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 |
|---|---|
| Webflow MCP Server christine31037/mcp-server Enables AI agents to interact with the Webflow Data API and Designer, so users can query and manage sites, CMS collections and blog content, update pages, and build responsive page elements through natural language. Supports both remote OAu | |
| Pentest MCP christine40143/pentest-mcp Enables professional penetration testers to orchestrate reconnaissance, web scanning, brute-force testing, exploitation, traffic capture, hash cracking, wordlist building, privilege escalation audits, and client report generation via STDIO/ | |
| MiniMax-Coding-Plan-MCP christine7322/minimax-coding-plan-mcp Enables coding-plan users to perform AI-powered web searches and analyze images from URLs or local files through MCP clients, returning structured search results and vision-based answers optimized for development workflows. | |
| Gitingest-MCP christinegauthier704/gitingest-mcp Enables MCP clients such as Claude Desktop, Cline, Cursor, and Windsurf to quickly extract information about GitHub repositories, including repository summaries, project directory structure, and file content. | |
| FirstData MCP christineiyer/firstdata Enables natural-language discovery of authoritative primary data sources, returning ranked recommendations with authority levels, access URLs, APIs, update frequency, and traceable evidence chains. Also supplies step-by-step navigation inst | |
| mem0-mcp-selfhosted christinelambert299/mem0-mcp-selfhosted Enables Claude Code to store and recall persistent cross-session memories using a self-hosted stack of Qdrant, Neo4j, and Ollama, backed by Anthropic or a local LLM. Exposes 11 tools for adding, searching, updating, and deleting memories pl | |
| vnsh-mcp christineo376/vnsh Enables AI agents to create, read, update, list, restore and version-share encrypted workspaces of files and context, so multiple agents and people can collaborate on one link that self-deletes 24 hours after the last edit. | |
| Basecamp MCP Server christinesiekiera06679/basecamp-mcp-server Enables MCP-capable clients such as Codex, Cursor, and Claude Desktop to read and manage Basecamp 3 projects through OAuth-authenticated API calls, covering projects, todos, messages, card tables, docs, uploads, and search. | |
| mcp-agent-chatterbox christofmilius/mcp-agent-chatterbox Enables AI agents to generate spoken audio locally on a GPU via the Chatterbox models, with zero-shot voice cloning from reference clips, multilingual output, and sentence-aligned chunking for long text. | |
| mcp-agent-docparser christofmilius/mcp-agent-docparser Enables MCP-aware agents to fetch documentation pages, strip navigation noise, convert HTML to clean markdown, and emit or return timestamped .md files ready for LLM contexts. | |
| mcp-agent-mail christofmilius/mcp-agent-mail Enables AI agents to read, send, and reply to GPG-encrypted email over IMAP/SMTP, manage a contact book with key provenance, and archive and search everything read. Key material and message bodies are kept out of the model's context window, | |
| openjev-router christofmilius/mcp-agent-openjev Provides agents with MCP tools for typed probabilistic decisions—Choice, Noul, and Score—with calibrated probabilities and abstention, using local OpenAI-compatible models via LM Studio logprobs. | |
| mcp-agent-playwright christofmilius/mcp-agent-playwright Enables AI agents to drive a real Playwright browser over MCP to navigate pages, read accessibility-tree snapshots, click, type, screenshot, and evaluate JavaScript, either in a managed browser or attached to a running Chromium-based browse | |
| mcp-agent-transcriber christofmilius/mcp-agent-transcriber Enables MCP-aware agents to fetch direct captions or download audio and transcribe with local Whisper from common video platforms like YouTube, Vimeo, and Twitch. | |
| Jira/Confluence Team Lead MCP christojansen75/jiramcp Provides sprint and developer analytics from Jira, answering questions about sprint content, developer performance, and refinement readiness. Can publish reports to Confluence for easy sharing. | |
| HISE MCP Server christoph-hart/hise_mcp_server Provides access to HISE documentation, including UI component properties, Scripting API methods, and module parameters. It features a searchable database of code snippets and best practices to assist in audio software development. | |
