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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| OpenSERP openserpapi/mcp Search Google, Bing, Yandex, Baidu, DuckDuckGo and Ecosia with original ranks, plus page extraction. | |
| python-openstackmcp-server openstack-kr/python-openstackmcp-server Enables AI assistants to manage OpenStack cloud resources including compute, images, identity, network, and block storage via the Model Context Protocol. | |
| OpenSwitchboard openswitchboard-ai/server Your AI posts what you want or have. You are introduced anonymously to whoever has the other half. | |
| OpenTabs opentabs-dev/opentabs Open-source MCP server that gives AI agents access to 100+ web applications through the user's authenticated browser session. No API keys, no screenshots, no DOM scraping — talks directly to web app internal APIs via a Chrome extension. Sup | |
| io.opentweet/mcp opentweetio/mcp-server Manage your Twitter/X presence from any AI assistant — schedule, threads, and more | |
| io.github.OpenWeb-Ninja/openwebninja-mcp openweb-ninja/openwebninja-mcp Official MCP server for OpenWeb Ninja APIs - 40+ real-time web data and SERP APIs as MCP tools | |
| OpenZiti Network Management openziti/ziti-mcp-server Manage OpenZiti zero-trust networks — through natural language | |
| Private SuperIntelligence operatingsystem-1/private-superintelligence-agent Private SuperIntelligence by Mitosis Labs: define the term, see privacy layers, join the waitlist. | |
| OP.GG MCP Server opgginc/opgg-mcp A Model Context Protocol implementation that enables AI agents to retrieve game data from OP.GG for League of Legends, Teamfight Tactics, Valorant, and esports through function calling. | |
| Ophis ophis-fi/ophis Agent tools for the Ophis intent-based DEX: parse, quote, build, relay orders, look up fee tiers. | |
| dark-memory-mcp opita-code/dark-memory-mcp Persistent memory + vibe-loop engine for AI agents. Single Go binary, SQLite-backed, stdio MCP. | |
| io.github.opjhabuilds/designpin-mcp-server opjhabuilds/designpin-mcp-server Push HTML prototypes to DesignPin for team review and pull reviewer feedback into your AI. | |
| macbox opslane/macbox-agent A real Mac for your agent: build, test, run, and tap through iOS apps on the simulator. | |
| io.github.OpsMaxx/opsmaxx opsmaxx/opsmaxx-mcp SSH, files, containers and databases via the OpsMaxx desktop app - scoped per capability, audited. | |
| com.opsmill/infrahub-mcp opsmill/infrahub-mcp An MCP server connects your AI assistants to Infrahub using the open MCP standard. | |
| Claude Critical Rules MCP Server optimaquantum/claude-critical-rules-mcp Enforces 21 critical rules derived from 96+ documented failure patterns to prevent common AI assistant mistakes. Provides automatic compliance checklists, rule summaries, and auto-updates. | |
| OptimistFi optimistfi/optimistfi-mcp Perpetual futures across 40 venues, perps prop firms and sourced theses on 6,100+ US stocks. | |
| OptimToken optimnow/ai-pricing-hub-mcp Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget. | |
| Options Analysis Suite options-analysis-suite/options-analysis-suite-mcp Options analytics: 17 pricing models, 17 Greeks, GEX, IV, 23 screeners, unusual, dark pool, max pain | |
| Gmail Postmaster Tools optipub/gmail-postmaster-tools-mcp Gmail Postmaster Tools v2 — domains, traffic metrics, and compliance via your own Google OAuth. | |
| Outlook SNDS optipub/outlook-snds-mcp Outlook.com SNDS IP Data and IP Status reports via the OAuth-secured REST API. | |
| io.github.Optisol-Business/db-metadata-extractor-mcp optisol-business/db-metadata-extractor-mcp Extract database metadata from PostgreSQL, Snowflake, SQL Server, BigQuery, and Oracle. | |
| Optuna MCP Server optuna/optuna-mcp A Model Context Protocol server that enables automated optimization and analysis using Optuna, allowing LLMs to perform hyperparameter optimization and interactively analyze optimization results via chat interfaces. | |
