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 |
|---|---|
| Paceva owenscheuer/paceva-mcp Your swim, bike and run training: readiness, HRV, sleep, workouts and race predictions. Read-only. | |
| OwnerSpec ownerspec-com/mcp-server Cited home water treatment answers, part matching and sizing calculators for AI agents. | |
| China News Feed ownly-network/china-news-feed-mcp China news (EN/ZH), Weibo 微博/Baidu 百度/Zhihu 知乎 hot lists and deletion watch from public data. | |
| OwnMemory ownmemoryhq/ownmemory Encrypted memory for Claude, on a server you deploy to your own Cloudflare account. | |
| agentmem oxgeneral/agentmem Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file. | |
| Tolk MCP Server oxgeneral/tolk-mcp-server MCP server for the Tolk smart contract compiler. Compile, validate, and explore TON contracts. | |
| io.github.snowmead/oxcode oxgraph/oxcode PageRank-curated code intelligence for coding agents over an indexed source repository. | |
| Watchdog oxtof/watchdog-mcp Who can change a Solana program or EVM contract, dependency advisories, scans. Paid per call (x402). | |
| oxframe oxygenframe/oxframe-cli Make videos from code: check scenes frame by frame, inspect nodes, render a frame, search the docs. | |
| wyd oxyplay/wyd Local runtime provenance for coding agents. Inspect sessions and explain which one owns a process. | |
| Global Agent Memory ozankasikci/global-agent-memory Shared, project-aware memory for Claude Code, Codex, and other agents with human review. | |
| io.github.ozanmutlu/gitlab-docs ozanmutlu/gitlab-docs-mcp Search and browse 2,900+ official GitLab documentation pages via MCP | |
| io.github.ozten/cantrip ozten/mcp-server-cantrip MCP server for Cantrip — AI-powered GTM engine for solo founders | |
| irkumo ozumin-dev/irkumo-mcp IR page and earnings release list URLs for 3,821 Japanese listed companies by code or name | |
| scrapewright ozymandias-owens-2/scrapewright Give it a URL, get structured rows. A model writes the parser once; replays are free. | |
| Calendar.app p-l-ta/calendar-mcp List, search, and manage calendar events via macOS Calendar.app across all configured accounts. | |
| Mail.app p-l-ta/mail-mcp Search, read, send, and manage email via macOS Mail.app across all configured accounts. | |
| DJ Claude p-poss/dj-claude Agents can now live code music for you, themselves, and each other while they work. | |
| io.github.p1va/symbols p1va/symbols MCP server to read, inspect and troubleshoot codebase symbols | |
| io.github.p1xelapp/solana-nft-mcp p1xelapp/solana-nft-mcp Read-only Solana NFT data for AI: ownership history, custody rules, marketplace sales and floors. | |
| io.github.P2Flux/mcp p2flux/mcp Let your AI assistant pay for web content in USDC (x402) within a budget you set. | |
| mcp-audit p4st4s/mcp-audit Transparent Go proxy that intercepts, signs, rate-limits, redacts, and audits all MCP JSON-RPC tool calls without modifying client or server. Stores to JSONL or SQLite with HMAC-SHA256 signatures. | |
| GitHub PR Context paarths-collab/github-pr-context-mcp Retrieves GitHub PR history as context material; the connected IDE agent does the reasoning. | |
| io.github.paarths-collab/quant-brain-mcp paarths-collab/quant-brain-mcp Stock analysis MCP: 38 indicators, 7 optimizers, 8 backtests, US + India sectors. | |
| adx-mcp-server pab1it0/adx-mcp-server AI assistants to query and analyze Azure Data Explorer databases through standardized interfaces. | |
| Chess.com MCP Server pab1it0/chess-mcp Provides access to Chess.com player data, game records, and public information through standardized MCP interfaces, allowing AI assistants to search and analyze chess information. | |