| swissdevjobs christoph34235/swissdevjobs-cli Enables AI agents to search and filter thousands of tech job postings across nine boards and eight countries — including salary-transparent listings and Swiss and Singapore government portals — and to apply directly. It also tracks prior ap | |
| codeforge christoph865/codeforge Enables automated software development workflow from GitLab issues to merge requests via AI agents, with tools for drafting specifications, implementing code, and managing GitLab operations. | |
| ASTRA 3.0 MCP Server christophejlegros-lgtm/astra-3.0- Enables closed-loop bridge between Cortical Labs' CL1 and Unreal Engine for real-time 3D navigation via neural spike decoding. | |
| ASTRA christophejlegros-lgtm/astra-unified-researchlab-mcp-fcs-v3.1.0 Exposes a bio-hybrid neuromorphic simulation pipeline to MCP clients, enabling AI assistants to query SNN LIF+STDP simulation, consciousness proxy assessment, bio-computing platform telemetry, and IRB ethics monitoring as MCP tools, resourc | |
| ASTRA MCP Server christophejlegros-lgtm/astra-unified-researchlab-mcp-v2.1 Exposes a bio-hybrid neuromorphic simulation pipeline (SNN LIF+STDP, consciousness proxies, ethics monitor) as MCP tools, resources, and prompts to AI assistants. | |
| ASTRA Unified Research Lab MCP Server christophejlegros-lgtm/astra-unified-researchlab-mcp-v2.4 Integrates a bio-hybrid neuromorphic simulation pipeline with SNN, consciousness proxies, and bio-computing platform telemetry as MCP tools, resources, and prompts for AI assistants. | |
| ASTRA MCP Server christophejlegros-lgtm/astra-unified-researchlab-mcp-v2.5 Exposes a bio-hybrid neuromorphic simulation pipeline (SNN, consciousness proxies, FinalSpark NeuroPlatform) as MCP tools, resources, and prompts for AI assistants like Claude, Cursor, and VS Code. | |
| ASTRA — Unified Research Lab + MCP Server christophejlegros-lgtm/astra-unified-researchlab-mcp-v2.6 Exposes a bio-hybrid neuromorphic simulation pipeline (SNN, consciousness proxies, wetware integration) as MCP tools, resources, and prompts for AI assistants. | |
| ASTRA MCP Server christophejlegros-lgtm/astra-unified-researchlab-mcp-v2.7 Enables AI assistants to query and control a bio-hybrid neuromorphic simulation pipeline, including SNN engine, consciousness proxies, and neuroplatform telemetry, via the Model Context Protocol. | |
| ASTRA — Unified Research Lab + MCP Server christophejlegros-lgtm/astra-unified-researchlab-mcp-v2.8 MCP server for ASTRA bio-hybrid neuromorphic simulation pipeline, exposing SNN, consciousness proxies, and living neural organoid control tools to AI assistants. | |
| ASTRA MCP Server christophejlegros-lgtm/astra-unified-researchlab-mcp-v2.9 Exposes a bio-hybrid neuromorphic simulation pipeline (SNN LIF+STDP, consciousness proxy, bio-platform telemetry, ethics monitor) to AI assistants via MCP tools, resources, and prompts. | |
| ASTRA Unified Research Lab MCP Server christophejlegros-lgtm/astra-unified-researchlab-mcp-v3.0.1 Enables AI assistants to interact with a bio-hybrid neuromorphic simulation pipeline, including a layered SNN engine, consciousness proxy metrics, NeuroPlatform wetware bridge, and ethics monitoring via 62 MCP tools, resources, and prompts. | |
| Calendar MCP Server christopheprat/calendar-mcp Enables access to Google Calendar events from a public ICS feed, allowing users to list and search calendar events within specific date ranges with automatic handling of recurring events. | |
| Roblox Documentation MCP Server christopher-buss/roblox-docs-mcp Enables AI agents to intelligently search and retrieve Roblox documentation through semantic search and vector embeddings, providing natural language access to complete Roblox Creator Documentation. | |
| Motion MCP Server christopher-czaban/motion-mcp-server An open-source MCP server enabling AI assistants to interact with the Motion API for intelligent task and project management. | |
| video-editor christopher-stevers/video-mcp An MCP server that enables natural language video editing using FFmpeg, supporting operations like trimming, merging, format conversion, and more with real-time progress tracking. | |
