzing recipients, tracking spending trends, and identifying market opportunities in governme |
24,551–24,600 of 115,409
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.