| OpusClip opus-pro/opusclip-mcp Turn long videos into AI-curated short clips: caption, reframe, thumbnail, schedule, and publish. | |
| Gorilla MCP opusforge/gorilla-mcp This MCP helps you find your first 100 users on social media channels using Gorilla, a tool designed for founders by founders. | |
| Opus Growth opusgrowth/opus-growth-the-mcp-connector-for-ad-platforms Run Google, Meta, TikTok, LinkedIn and Microsoft Ads, GA4, Search Console and WordPress from your AI | |
| OrangePro orangeproai/orangepro-mcp Find test gaps, generate grounded tests, and dynamically prove behavior with mutation testing. | |
| Orangescrum MCP Server orangescrum/orangescrum-mcp-server Manage Orangescrum projects, tasks, users, sprints, test cases, releases, and risks from AI tools. | |
| io.github.Oratorian/discord-node-mcp oratorian/discord-node-mcp MCP server for controlling Discord servers via bot token | |
| Orbis API Marketplace orbisapi/orbis-mcp 8,000+ pay-per-call APIs via x402 USDC micropayments on Base. No API keys needed. | |
| io.github.OrderlyNetwork/orderly-mcp orderlynetwork/orderly-mcp MCP Server for Orderly Network - Documentation and SDK patterns | |
| Coda MCP Server orellazri/coda-mcp A Model Context Protocol server that enables AI assistants to interact with Coda documents, allowing operations like listing, creating, reading, updating, and duplicating pages. | |
| io.github.orenyomtov/maccabi-health orenyomtov/maccabi-health Read your own Maccabi Healthcare records: labs, prescriptions, visits, referrals, PDFs. | |
| PenlyDoc orestklymko/penlydoc-mcp Send documents for e-signature, track who signed and save sealed PDFs with PenlyDoc. | |
| droidprobe orhanbalci/droidprobe Read-only MCP server to inspect an Android device over ADB: hardware, packages, permissions, logs. | |
| YAML Workflow orieg/yaml-workflow Expose declarative YAML-defined workflows as MCP tools over stdio | |
| io.github.orifisher2/sqlike-mcp orifisher2/sqlike Lints SQL and checks rewrites return the same rows. Postgres, MySQL, MariaDB, SQLite, MSSQL, DuckDB | |
| FL Studio Agent origami-research/fl-studio-agent Drive FL Studio from an AI agent: write notes, set tempo and levels, check what sounds, render. | |
| Local Whisper orihuelaconde/local-whisper-mcp Private audio and video transcription with Whisper on your own computer, on the GPU or CPU. | |
| Orion Celestia Intel orioninfra/orion-agent-kit Celestia network intelligence for AI agents: daily analysis, anomaly signals and DA metrics. | |
| io.github.orionlabsai/agentum-mcp-server orionlabsai/agentum-mcp-server Dados globais reais (CNPJ, CEP, LEI, VAT, câmbio) via MCP, pagos em USDC por chamada (x402). | |
| io.github.OrionSmithers/agent-data-pro orionsmithers/agent-data-pro Research articles and live crypto prices for AI agents via x402 on Base. | |
| io.github.orlench/shouldigo-surf orlench/shouldigo-surf-mcp MCP server for Should I Go? — real-time surf conditions for 73+ beaches worldwide | |
| io.github.oro-intel/oro-intel-mcp oro-intel/oro-intel-mcp UK public procurement data for AI agents: tenders, contracts, buyer and supplier profiles. | |
| io.github.365xbusiness/vigo-mcp orphicone-platform/vigo-mcp AI-powered Hong Kong SFC regulatory intelligence. Bilingual EN/ZH compliance queries. | |
| Domain Security ortamarco/domain-security-mcp-server Audit a domain's email and web security: SPF, DKIM, DMARC, MTA-STS, DNSSEC, TLS, WHOIS. No API keys. | |
| Mexican Tax & Banking ortamarco/mx-fiscal-mcp-server Validate RFC, CURP, CLABE and NSS, read CFDI 4.0 invoices and check their SAT status. No keys. | |
| SEO & GEO ortamarco/seo-geo-mcp-server Audit a page's SEO and its readiness for AI answer engines: meta, schema, robots, sitemaps, AI bots. | |
| WHOOP (read-only) oryanomer1/whoop-mcp Read-only access to your WHOOP recovery, HRV, sleep, strain, workouts and trends. | |
| p6xer MCP Server osama-ata/p6xer-mcp-server An MCP server for Primavera P6 XER files. |
14,251–14,300 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.