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 |
|---|---|
| Aseprite MCP Tools ext-sakamoro/asepritemcp A Python MCP server enabling programmatic interaction with Aseprite for pixel art creation and manipulation with features like drawing operations, palette management, and batch processing. | |
| garageband-llm-bridge extao15/garageband-llm-bridge A local CLI and MCP server enabling an LLM to control GarageBand on macOS via AppleScript, accessibility automation, and MIDI workflows. | |
| web-summaries-mcp extempore66/web-summaries-mcp A Streamable HTTP MCP server that fetches YouTube transcripts and lets an LLM semantically search within them. | |
| web-summaries-mcp extempore66/web-summaries-mcp-v2 Fetches YouTube transcripts and enables semantic search within them using local embeddings, allowing an LLM to retrieve relevant passages with timestamps. | |
| Rule MCP Server extend-marketing/rule-mcp-server A Model Context Protocol (MCP) server for the Rule marketing automation platform. It provides full access to Rule's REST API v2 for subscriber management, campaigns, transactional messages, and more. | |
| ontoloom extensityai/ontoloom MCP server for building and exploring OWL 2 ontologies using AI agents, with tools for axiom management, structural pattern matching, and persistent selections. | |
| tcs_mcp_claude exthnet/tcs_mcp_claude MCP server that integrates Claude with the Kyushu University supercomputer Genkai's TCS (PJM) job scheduler. It enables natural language control of job submission, status monitoring, deletion, resource queries, and reading output files. | |
| tcs-mcp exthnet/tcs_mcp_codex MCP server to operate Fujitsu Technical Computing Suite (TCS/PJM) on Kyushu University's supercomputer 'Genkai' from MCP clients like Codex, supporting direct and SSH modes for job submission, monitoring, and file operations. | |
| mcp-py-devto extinctsion/mcp-py-devto Enables interaction with dev.to platform through a message-based architecture, supporting article management operations like create, update, delete, and get articles. | |
| codemenu-mcp extiri/codemenu-mcp Enables AI assistants to search and retrieve code snippets from the CodeMenu snippet manager via the local HTTP API. | |
| gcv-kie-mcp extreez/mcp-kie MCP server for kie.ai providing image, video, and music generation with cost estimation, spending limits, and a transaction ledger. | |
| project-memory-mcp extrei/project-memory-mcp Enables coding agents to persist notes, decisions, requirements, and learnings per project in SQLite and retrieve them across sessions via search and status tools. | |
| odools-mcp extrememicro/odools-mcp Enables precise, position-based Odoo code navigation through a local MCP adapter that exposes read-only definition, declaration, references, and status tools via the OdooLS runtime. | |
| open-scout exux23/open-scout Enables agents to query a self-hosted, locally indexed web corpus through MCP tools for keyword, neural, or hybrid search, to fetch clean text from already-indexed URLs, and to discover pages similar to an indexed URL. | |
| Jatobá Brain ey-luccas/jatoba-brain Provides persistent, multi-project memory for AI agents via MCP, enabling them to store and retrieve tasks, decisions, errors, checkpoints, and documentation while keeping context isolated by project. | |
| autocad-com-mcp ey2h/autocad-com-mcp Enables AI clients to control a running AutoCAD via Windows COM, supporting zoom, selection, highlighting, entity queries, and command or LISP execution without restarting AutoCAD. | |
| CV Resume Builder MCP eyaab/cv-resume-builder-mcp Automatically generates and updates CVs/resumes by aggregating data from git commits, Jira tickets, Credly certifications, and existing PDF resumes, with LaTeX formatting support. | |
| gemini-web-pro eyad-eladawy/antigravity-universal-ai-bridge Enables Antigravity IDE to delegate coding, debugging, and architecture work to an already logged-in Gemini, Claude, ChatGPT, or DeepSeek web session, then applies the returned changes directly to workspace files over a local WebSocket brid | |
| relay-image-mcp eyaeya/relay-image-mcp Enables image generation and editing through a configurable relay image API, with explicit parameters, original image preservation, and technical verification of output dimensions and transparency. | |
| @cig-chat/mcp eyalbarash/cig-chat-mcp MCP server for the cig.chat API that lets you connect Claude, Cursor, or any MCP client to your cig.chat bot to manage subscribers, tags, flows, WhatsApp templates, broadcasts, and shop operations in plain language. | |
| vscode-helper eyalev/vscode-self-mcp Enables AI agents to control VSCode workspaces, including file operations, terminal commands, search, and workspace management. | |
| codex-mcp-bridge eyalk11/codex-mcp-bridge MCP server that lets Claude Code drive the local Codex CLI as a sub-agent for concurrent queries and optional file/shell actions, using the CLI's existing login and sessions. | |
| dsh-mcp-bridge eyalm321/dsh-mcp-bridge Exposes DeepSeek Harness capabilities—durable memory, task ledger, project-agent dispatch, and the wider MCP estate—as declared MCP tools for any MCP client. | |
| dynadot-mcp eyalm321/dynadot-mcp MCP server for Dynadot API to manage domains, DNS, contacts, nameservers, folders, and aftermarket. | |
| github-mcp eyalm321/github-mcp An MCP server providing 1,112 tools for the GitHub REST API across all 44 API categories. It enables comprehensive GitHub operations through Claude with typed validation and category filtering. | |
