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 |
|---|---|
| postgres-mcp-server anilsrml/postgres-mcp-server Acts as a secure bridge connecting PostgreSQL databases to AI models, enabling natural language querying, schema analysis, and controlled write operations with multi-layer security. | |
| roborock-mcp anilsrml/roborock-mcp Control Roborock robot vacuums: live status, the home map as an image with room names on it, clean only the rooms you name, pause and return to the dock. | |
| MCP Basic Create Tool anilvermaspeaks/mcp-bacis-create-tool A minimal MCP server using FastMCP to demonstrate tool creation, including a get_weather example. | |
| Anima MCP Server anima-labs-ai/mcp Provides 77 tools for AI agent communication, enabling agents to manage emails, phone messaging, domains, and webhooks. It allows AI models to interact with the Anima platform to automate workflows and administrative tasks across various co | |
| Archipelago Games anima-research/games-mcpl Lets agents play Doom-engine games (Freedoom, Doom, Doom II, Heretic) one turn at a time over network MCPL, taking actions like move, turn, goto, attack and use while receiving frames, events, bearings and map clearance. Enables people to w | |
| heartbeat-mcpl anima-research/heartbeat-mcpl Periodically sends heartbeat events to wake Connectome agents for self-check-in, with configurable interval and management tools. | |
| agileconfig-mcp-server animacaeli/agile-confg-mcp MCP server that exposes all AgileConfig RESTful APIs as tools, enabling AI assistants to manage configuration, applications, users, nodes, and more via natural language. | |
| Human-In-the-Loop MCP Server animalnots/human-in-the-loop-mcp-server Enables AI assistants to interact with humans through GUI dialogs for text input, choices, confirmations, and information display. | |
| anima-use-google animamesh/anima-use-google MCP server that lets AI agents perform Google AI Mode searches using the user's own browser session, returning synthesized answers with citations. | |
| MCP-Atlas animesh-eth/mcp-atlas-rl A large-scale benchmark that evaluates AI agents' tool-use competency across 36 real MCP servers using a reproducible Docker sandbox and LLM-as-judge scoring. | |
| animotion-mcp animotion-mcp/animotion-mcp.github.io 745+ CSS3 animations and 9,000+ real SVG icons (Lucide, Heroicons, Tabler, Bootstrap) for AI coding agents. Zero-clone setup via npx animotion-mcp. 10 MCP tools including search_animations, get_icon, suggest_animation, compose_animation, an | |
| SubMCP animuni-express/submcp MCP server that delegates bounded subtasks to NVIDIA NIM sub-agents, enabling context offload and parallel fan-out for coding assistants like Claude Code and Cursor. | |
| Multi-Agent Research Assistant MCP Server anindasau/llmengg_8-multi-agent-research-assistant-mcp-server FastMCP server offering weather and news lookup tools, demonstrating MCP integration with a LangGraph multi-agent research workflow. | |
| mcp-abap-adt anindyadr-sap/mcp-abap-adt--cds Enables MCP clients to connect to SAP ABAP systems and retrieve development information such as source code and table structures. | |
| Remote MCP Server on Cloudflare (Authless) aninibread/remote-mcp-server-authless A template for deploying remote Model Context Protocol servers on Cloudflare Workers without authentication. It enables users to define custom tools and access them through an SSE endpoint from clients like Cloudflare AI Playground or Claud | |
| datahub-okf-governed-query anionix/datahub-okf-governed-query Security-focused MCP adapter that combines read-only DataHub metadata with a reviewed OKF-derived policy IR to execute closed, typed SQL queries against synthetic PostgreSQL data. | |
| AI Development Guidelines MCP Server anip1805-dotcom/mcpcodeai Provides AI agents with professional coding standards, development best practices, and context-aware guidance through static documentation and AI-powered custom recommendations. Enables agents to access comprehensive development guidelines | |
| MCP-AWS anirban1592/google_openai_mcp A custom server with tools that enable AI agents to provision and terminate AWS EC2 instances through natural language commands. | |
| MCP-AWS anirban1592/mcp-server-aws Enables AI agents to provision and terminate AWS EC2 instances using natural language commands. | |
| smt-sudoku-mcp anirbanbasu/smt-sudoku-mcp Enables agents to generate uniquely-solvable Sudoku puzzles, validate partial or complete grids, and solve puzzles using SMT solving with Z3, all through stateless MCP tools. | |
| Chrome DevTools MCP anirbandz/chrome_mcp_devtool Enables AI coding assistants to control and inspect a live Chrome browser for automation, debugging, performance analysis, network monitoring, and DOM interaction through Chrome DevTools Protocol. | |
| Oumi MCP Server aniruddh-alt/oumi-mcp Provides access to over 500 pre-configured YAML templates and guided workflows for fine-tuning, training, and evaluating LLMs like Llama and DeepSeek. It enables AI assistants to search for recipes, retrieve configurations, and validate par | |
| Renpho Health MCP aniruddh-jammoria/renpho-health-mcp Enables AI agents to query and analyze Renpho smart scale data (weight, body fat, etc.) by syncing it from the Renpho app and exposing it through MCP tools for conversational exploration. | |
| Gahmen MCP Server aniruddha-adhikary/gahmen-mcp Provides access to Singapore's data.gov.sg government datasets and collections, enabling search, metadata retrieval, and dataset downloads through the CKAN datastore API. | |
| Career Copilot MCP aniruddha-shukla/week-5-mcp Enables exploring and analyzing US Data Analyst job postings, offering job search, salary benchmarking, and skill-demand insights through MCP tools, resources, and a career gap review prompt. | |
| MCP Web Scraper Server aniruddha1202/mcp-web-scraper An advanced web search and scraping server that enables AI models to perform targeted DuckDuckGo searches and extract clean content, tables, and metadata from webpages. It provides specialized tools for news discovery, link extraction, and | |
