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 |
|---|---|
| eyd-v ardianryan/eyd-v Enables AI agents to look up official EYD Edisi Kelima spelling rules and check or correct Indonesian text for common errors such as nonstandard prepositions, particles, affixed forms, and punctuation through tool calls. | |
| mtik-mcp ardianryan/mikrotik-skill Enables AI assistants to audit, inspect, and safely configure MikroTik RouterOS v7 routers through tools for connection testing, system status, security audits, firewall mangle management, routing, DHCP leases, sanitized exports, containers | |
| vision-mcp arealicehole/vision-mcp Enables AI-powered vision analysis using local Ollama models. Supports screenshot analysis, OCR, text detection, and health monitoring via MCP protocol. | |
| IVR Flow Linter arebury/ivr-flow-linter Validates IVR flow definitions (JSON) to detect errors like unreachable nodes, dead ends, and missing fallbacks, providing scores and fix suggestions. Includes interactive visualization widget for ChatGPT and Claude Desktop integration. | |
| Axcel MCP aredamz/axcel-mcp Enables any MCP-compatible AI agent to generate videos and images from text or reference frames, chain scenes into seamless multi-scene films with sound and speech, and download finished media with manifests and previews. It also exposes ac | |
| @aredotna/mcp aredotna/mcp MCP server for the Are.na API, providing 40+ auto-generated tools and custom composite tools to interact with Are.na channels, blocks, and users. | |
| SuperBox Executor areebahmeddd/superbox-executor Remote MCP server executor on Cloudflare Workers that runs Python-based tools from GitHub repos via a lightweight TypeScript interpreter, supporting requests and common builtins. | |
| time-left-mcp-chatgpt areeburrehman-26/time-left-mcp-chatgpt Provides a single tool to display visual progress bars for time remaining in the current day, week, month, and year, enabling ChatGPT to answer 'how much time is left?' queries with elegant visualizations. | |
| MCP Docs Server areeshaasattar/ai-web-scraping-mcp Enables users to search and fetch documentation from supported libraries (langchain, llama-index, openai, uv) as clean, readable text, which can be used as context for answering questions. | |
| MCP-LOGO-GEN arekhalpern/mcp-logo-gen MCP Tool Server for Logo Generation.
This server provides logo generation capabilities using FAL AI, with tools for image generation, background removal, and image scaling. | |
| Flutter Inspector MCP Server arenukvern/mcp_flutter A Model Context Protocol server that connects Flutter apps with AI coding assistants like Cursor, Claude, and Cline, enabling AI-powered analysis of widget trees, navigation, and layout issues. | |
| serena areo-rgb/serena Provides IDE-like coding capabilities for AI agents via MCP, enabling semantic code retrieval, symbol-level editing, refactoring, and navigation across many programming languages. | |
| ModelsAgree arephan/modelsagree-mcp What ChatGPT, Claude, Gemini & Grok agree is the best product, tool, or service for any "best X for Y" need — continuously re-polled rankings with a dated verdict and a public poll audit trail. Excludes medical, financial, and legal advice. | |
| ares_onshape_local ares-23247/ares-onshape-local Enables agents to prepare, track and verify native editable Onshape CAD features through a signed-in browser session or your own API Explorer, while making zero outbound Onshape requests itself. It searches saved receipts, builds standard f | |
| IMAP MCP Server ares952/mcpgenericimap A read-only IMAP server for the Model Context Protocol that lets users list mailboxes, search messages, and retrieve messages and attachments through MCP. It exposes Streamable HTTP at /mcp with strict safety limits. | |
| designer-mcp aresbotv1-beep/designer-mcp A visual designer pen for Claude Code that lets users click, drag, or draw on webpages to get source code locations and screenshots for direct editing and verification. | |
| RE Data Refinery MCP Server areshms/re-refinery-mcp Turns messy real estate data into clean, scored, AI-ready property intelligence for Columbus, OH metro, with pay-per-query via x402 micropayments. Enables natural-language search, investment scoring, and enrichment tools for MCP clients. | |
| ChatGPT MCP Bridge aresqqqqq/chatgpt-mcp-bridge Enables ChatGPT to read and edit local project files, inspect Git changes, and run approved development scripts through a secure MCP tunnel, with optional Codex Desktop integration. | |
| flameox arezende52784/flameox Enables agents to gather bounded, reproducible runtime evidence by coordinating local profilers, benchmark tools, and trace processors against explicit artifacts or captured commands. It exposes typed analysis and capture operations over MC | |
| CC-Meta areznik23/cc-meta An MCP server that evaluates prompts using AI to provide detailed feedback on clarity, completeness, and effectiveness. | |
| docs-publisher arfzkwn-coder/docs-publisher-mcp Enables Claude to create, read, edit, list, and delete tutorials on Git-based documentation sites, upload images from public HTTPS links, and optionally trigger site redeploys directly through GitHub. | |
| BrowserHive arg1998/browserhive Enables AI agents to run isolated, stealthy browser sessions locally, with safe vault-based logins, human takeover, and replayable audit trails. | |
| arga-enfusion arga-reforger/arga_enfusion_mcp Enables AI agents to inspect Arma Reforger .pak archives and resolve resource GUIDs from resourceDatabase.rdb, supporting file discovery, regex search, content reading, extraction, and path/GUID lookups across game and mod sources. | |
| openapi-mcp arge2004/openapi-mcp Enables agents to query real-time OpenAPI documentation of backend services, providing tools to list services, endpoints, and schemas via MCP. | |
| Customer Health Intelligence MCP Server arghamza/mcp-server Provides deterministic mock customer health, product usage, and recommended playbook data via three MCP tools for a Customer Success Orchestrator demo. | |
