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 |
|---|---|
| easyeda-mcp cheewee2000/easyeda-mcp Enables MCP clients like Claude Code to control a running EasyEDA Pro instance for PCB design automation, including DRC checks, project management, and script execution via a bridge server. | |
| Aidderall MCP Server cheezcake/aidderall_mcp Provides AI assistants with a hierarchical task management system that maintains focus and context across complex problem-solving sessions, solving context window limitations through organized task structures. | |
| Nexus MCP cheezcake/nexus_mcp Enables Claude Code to interact with a temporal knowledge graph through 24 tools for CRUD, search, traversal, and view management, with automatic entity resolution via a context hook. | |
| shop-mcp cheffcorleone/commerce-mcp Enables AI agents to browse products, look up orders, and place orders through MCP tools, with API-key authentication, rate limiting, and idempotent order operations. | |
| mcp-nextcloud-calendar cheffromspace/mcp-nextcloud-calendar mcp-nextcloud-calendar | |
| overtooled-mcp chefjulio/overtooled-mcp MCP server for local file conversion, analysis, and image processing across 44 formats with 7 tools, all processed locally. | |
| tradingview-mcp-chefy chefy3x/tradingview-mcp-chefy Token-efficient TradingView MCP for traders who backtest Pine strategies; aggregates strategy results and trade data server-side to reduce token usage. | |
| F5 BIG-IP MCP Server chellanetai/f5-mcp-claude Enables Claude to query an F5 BIG-IP over read-only iControl REST, retrieving system/version and failover state, virtual server and pool member health, and any other readable /mgmt/tm/ object through natural-language questions. Every tool i | |
| AIE7-MCP chelsea-zhou/aie7-mcp MCP server that provides web search capabilities using the Tavily API. | |
| gtfs-scorecard chelseakr/gtfs-scorecard A read-only MCP server that answers questions about GTFS transit feed quality from the published gtfsscorecard.org scorecards: letter grades, the fixes that matter most, and score history. It runs locally over stdio with no API key and no w | |
| ctroy-code-analysis chelseatroy/ctroy-code-analysis An MCP server that provides six code review tools for use with Claude Code or any MCP client. Each tool reads a file from disk, pairs its contents with a structured review prompt, and returns the bundle for the LLM to evaluate. | |
| ark-nitrado-mcp chelseyklein/ark-nitrado-mcp An MCP server that lets Claude check your Nitrado-hosted ARK server: live status, settings, and files without using the web panel. | |
| ark-wiki-mcp chelseyklein/ark-wiki-mcp An MCP server that lets Claude answer ARK: Survival Ascended / Evolved questions by querying the ARK community wiki for taming, crafting, spawns, and stats. | |
| ContextTree MCP chelslava/mcp-context-tree Enables AI coding assistants to perform local semantic code search using AST parsing and embeddings, finding code by meaning with exact file and line locations, plus AST-based usage lookup. | |
| heracleum-tox-mcp-server chemagents/heracleum-tox-mcp-server Reproduces the in-silico toxicological profile of Heracleum sosnowskyi metabolites from Rassabina & Fedorov (2025) using open-source models for LD50 prediction, toxicity classification, chemical space clustering, and synthesis cost estimati | |
| tox-antitargets-mcp-server chemagents/tox-antitargets-mcp-server An MCP server that reproduces the results of Nikitin et al., 'Towards Explainable Computational Toxicology: Linking Antitargets to Rodent Acute Toxicity' as callable tools, enabling users to compute toxicity predictions and mechanistic anal | |
| ChemDataDoctor MCP chemaiatlas/chemdatadoctor-mcp Enables local validation, normalization, duplicate detection, and cleaning of chemical compound datasets and identifiers through MCP tools, with stdio-only operation and no outbound requests or telemetry. | |
| Today's Headlines MCP Server chemany/toutiao_mcp_server A full-featured content management platform for Today's Headlines that supports automated login, content publishing, and data analytics, with complete compatibility with Xiaohongshu's publishing tool format for one-click multi-platform publ | |
| Zhihu MCP Server chemany/zhihu_mcp_server A simple HTTP API server that allows users to publish articles, create answers, manage columns, and upload images on Zhihu (a Chinese Q&A platform) through straightforward REST API endpoints. | |
| aijobsboom-x402 chemi-kill/aijobsboom-x402 x402-gated data API (Cloudflare Worker) plus an MCP server wrapper serving aggregate weekly stats from the aijobsboom.com skilled-trades job board — trade counts, perk flags, scrub-rule counts. $0.01/$0.10 USDC per call, no raw job listings | |
| rotacloud-mcp-node chemicalluck/rotacloud-mcp-node MCP server exposing the RotaCloud API to Claude and other MCP clients, covering all 129 documented v1 operations across 36 resources including shifts, attendance, leave, users, locations, roles, and timesheets. | |
| cheminfo-mcp-server cheminfo/cheminfo-mcp-server Enables MCP clients and the cheminfo chat to call one catalog of tools while carrying produced structures, reaction schemes, spectra and files beside the answer rather than through the model. It provides tool listing, tool invocation, and s | |
| CraftGraph MCP chemiofitor4096/craft-graph-mcp Enables AI clients to query live Minecraft recipe data and compute recipe trees, production plans, and searches from a running game or disk snapshots, with markdown, TSV, JSON, and HTML outputs. | |
| tutu-mcp-kit chemisttt/tutu-mcp-kit MCP server for searching multi-transport routes and hotels, enabling trip planning with combined ticket and hotel options and deep links to purchase on Tutu.ru. | |
