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 |
|---|---|
| io.github.platformtaxhub-hash/platformtaxhub-mcp platformtaxhub-hash/platformtaxhub-mcp Free platform-income calculators (take-home pay, payout calendar, benefits) as MCP tools. | |
| PCQ playidea-lab/pcq Python library for agent-operable experiment evidence and control. Bring any training code | |
| Steam MCP playtide-studios/steam-mcp Steam market intelligence MCP server for game developers: app search, trends, reviews, news. | |
| PLCs.ai plcsai/plcs-ai-mcp Query Allen-Bradley and Siemens PLC projects, live tag values, and analyses in plain English. | |
| com.getplexa/mcp plexa-xyz/mcp Economic-safety tools for trading agents: executable quote + rug/honeypot pretrade check via x402. | |
| io.github.plopez053/ayudas-es plopez053/ayudas-es-mcp Ayudas y subvenciones de España (BDNS) y BOE en directo: recuentos, plazos y calendario previsto. | |
| SanAlert plrojek/sanalert-mcp Unofficial threat level from the air for a place in Poland, worked out on your own computer. | |
| Plug and Ship plugandship/plugandship-mcp Search MCP servers, agent skills and coding-agent plugins: trending tools and best-of lists. | |
| Plugolis plugolis/plugolis-mcp Search the Plugolis directory of MCP servers and step-by-step fixes for common MCP errors. | |
| PlugRail Japanese Calendar plugrail/servers Japanese holiday and business-day calculations using official Japan Cabinet Office data. | |
| Plumb plumbkit/plumb LSP-backed IDE intelligence plus concurrency-safe, transactional edits for AI coding agents. | |
| io.github.plur-ai/plur plur-ai/plur Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP. | |
| PineLabs Plural PG — Payment Gateway MCP Server plural-pinelabs/pinelabs-online-mcp Create payment orders, checkout, subscriptions & UPI via PineLabs Plural PG gateway | |
| Threadminder pluralityworks/threadminder-mcp Persistent context for Claude. Your AI always knows your projects and next actions across sessions. | |
| io.github.plus8bit/deadchannel plus8bit/deadchannel Check an x402 endpoint before you pay it: verdict, risk score and what is wrong. $0.005 in USDC. | |
| io.github.plyo-dev/plyo-mcp plyo-dev/plyo-mcp Save, publish, restore and back up AI-built projects on Plyo, for people who build with AI. | |
| Forge — Agent Reputation Protocol pm577/forge-mcp Portable reputation for AI agents. MCP-native identity, vouching, trust scores. | |
| GPU MCP Server pmady/gpu-mcp-server NVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG. | |
| io.github.pmgarg/cgraphy pmgarg/cgraphy Code knowledge graph over MCP: token-budgeted context for AI coding agents. | |
| Deep Research MCP pminervini/deep-research-mcp A Python-based agent that integrates research providers (OpenAI, Gemini, DR-Tulu, Open Deep Research) with Claude Code via the Model Context Protocol for automated deep research. | |
| pmpt-mcp pmptwiki/pmpt-cli MCP server for pmptwiki — auto-saves project milestones with summaries, manages version history, and publishes AI-driven projects to pmptwiki.com community platform. | |
| PnL Labs — Solana Trust & Risk Checks pnllabs/pnllabs-mcp Trust checks for Solana trading: realized-PnL wallet trust, token safety, trade cost, forensics. | |
| io.github.pnp/cli-microsoft365-mcp-server pnp/cli-microsoft365-mcp-server MCP server for CLI for Microsoft 365 to manage your tenant using natural language | |
| PnP PowerShell pnp/pnp-powershell-mcp-server Manage Microsoft 365 in natural language with PnP PowerShell and author PnP PowerShell scripts. | |
| thread-keeper po4erk91/thread-keeper Multi-agent shared brain across Claude, Codex, Antigravity, Gemini, Copilot, and VS Code. | |