| Linear MCP Server argia-andreas/linear-mcp-server A server that allows AI assistants to access and retrieve Linear ticket data through the Model Context Protocol (MCP) standard, currently focused on fetching a user's todo tickets. | |
| argmem-mcp argmem/mcp Enables LLM agents and MCP clients to build an argumentation-based memory store where grounded observations support claims, objections contest them, and beliefs are computed as held, contested, lapsed, or retracted, all persisted in an appe | |
| appium-mcp-server argneshu/appium-mcp-server Provides Appium mobile automation capabilities to Claude and other MCP-compatible clients, enabling cross-platform iOS and Android automation, element interaction, and session management. | |
| Agentic Mail Bridge argontechsolutions/agentic-mail-bridge Enables supervised reading, drafting, and sending of email across labeled Gmail, Google Workspace, and Purelymail accounts without a default sender, using explicit delivery authorizations and secure local credential storage. | |
| argocd-mcp argoproj-labs/mcp-for-argocd An implementation of Model Context Protocol (MCP) server for Argo CD. | |
| mcp-o11y argotdev/mcp-o11y An MCP server that demonstrates comprehensive observability with Sentry, OpenTelemetry, and Braintrust, providing tools for file, data, and HTTP operations along with real-time status and configuration resources. | |
| NHL MCP Server argotdev/nhl-mcp-python Provides access to live NHL game data, team and player statistics, standings, schedules, playoff information, and head-to-head comparisons through natural language queries using official NHL APIs. | |
| NHL MCP Server argotdev/nhl-mcp-ts Provides access to live NHL game data, player and team statistics, standings, schedules, playoff brackets, and historical comparisons through natural language queries using the official NHL API. | |
| Plaid MCP Server argotdev/plaid-mcp-python An MCP server for integrating with Plaid's API in sandbox mode, enabling linking bank accounts, fetching transactions, balances, and account information. | |
| Spotify MCP Server (Python) argotdev/spotify-mcp-py Enables interaction with Spotify through MCP, providing tools for searching tracks, artists, albums, playlists, and accessing user data like top tracks and recently played. | |
| tutor-mcp-python argotdev/tutor-mcp-python An AI tutoring system that runs as an MCP server, allowing Claude to access and interact with your local educational materials to provide personalized tutoring based on your actual course content. | |
| AI News MCP argusonline01/ai-news-mcp Local MCP server that ingests and normalizes recent AI, tech, and research news from multiple sources, exposing tools for media agents to query and retrieve article content on demand. | |
| synartesis-proxy arhaandev24/synartesis An MCP proxy that records every tool call, restores prior state on undo, and blocks irreversible actions until a human approves them. | |
| Second-Take arhamchoudhary-ui/second-take Simulates an Alexa+ booking assistant with MCP tools to preview, approve, change, and recover reservations, preventing duplicates and preserving user edits. | |
| actions-check arhancanli/actions-check-mcp Enables reviewing GitHub Actions workflows for outdated actions, deprecated Node runtimes, retired runners, deprecated commands, and security risks, with file, line, and fix for each finding. | |
| canli-fundamentals-mcp arhancanli/canli-fundamentals-mcp Enables AI assistants to look up SEC company fundamentals point in time: what a company first reported, what was known on any given date, and which values were later restated, with the filing behind each value. Supports querying history ove | |
| canli-mcp arhancanli/canli-mcp A full finance desk for your AI agent: 355 tools in one free server with no API key, reading SEC filings, earnings guidance, insider trades, options, rates and macro data from the source, plus quant analytics and backtest validation. The ag | |
| canli-research-mcp arhancanli/canli-research-mcp Enables AI assistants to search and read an open quant research record: papers, topics, killed candidates, trial counts, live paper-trading sleeves, and a tamper-evident chain head. It provides six read-only tools over public CDN files, ret | |
| canli-validation-mcp arhancanli/canli-validation-mcp Check a backtest before trusting it: deflated Sharpe, CSCV overfitting, minimum track record length, breadth ceiling and paper-evidence checks. Deflated Sharpe and track record are tested in CI against the papers' worked examples, CSCV agai | |
| citation-check arhancanli/citation-check-mcp Enables verifying citations in reference lists and BibTeX by detecting fabricated or mismatched references and retractions, and returning corrected BibTeX. | |
| Config Check arhancanli/config-check-mcp Enables agents to validate JSON, JSONC, YAML, and TOML configuration files against official SchemaStore schemas, pinpointing errors and likely key misspellings, and to look up schema-backed setting details. | |
| contact-check arhancanli/contact-check-mcp Enables agents to validate and normalize phone numbers, email addresses, and postal addresses with production-grade, country-specific rules, including formatting, typo detection, and checks for disposable domains or fictional numbers. | |
| cron-check arhancanli/cron-check-mcp Explains cron expressions in plain English, checks them for errors and gotchas, lists next run times in any time zone, and converts between Unix cron, GitHub Actions, Kubernetes, AWS EventBridge, Quartz and Spring dialects. | |
| Dockerfile Check arhancanli/dockerfile-check-mcp Enables agents to validate Dockerfiles for build-breaking syntax errors, risky patterns like root users and secrets in ENV/ARG, and cache-order problems, returning every finding with its line and a fix. It also verifies referenced container | |
| domain-health arhancanli/domain-health-mcp Provides comprehensive email deliverability and domain registration analysis, evaluating SPF, DKIM, DMARC, DNS records, and expiry to identify issues and suggest fixes. |
30,251–30,300 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.