| materials-studio-mcp-moc christopher2lllp3t-cell/materials-studio-mcp-moc MCP server for BIOVIA Materials Studio 2023 on Windows, providing controlled preparation of Forcite and CASTEP inputs, model building, and LAMMPS/VMD pre-processing with reproducible, auditable workflows and strict scientific boundaries. | |
| tmux-bridge-mcp christopherbutt000/tmux-bridge-mcp Enables AI agents running in separate tmux panes to read each other's output, send messages and keystrokes, and coordinate multi-agent workflows through standard MCP tool calls, without frameworks or extra infrastructure. | |
| Cloud Discord MCP christopherdodzi817-max/discord-mcp bot control | |
| pc-bot christopherdond/pc-bot MCP server that enables AI agents to control Windows by clicking, typing, and navigating with a visible cursor overlay, using a layered approach (native UIA, browser CDP, pixel fallback) for reliable interaction. | |
| mcp-bitbucket-dc christopherekfeldt/mcp-bitbucket-dc An MCP server for Bitbucket Data Center that enables AI assistants to search code, browse files, and manage pull requests through a standardized interface. It supports comprehensive repository exploration, including Lucene-style code search | |
| freellmpool christopherf29863/freellmpool Enables MCP clients to query and chat through a pool of free LLM providers behind a single OpenAI-compatible gateway. It exposes routing across enabled keyless, free-tier, and pinned provider routes, with automatic failover and model catalo | |
| mcp-server-duckdb christopherfedorov/mcp-server-duckdb Enables database interaction through the Model Context Protocol, including running SQL queries, creating tables, and inspecting schemas, with optional read-only enforcement. | |
| comfyui christophergoodale/comfy_mcp Enables an AI agent to generate images on a remote ComfyUI machine by invoking named, swappable exported ComfyUI API workflows and save the results into a local workspace directory. | |
| Sheets & Drive MCP Server christophergoodale/sheets_drive_mcp Enables Claude to list, search, and share Google Drive files and read, write, append, and create Google Sheets through natural-language requests. | |
| Zendesk MCP Server christopherjang6062/zendesk-mcp-server Enables AI assistants to retrieve and manage support tickets, comments, and attachments, and to search help center articles as a knowledge base, with each request carrying the operator's own OAuth-authenticated permissions. | |
| ombre-brain christopherk57231/ombre-brain Provides Claude with persistent cross-conversation memory, tagging each stored memory with valence and arousal coordinates and letting emotionally charged or unresolved ones surface automatically. Memories live as Obsidian-compatible Markdo | |
| LOOP Developer Agent christophermwanginjoroge/loop_mcp MCP server for LOOP financial infrastructure, enabling AI agents to inspect projects, generate payment integration code, and execute sandbox-validated transactions (M-Pesa, LOOP, PesaLink) with a deterministic policy engine. | |
| InstantDB MCP Server christophersutton/instantdb-mcp Provides a read-only interface for querying InstantDB data with tools to execute queries and retrieve examples based on pre-defined patterns. | |
| mcp-marketing-analytics christophertanenso/mcp-marketing-analytics Enables natural language querying of Google Analytics 4, Google Search Console, Meta Ads, and Google Ads data through Claude. | |
| script-decoder-mcp christophervalvo/script-decoder-mcp Enables static analysis of scripts without executing them, providing plain-English behavior explanations, decoded obfuscated content, IOC extraction, risk scoring, and MITRE ATT&CK mapping. | |
| remix-mcp christopherwxyz/remix-mcp A Rust MCP server that enables AI assistants to control Ableton Live via OSC, offering 266 tools for transport, tracks, clips, scenes, devices, and more. | |
| Multi-Provider Image Generation Server christophezhao/image-gen-mcp-server Enables AI-assisted image generation from text prompts using multiple providers (Tencent Hunyuan, OpenAI DALL-E 3, and Doubao) with support for various artistic styles, resolutions, and negative prompts through a unified interface. | |
| open-design-system-mcp-starter christophhdesign/open-design-system-mcp-starter Provides a real API for coding agents to look up design system components, props, and tokens, preventing guessed answers. |
38,751–38,800 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.