| Remote MCP Server (Authless) aniruddha1202/remote-mcp-server-authless-1 Deployable MCP server on Cloudflare Workers without authentication, enabling AI agents to use custom tools via SSE endpoint. Supports connection to Cloudflare AI Playground and local clients like Claude Desktop. | |
| aurora-lens aniruddhaadak80/aurora-lens Enables agents to query live NOAA/USGS space-weather and earthquake feeds, compute deterministic storm-risk assessments with hash-chained integrity seals, and verify data authenticity via JSON-RPC tools. | |
| Crucible aniruddhaadak80/crucible Enables agents to turn a real model failure into a deterministic benchmark task by forging it with exact assertions, grading the task itself across six weighted factors, and inspecting a tamper-evident SHA-384 audit trail. Exposes eleven ty | |
| Cryptotremor aniruddhaadak80/cryptotremor Enables agents to inventory cryptographic primitives and score their quantum break cost, rupture year, and harvest-now-decrypt-later exposure against modelled attacker roadmaps and compliance deadlines. Exposes read and idempotent mutation | |
| frostwatch aniruddhaadak80/frostwatch Enables agents to pull live overnight forecasts for grower blocks and score frost risk with an itemised, versioned engine, returning cold-window start/end hours and a run-protection, stand-by, or no-action verdict. It also lets agents list | |
| Handover aniruddhaadak80/handover Enables an agent to log doses, observations, and tasks on a per-person shift-change board, run a deterministic readiness check that cites public drug-label sources, seal a hash-chained handover brief, and replay the audit chain through nine | |
| helio-commons aniruddhaadak80/helio-commons Enables agents to manage space-compute mission cards, run readiness forecasts, verify audit trails, and export decision briefs through JSON-RPC tools. | |
| helios-pulse aniruddhaadak80/helios-pulse Enables AI agents to query live space weather, aurora forecasts, earthquake feeds, and the Helios Oracle over HTTPS with no API keys. | |
| hooklens aniruddhaadak80/hooklens Enables AI agents to create webhook bins, list and retrieve captured requests, inspect payloads with seal-chain verification, and clear bins via MCP tools. | |
| laneplan-relay aniruddhaadak80/laneplan-relay Enables agents to walk declared relay lane graphs and deterministically identify the first handoff that loops, exceeds the visit budget, or misses its window, with supporting tools for cycle enumeration and handoff scoring over stdio. | |
| Mintline aniruddhaadak80/mintline Enables agents to assay Solana mints against live on-chain metadata, register, dispute, share, or retire token-identity claims, and replay a tamper-evident SHA-384 ledger to confirm every recorded action and export the resulting dossier. | |
| openplate aniruddhaadak80/openplate Enables agents to search open museum collections, compare artwork copyright terms with institutions’ reproduction claims, assess intended uses, and export sealed credit lines or dockets through MCP tools. | |
| Patchbay aniruddhaadak80/patchbay Exposes an MCP-style JSON-RPC interface at /api/mcp that lets an assistant read a live model catalog, compile and score routing policies across fast/balanced/deep lanes, patch lane assignments, and replay per-entity hash chains to verify in | |
| pqc-triage aniruddhaadak80/pqc-triage Enables an agent to import real dependency manifests and source excerpts, resolve each cryptographic surface to an algorithm, and assess it against published quantum resource estimates and NIST transition dates. Supports recording migration | |
| pulsegrid aniruddhaadak80/pulsegrid Enables agents to retrieve live planetary risk intelligence—space weather, earthquakes, and wildfires—fused into a deterministic Instability Index, along with sealed briefing and integrity verification tools. | |
| Safety Herbarium MCP Server aniruddhaadak80/safety-herbarium Enables agents to build and inspect AI-safety reading volumes by mounting live arXiv papers and open-access textbooks, grading how well those volumes cover ten risk classes, and exporting syllabi or sealed JSON. Every mutation is appended t | |
| Shorwatch aniruddhaadak80/shorwatch Enables agents to probe a live host's TLS handshake, read the actual SubjectPublicKeyInfo from the served certificate, and corroborate that exact key against Certificate Transparency logs to learn how long it has been harvestable. Exposes t | |
| skill-relay aniruddhaadak80/skill-relay Enables agents to discover, score, and package public agent skills into cross-harness relay packs, then create, update, and verify them over JSON-RPC. | |
| skillforge aniruddhaadak80/skillforge Enables AI agents to search, retrieve, score, compose, and verify reusable agent skills from the SkillForge registry via MCP. | |
| solar-sentinel aniruddhaadak80/solar-sentinel Enables AI agents to query live NOAA and NASA solar storm feeds, compute deterministic geomagnetic risk scores, and verify hash-chained data seals through MCP tools. | |
| stewardship-ledger aniruddhaadak80/stewardship-ledger Enables agents to create, update, score, and verify tamper-evident stewardship cases through JSON-RPC MCP tools, making AI accountability records inspectable and replayable. | |
| Swellread aniruddhaadak80/swellread Enables agents to query live surf-break conditions, run what-if tide and engine evaluations, and create, update, log, export, or verify sealed session records through typed JSON-RPC tools. | |
| Telltale MCP Server aniruddhaadak80/telltale Exposes twelve typed tools over MCP-style JSON-RPC 2.0 so agents can grade a multi-turn transcript against escalating social pressure, report the turn a position moved, what it cost in verified facts, and whether it reverted once the load s | |
| terra-pulse aniruddhaadak80/terra-pulse Enables AI agents to query live earthquake and disaster event data, and to compute deterministic risk assessments with tamper-evident seals. |
29,151–29,200 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.