| hearthsmith eyalm321/hearthsmith Lets MCP clients manage the hearthsmith task store—listing, adding, completing, blocking, and snoozing tasks—and read recent nags so coding agents can pick up and respond to the blacksmith's reminders. | |
| hyperpanes-mcp eyalm321/hyperpanes-mcp MCP server for hyperpanes terminal workspace app, enabling AI agents to compose and launch workspace layouts, inspect and drive terminal panes, stream output, and orchestrate agent hierarchies. | |
| jlcpcb-mcp eyalm321/jlcpcb-mcp MCP server for JLCPCB/LCSC component search, live stock and pricing, datasheets, and PCB/3D printing ordering via authenticated API. | |
| multilingual-dictionary-mcp eyalm321/multilingual-dictionary-mcp An MCP server for multilingual dictionary lookups with word relations such as synonyms, antonyms, and definitions, leveraging ConceptNet, Wiktionary, and Datamuse APIs. | |
| originality-mcp eyalm321/originality-mcp MCP server for Originality.ai that provides tools for AI detection, plagiarism checking, fact verification, readability analysis, grammar/spelling, and SEO optimization. | |
| zernio-mcp eyalm321/zernio-mcp A Model Context Protocol (MCP) server that gives Claude full access to the Zernio social media management API — 273 tools covering posts, analytics, inbox, ads, contacts, WhatsApp Business, and more across 14+ platforms. | |
| telegram-mcp eyalwerber/telegram-mcp Enables fetching the most recent image from a specified Telegram group and waiting for new images to be posted, using a user account over MTProto. | |
| chisel eyamans/chisel Enables AI agents to construct, edit, and export 3D models using geometric primitives and boolean operations, with multi-view rendering to facilitate spatial reasoning. | |
| fmod-studio-mcp eyamans/fmod-studio-mcp An MCP server that drives FMOD Studio live through its scripting terminal, exposing the FMOD Studio Scripting API as MCP tools for immediate project editing. | |
| Secure Clinical LLM Access via MCP eyasu11321238a/secure-clinical-llm-mcp An MCP server that enables LLMs to securely query synthetic clinical data through validated, scoped tools (patient summaries, conditions, medications, lab trends, encounters) while maintaining audit logs and access controls. | |
| browser-mcp eye-fox/browser-mcp Enables AI agents to control a local Chromium browser via CDP for page snapshots, screenshots, human-like interactions, autonomous crawling, API/GraphQL reconnaissance, authenticated differential testing, and Burp-like intercept, repeater, | |
| inbox-tap-mcp eye-fox/inbox-tap-mcp Enables AI agents to create and use temporary email and SMS inboxes, check messages, and wait for or extract OTPs and verification links during account registration. Combines both channels through a unified OTP tool while redacting sensitiv | |
| vghsdk-mcp eyeduck-ai/vghsdk-mcp MCP server for querying patient, surgery, outpatient, inpatient, consent, and IVI data within the VGH intranet. Provides 27 tools with unified authentication and date formatting. | |
| wxrpa eyeing0721/wxrpa Enables agents to drive WeChat 4.x on Windows without hijacking the foreground window, mouse, or keyboard — sending text and file messages through message posting rather than input injection. Also exposes tools for decrypting and querying t | |
| PyPen MCP eyenoticeall/pypen Enables LLM-powered browser automation and security testing with features like browser management, network monitoring, DOM manipulation, and captcha handling. | |
| JIT Tool Synthesis eyeseethru/jit-tool-synthesis Enables on-demand generation of TypeScript tools using an LLM with human-in-the-loop approval and safe sandboxed execution. It allows users to create and persist custom functionality through natural language requests. | |
| mQuickCalc Finance MCP Server eyetoolkit/mquickcalc-finance-mcp Enables AI agents to calculate Etsy, eBay, and Stripe fees, compare platform fees, and analyze profit margins through MCP tools. | |
| mquickcalc-health eyetoolkit/mquickcalc-health-mcp Enables AI agents to calculate BMI, BMR, TDEE, daily calorie needs, and macro nutrient splits using mQuickCalc's health formulas. | |
| mquickcalc-utility eyetoolkit/mquickcalc-utility-mcp Enables AI agents to perform 22 unit conversions and common calculations such as length, weight, temperature, volume, tip, percentage, date difference, age, currency, cooking, and fuel consumption. | |
| Xledger MCP Server eyevinn/xledger-mcp-server Provides read-only access to Xledger accounting data via GraphQL API for querying invoices, balances, projects, timesheets, and more. | |
| Eyevinn Open Source Cloud MCP Server eyevinnosc/mcp-server MCP Server for Eyevinn Open Source Cloud API, enabling creation of solutions based on open web services. Web services based on open source where the creator gets a share of the revenue the platform generates. | |
| MeshCentral MCP Server eynaexp/meshcentral-mcp Enables AI assistants to control a MeshCentral panel by listing and managing devices and groups, running remote commands, performing power actions, sending notifications, and managing users, events, notes, and Intel AMT scans. | |
| blocksnet-mcp eynor-k/blocksnet-mcp Local MCP server for urban analytics that wraps BlocksNet agent, enabling natural language urban questions to be answered with structured JSON results. | |
| Cuprice MCP Server eynullabeyli/cuprice-mcp Public MCP server for integrating Cuprice pricing widgets from AI tools like Cursor, Claude Desktop, and Claude Code. | |
| mcpapp1 eyosiasbisrat/mcpapp1 Enables MCP clients to retrieve live National Weather Service alerts for any US state and verify connectivity via an echo resource. |
49,201–49,250 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.