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 |
|---|---|
| CoDesign bioinfornatics/co-design Enables a local product design workflow in Goose, from evidence and framing through journey approval, handoff, and QA. | |
| barista-memory biokys/barista-memory Enables archiving and retrieving GaggiMate espresso shot history, managing bean/grind/dose context periods, monitoring machine state and power sessions, and writing profiles and settings through MCP tools. | |
| TradingView MCP Bridge biola-dev/tradingview-mcp Connects an AI assistant to a locally running TradingView Desktop app through Chrome DevTools Protocol, enabling chart analysis, Pine Script development, drawing, alerts, replay practice, screenshots, and multi-pane workflow automation. | |
| bsp-mcp biological-sovereignty-protocol/bsp-mcp Connects AI assistants to health data via the Biological Sovereignty Protocol, with cryptographically verified user consent enforced on-chain. | |
| voice biomedichen/opencode-voice Exposes push-to-talk speech tools to an agent: check whether the offline ASR daemon is ready, wait for the user to confirm something aloud without auto-submitting that utterance, and interrupt the current turn when the user speaks a stop ph | |
| scinote-mcp bionanomics/scinote-mcp Exposes SciNote ELN bench workflows as MCP tools so an AI assistant can drive them by voice or chat, including ticking checklist items, completing steps, consuming inventory stock, and adding result notes through the SciNote REST API with t | |
| joplin-mcp biontdv/joplin-mcp A Model Context Protocol server that turns your Joplin notebook into a tool an LLM can actually use — read, search, write, and organize notes, and pull OCR'd text straight out of your screenshots. | |
| e-rechnung-mcp biorazlagaem-dev/e-rechnung-mcp MCP server for German e-invoicing with tools to generate and validate XRechnung CII XML locally, supporting German VAT rates and § 19 UStG. | |
| slack-archive-mcp bioshazard/slack-archive-mcp Enables agents to search and retrieve Slack message history from a portable SQLite archive through read-only tools for status, channels, messages, threads, and surrounding context. | |
| SmartAPI MCP Server biothings/smartapi-mcp Enables integration between MCP-compatible clients and APIs registered in the SmartAPI registry, allowing seamless discovery and interaction with bioinformatics and life sciences APIs through standardized MCP protocols. | |
| actian-docs-mcp bipin-24/docs-mcp Enables natural-language queries across Actian product documentation, GA4 content analytics, and Jenkins CI build status. | |
| knowflow bipin-24/knowflow Connects documentation, GA4 search analytics, Jenkins CI pipeline, and RAGAS-style evaluation to Claude for content gap analysis and documentation improvements. | |
| BI Portal Report Builder MCP Server biplatform-demo/mcp-server MCP server exposing BI Portal's self-service Report Builder to MCP clients, enabling listing datasets, running ad-hoc queries, creating/editing/submitting draft reports, and viewing saved dashboards. | |
| memroach_mcp_server biplav-crl/memroach Backs your AI coding agent's memories, skills, and settings to CockroachDB with automatic sync, hybrid semantic+keyword search, knowledge graph, smart context priming, and 16 MCP tools for cross-machine memory management. | |
| pterodactyl-mcp bippy-s-ai-helpers/pterodactyl-mcp Enables MCP clients to drive a Pterodactyl game panel over both its client and application API trees, covering servers, files, backups, schedules, databases, subusers, nodes, nests, and an eight-tool wings websocket console suite. Exposes 1 | |
| Portainer MCP Server birajmainali/poratiner-ce-mcp-server Enables AI assistants to manage Docker containers, images, networks, and services through the Portainer API. | |
| lipi-mcp birajrai/lipi-mcp Enables MCP hosts to access and manage a Lipi vault, including creating, reading, updating, renaming, deleting, and searching notes with romanized Devanagari search. | |
| Biofact biranjan01/biofact An MCP server that lets AI agents record each executed analysis step with SHA-256 hashes of inputs and outputs, validate bioinformatics file formats (FASTA, FASTQ, VCF, BED, GFF/GTF, CSV, TSV, JSON), verify recorded files still match their | |
| vikalp biranjan01/vikalp Enables AI agents to access live NSE option chains, compute greeks and implied volatility, evaluate multi-leg strategy payoffs and max pain, and analyze open option positions with hold/exit levels. | |
| polymarket-mcp-server birantx/polymarket-mcp-server Polymarket prediction markets for Claude — market search, order books, price history, and a liquidity-rewards scanner. Credential-free. | |
| polymarket-mcp-server birantx2/polymarket-mcp-server Provides read-only access to Polymarket prediction markets, enabling searches, order book inspection, price history, reward market rankings, and trader activity via natural language. | |
| Permission Marketing MCP bircher988/mcp Operationalizes Seth Godin's Permission Marketing framework to manage user trust and delegation in AI agent systems through a structured five-level permission ladder. It provides tools for requesting, auditing, and revoking permissions to e | |
| sandbox-mcp bird/sandbox-mcp Provides a local, isolated Linux VM sandbox for AI agents using Apple's Virtualization.framework, enabling fast command execution (~60ms) and package management without cloud costs. | |
| gdb-mcp birdeclipse/gdb-mcp Enables AI agents to debug C/C++ programs with GDB or LLDB, supporting breakpoints, stepping, variable inspection, and function calls. | |
| eBird MCP Server birdingkit/ebird-mcp-server Integrates the eBird API with Claude to query bird observation data, including recent sightings, rare bird reports, contributor statistics, hotspot locations, and taxonomy information through natural language. | |