| Tripadvisor MCP pab1it0/tripadvisor-mcp MCP server that enables LLMs to interact with Tripadvisor API, supporting location data, reviews, and photos through standardized MCP interfaces | |
| io.github.pablixnieto2/etld-mcp-server pablixnieto2/etld-mcp-server Deterministic B2B Data Middleware. Waterfall parsing for CSV, EDI, SEC & Finance. No hallucinations. | |
| io.github.pablo-albaladejo/kaiord pablo-albaladejo/kaiord Convert, validate, and inspect workout files (FIT, TCX, ZWO, Garmin Connect) for AI agents. | |
| AMR (antimicrobial resistance) pabloestepaa/amr-mcp Antimicrobial resistance genes, sequences and literature from NCBI and UniProt | |
| PacketExchange packetexchangeio/packetexchange-mcp SMS, voice calls, OTP verification, phone numbers and wholesale voice routes by Minutes Network. | |
| Packrift MCP packrift/packrift-mcp Find, size, price and order packaging: boxes, mailers, poly bags, tape. Live price and stock. | |
| io.github.packwarden-dev/packwarden packwarden-dev/packwarden Thunderstore mod search, dependency checks and r2modman export. Not affiliated with Thunderstore. | |
| Pact Tooling pact-community-organization/pact-mcp Pact 5 tooling: REPL test runs, trap scanning, gas estimation, interface diff, format checks. | |
| AgentPump pact-layer/agentpump-mcp Operate the AgentPump agent economy: read the market, create, fund, and run autonomous agents. | |
| pactlio-mcp pactlio-ai/pactlio-mcp Contract and wills legal tools for AI agents: statute-cited requirements per contract type and US state, non-compete enforceability for all 50 states + DC, intake schemas, async multi-agent contract drafting with free previews, and contract | |
| PageGuard MCP pageguard/pageguard-mcp Privacy compliance scanning for AI coding tools. Detects tracking tech, cookies, and data gaps. | |
| Pagelive pagelive/pagelive-mcp Publish pages straight from Claude as private, branded, tracked links. | |
| io.github.PagerDuty/pagerduty-mcp pagerduty/pagerduty-mcp-server PagerDuty's official MCP server which provides tools to interact with your PagerDuty account. | |
| pAIchart MCP Hub paichart/paichart MCP Hub: AI service discovery, per-user OAuth, and multi-service workflow orchestration | |
| PaidSync.ai paidsync/paidsync-mcp Run ads on Google, Meta, LinkedIn, TikTok and more from AI. 610+ tools across 14 platforms. | |
| tab paidwithtab/tab Agents pay per call over HTTP 402 and x402: 8,600+ API routes, signed budgets and receipts. | |
| io.github.paiml/pforge paiml/pforge Zero-boilerplate MCP server framework with declarative YAML configuration | |
| Web Page Fetcher paimonchan/paimon-mcp-fetch Fetch web pages with SSRF protection. Returns clean, readable markdown from any URL. | |
| io.github.pairbook-io/pairbook-mcp pairbook-io/pairbook-mcp Portfolio risk analysis, correlation and ETF overlap for 4,700+ US stocks and ETFs. Free, no key. | |
| Pairoa pairoa/docs Your AI meets theirs before you do — private matching for needs, offers, and opportunities over MCP. | |
| io.github.Pakvothe/i1n pakvothe/i1n-cli Agent-complete localization: extract strings, push keys, AI-translate, pull type-safe TS types. | |
| run.pay palabrex/runpay-mcp Stripe-native marketplace where AI agents discover and pay per call for API services. | |
| io.github.paladinfi/paladin-swap paladinfi/paladin-swap-mcp Multi-aggregator swap router for AI agents on Base. 10 bps fee. MCP-native, non-custodial. | |
| com.paladinfi/trust-check-mcp paladinfi/trust-check-mcp Free OFAC SDN wallet screen + sample preview for AI agents on Base. Read-only, no payment surface. |
14,351–14,400 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.