| PocketBase Cloud pocketbasecloud/mcp Manage PocketBase Cloud projects, instances, deploys, domains, collections and records. | |
| io.github.pocketlantern/pocketlantern pocketlantern/pocketlantern Blocker-aware decision layer for AI coding agents, grounded in source-linked, time-sensitive facts. | |
| Shotpipe — Screenshots & OG Images podop29/shotpipe-mcp Screenshot any URL and see it, or mint a social card — hosted, SSRF-safe, cached. No Chrome to run. | |
| POEditor poeditor/poeditor-mcp Official MCP server for POEditor, the translation management system. Hosted, OAuth 2.1. | |
| Pokémon TCG API pokemontcgapi/mcp-server English, Japanese and Chinese Pokémon cards: search, sets, illustrators, prices, photo lookup. | |
| Pokerai API pokerai-bet/mcp Solver-grade GTO strategy for study. Real-time assistance (RTA) at real-money tables is prohibited. | |
| Pocket Network Agentic Marketplace pokt-network/agentic-portal-mcp Search and call pay-per-request data services, paying in USDC on Base with x402. | |
| agent-mailbox — Mailbox and Wake System for AI Agent Teams polaris-smart/agent-mailbox Mailbox + wake system for AI agent teams: letters always land, right agent wakes, quiet otherwise. | |
| GSC Scanner poliakarmai/gsc Local security scanner for AI agents: SAST, SCA, secrets, IaC; verifies exploit and fix. | |
| Recall polign/recall Agent memory that keeps every correction, with history and as-of reads. Runs on your database. | |
| CustomGPT MCP Server poll-the-people/customgpt-mcp A full-featured MCP server providing seamless access to CustomGPT.ai APIs, enabling agent and conversation management through MCP-compatible clients. | |
| io.github.Pollamin/opendock pollamin/opendock-mcp MCP for the Opendock Neutron API. | |
| polsolbridge/solana-swap-api Non-custodial crypto swaps for AI agents: Solana (Jupiter) + 7
EVM chains (KyberSwap), 1288+ assets, cross-chain routing,
priority-fee oracle, Hyperliquid perps. Returns unsigned
transactions — your wallet signs, no API key, no KYC. Hosted
| |
| Magic Cloud polterguy/magic Generate secured CRUD APIs over your database, run SQL, manage files, tasks and a headless browser | |
| io.github.backspacevenkat/perspectives polydev-ai/perspectives-mcp Query GPT 5.2, Claude Opus 4.5, Gemini 3, Grok 4.1 simultaneously for AI perspectives | |
| io.github.polydev-ai/polydev polydev-ai/polydev Query GPT-5, Claude, Gemini, and Grok simultaneously through one MCP server | |
| PolyDoc polydoc-tech/polydoc-mcp HTML/URL to PDF, screenshots, e-invoices. PDF/A and PDF/UA output with optional veraPDF verify. | |
| io.github.polygraphso/litmus polygraphso/litmus Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only. | |
| PMWallets polymarketwallets/pmwallets-node Polymarket smart-money data: rank traders by on-chain PnL, follow them, read their fills. | |
| dibs polymatx/dibs Coordination for parallel coding agents: TTL file claims stored in the git common dir (visible across all worktrees), enforcement hooks that block colliding edits, agent presence, handoff notes, and a git-committed lessons knowledge base wi | |
| Polyrama polyrama/mcp Research Polymarket and Kalshi markets, traders, signals, backtests, and paper orders. | |
| dev.txn/mcp-server polyxmedia/txn-dev-mcp-server Wallets, payments and human hiring for AI agents: pay other agents, escrow a budget, hire a person. | |
| Span pontivus-com/span Codebase understanding with exact evidence, qualified on every read and re-aligned on change. | |
| io.github.PonzuTech/ponzu ponzutech/ponzu_mcp ERC-20 token launchpad on Ethereum — deploy, presale, swap, and farm via AI agents | |
| Poof poof-bg/mcp Remove backgrounds from images, videos and animated GIFs: transparent cutouts, mattes, GIF stickers. |
16,551–16,600 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.