| MCPymol chemrich/mcpymol A Model Context Protocol server that lets you drive PyMOL with natural language, enabling structure loading, analytical views, measurements, and protein exploration through AI assistants. | |
| scientist-literature chemyibinjiang/scientist-literature-browser-mcp Enables Codex to access and extract approved publisher content, including article text, figures, PDFs, and supplementary information, through governed persistent browser sessions and challenge recovery. | |
| ocrmypdf-mcp chemysterium/ocrmypdf-mcp Provides OCR capabilities to add searchable text layers to scanned PDFs, with tools to check OCR need, process single files or batch folders, and integrate with Zotero attachment storage. | |
| AI-SyncForge chen-muxi/ai-syncforge A LAN multi-AI collaborative development ecosystem connecting tools like Cursor, Windsurf, and Claude Desktop via MCP for automated Dev-QA-Ops workflows. | |
| Ansys Workbench MCP chen-xin-yuan/sci_training Enables MCP clients like Codex to control Ansys Workbench and ICEM CFD locally, executing scripts, managing projects, and running simulations. | |
| quant-core chen171111/mcp-portfolio Enables clients to inspect strategy catalogs and stock pools, run real backtests with performance metrics, fetch recent quotes, and view risk and trading-cost configuration for an A-share quant framework. | |
| godot-mcp chen19007/godot-mcp MCP server for automating GDScript code linting, formatting, and export validation in Godot projects. | |
| agc-connect-mcp chen2he/agc-connect-mcp Enables AI agents to manage Huawei AppGallery Connect apps, including uploads, releases, reviews, and reports, and to search HarmonyOS official documentation. | |
| ai-memory-mcp chen789654/ai-memory-mcp Enables AI assistants to retain memory across sessions by storing conversations locally in Markdown files, allowing personalization and continuity without external servers. | |
| Typst MCP Server chen80097/typst-mcp Enables AI models to interact with Typst by converting LaTeX to Typst, validating Typst syntax, rendering Typst code to images, and browsing Typst documentation chapters. | |
| Graphiti MCP Server chen9z/graphiti_mcp_server Enables AI assistants to build and query temporally-aware knowledge graphs from conversations and data, maintaining persistent memory of entities, relationships, and facts across interactions. | |
| paper-search chenchaozhao/citekick MCP server providing agentic tools for academic paper search, with support for OpenAlex API and optional API keys. | |
| MCP Python Demo chenchen0611/mcp-python-demo An MCP-based project that integrates Zhipu AI and Tencent Map APIs to provide weather queries, geocoding, and web search functionality through both command-line and web interfaces. | |
| DevSpace chenchihcu/devspace-mcp A self-hosted MCP server that gives ChatGPT a secure connection to your local machine, enabling it to read, edit, search, and run code in your projects. | |
| AgentRig chencj-io/agentrig Enables evidence-first regression testing for AI agents by turning production traces into reviewed, replayable cases that gate releases. It supports reproducible, auditable agent evaluation with controlled tool execution, evidence-based jud | |
| MCP Server chendaleiq/mcp-iot A modular server based on Model Context Protocol (MCP) that provides weather queries, mathematical calculations, and search functionalities. | |
| vmix-workbench-mcp chendpoc/vmix-workbench-mcp Enables AI agents to inspect and control vMix live production: import media, assemble multi-layer scenes, update titles, configure native transitions and stinger bindings, and create managed triggers for automated actions. | |
| mongodb3-mcp-server chenfukun/mongodb3-mcp-server A lightweight MCP server for MongoDB 3.6+ providing read, write, metadata, and management tools. | |
| Customer-Try cheng180/mcp-customer-agent MCP server for intelligent car sales customer service, providing inventory search, stock checking, and price quoting tools. | |
| Azure Data Explorer MCP Server cheng306/mcp-server Enables users to authenticate with Azure Data Explorer and execute KQL queries via natural language through the Model Context Protocol. | |
| cascade-mcp cheng6563/cascade-mcp Enables AI assistants to run shell commands, read, write, edit, search, and stream files on remote SSH servers and Docker containers, including nested multi-layer chains, without installing any runtime on the target hosts. It auto-injects a | |
| image-forge-mcp cheng77c/image-forge-mcp An MCP server for AI-powered image processing (generate, edit, vary, analyze) supporting OpenAI, Gemini, Ideogram, and custom relay endpoints. | |
| UE-MCP chengdagong/ue-mcp Enables AI assistants to interact with Unreal Editor 5 through the Python remote execution protocol. It allows for managing the editor lifecycle, configuring project settings, and executing Python scripts directly within the Unreal Engine e | |
| CNKI-Enhanced-MCP chengdsyj-studio/cnki-enhanced-mcp Enables AI to search, filter, and process CNKI academic literature through natural language, including structured search, metadata retrieval, full-text reading, citation export, and PDF/CAJ download. | |
| ParentSquare MCP chengeusa3/parentsquare-mcp MCP server that gives Claude read access to your ParentSquare parent account, enabling queries about school posts, calendars, messages, directory, signups, forms, payments, and files. It also parses image/PDF attachments so calendar flyers | |
| remote-mcp-server-authless chengfei867/remote-mcp-server-authless Enables deploying a remote MCP server on Cloudflare Workers without authentication, allowing custom tools and connections to MCP clients like Cloudflare AI Playground or Claude Desktop. |
38,151–38,200 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.