| zotero-mcp birdinthetree/zotero-mcp Read+write MCP server for Zotero with full write support — create items, manage collections, find and merge duplicates, import BibTeX | |
| forgejo-mcp-server birdiz/forgejo-mcp Enables assistants to read Forgejo repositories and manage issues and pull requests directly from the working session, using the caller's own token against any Forgejo instance. | |
| MCP Trello birdiz/trello-mcp Enables Claude to interact with Trello boards, lists, cards, and labels through a set of MCP tools. | |
| DaisyUI MCP Server birdseyevue/daisyui-mcp A token-efficient local MCP server that exposes DaisyUI component documentation via tools, enabling AI assistants to build UIs using DaisyUI components. | |
| Gauntlet-Incept MCP birdsmith/gauntlet-incept-mcp Enables Claude Desktop to interact with the Gauntlet Incept system for generating, tagging, and grading educational content for K-8 students directly through natural language. | |
| batch-runner birdywen/batch-runner-mcp Enables running multiple bash steps in one MCP call with per-step contains, notContains, or regex expectations, reporting process failures and expectation failures separately. Also provides async status polling, cancellation, guarded comman | |
| infinity-bemind birincsik-byte/mcp-infinity-bemind Enables querying sprint board capacity and task data for a team, allowing Claude to retrieve person tasks, sprint breakdowns, and capacity reports. | |
| indaga-agent birinets/indaga-agent A local-first MCP server for querying multi-omic personal health data (genome, labs, wearables) with an honesty contract and progressive disclosure skills. | |
| Quorum Agents birol91/quorum-agents Enables orchestrating multiple specialist Claude Code agents as a team, with live visualization and agent-to-agent messaging. | |
| Knihobot MCP birosrichard/knihobot-mcp Enables MCP clients to search the Knihobot.cz public book catalog, inspect live physical copies, compare editions, and retrieve recommendations. | |
| reknihy-mcp birosrichard/reknihy-mcp Enables read-only search and retrieval of the public Reknihy.cz book catalog, including filtering, sorting, ISBN lookup, category browsing, and access to product details such as price, availability, and images. | |
| Multi-Tenant Analytics MCP biru-codeastromer/multi-tenant-ecommerce-analytics-mcp Enables e-commerce clients to query their own analytics data in plain English with strict tenant isolation enforced by the database. | |
| groq-whisper-mcp bis-code/groq-whisper-mcp Transcribe audio/video files using Groq-hosted Whisper with word-level timestamps, automatic caching, and cost estimation, offering up to 9x savings over OpenAI Whisper. | |
| Tally bisale24-ops/tally-mcp Enables voice-first shared household expense tracking through Alexa+, letting flatmates record purchases, check balances, and settle debts in the fewest payments. | |
| MCP Shipping Control Center bischoff99/mcp-server Enables comprehensive shipping and order management through EasyPost and Veeqo integrations. Supports creating orders, generating shipping labels, tracking shipments, and managing unified workflows with a web-based dashboard interface. | |
| Agricultural AI MCP Server bishaljena/fs-gate Provides real-time crop price data from Indian government sources and agricultural web search capabilities. Enables AI chatbots to access comprehensive agricultural market information and news for farming-related queries. | |
| mcp-onepiece bishalw/mcp-onepiece Provides structured access to One Piece Wiki content—articles, infoboxes, chapters, episodes, and story arcs—with configurable spoiler limits that keep responses within what a user has read. | |
| oyama-opendata-mcp bishi-eava/oyama-opendata-mcp Read-only MCP server providing population and age distribution data for Oyama City, Japan, enabling AI clients like Claude to query and analyze open data. | |
| Vulnerable Notes MCP Server bishnubista/vulnerable-notes-mcp A deliberately insecure note management server designed to test security scanners and train developers by demonstrating common MCP vulnerabilities. It provides tools for creating, searching, and exporting notes while featuring intentional f | |
| DOMRay MCP Server bishoku/domray Enables AI coding agents to inspect active authenticated browser sessions and runtime state, capture user breadcrumbs and network/error telemetry, and generate Playwright/Cypress tests or MSW mock handlers through standard MCP tools. | |
| kcdevs-mcp bishop81/kcdevs-mcp Enables AI assistants to search live Kansas City developer jobs, look up hiring companies, and retrieve salary/demand statistics. | |
| AI SEO Toolkit bishwas-py/ai-seo-toolkit Provides eight SEO and AI-search workflows that run inside Claude and ChatGPT, covering Search Console auditing, traffic-drop diagnosis, keyword clustering, AI citation guidance, competitor gap analysis, content refresh, JSON-LD schema gene | |
| AutoCAD MCP bisingwaj/autocad-mcp Enables an AI assistant to conversationally control Autodesk AutoCAD, drawing, inspecting, and editing plans, and includes a cross-platform DXF engine that runs without AutoCAD on macOS and Linux. It exposes tools for rendering views as ima | |
| RAG Config Generator MCP bisma474/rag-config-generator-mcp Generates RAG pipeline configurations from natural language descriptions, providing recommendations for chunking, embeddings, and vector stores. | |
| youtube-mcp-server bismanwaz/-youtube-mcp-server Enables querying YouTube Data API v3 through natural language, providing access to trending videos, search, channel uploads, video details, and comments. |
34,351–34,400 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.