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 |
|---|---|
| Figma Console MCP dexmachina-design/figma-console-mcp Model Context Protocol server that bridges design and development, giving AI assistants complete access to Figma for extraction, creation, debugging, and bidirectional token sync. | |
| AHME dexopt/ahme-mcp Provides AI coding assistants with long-term memory by compressing conversation history into a dense summary using a local Ollama model, fully local and free. | |
| Pump.fun MCP Server dexoryn/pumpfun-mcp-server Enables AI assistants to interact with the Pump.fun platform on Solana for creating, buying, and selling meme tokens. Provides comprehensive token management including balance checking, account management, and secure transaction handling. | |
| Volkern MCP Server dexpertmx/mcp-volkern Integrates Volkern CRM with AI agents to manage leads, schedule appointments, and handle tasks through natural language. It enables users to interact with CRM data, send WhatsApp messages, and track interactions directly within MCP-compatib | |
| Dexra Trader dexra-dev/template-hermes Enables trading tokens on Solana through Jupiter while Dexra's token and swap checks gate every buy, with sells never blocked and dry-run mode by default. Exposes token checks, preflights, fresh launches, buys and sells as tools that any MC | |
| FinCobra MCP dexstandard/fincobra-mcp Enables creating and tracking payment invoices and retrieving watchlist net-worth and source data via the FinCobra Checkout and Watchlist APIs. | |
| opendexter dexter-dao/opendexter-ide An MCP server that enables AI agents to search, pay for, and call paid APIs using the x402 protocol, with automatic USDC settlement. | |
| Weather MCP Server dexter-onboard/weather-mcp-server Enables MCP clients to retrieve active weather alerts for US states and five-period forecasts for US coordinates. | |
| Ollama Web Search dexterbed/ollama-web-search Enables web search and web fetch operations using Ollama's hosted APIs, allowing MCP clients to search the web and retrieve page content. | |
| Dev Research Assistant dextheking1/dev-research-assistant Enables an AI assistant to fetch and summarize public GitHub READMEs, inspect repository stats and open issues, and summarize pasted text through four MCP tools. | |
| adwhiz-mcp dexun-inc/adwhiz-mcp Enables MCP clients like Claude Desktop to query DEXUN AdWhiz for ad account lists, AI recommendations, savings summaries, recent activity, and API quota, all read-only. | |
| wohaoniu-zhitou-mcp dexun-inc/wohaoniu-zhitou-mcp Enables AI agents to use 我好牛AI智投 for checking brand visibility in Chinese AI chatbots and generating ad hooks and scripts directly in chat. | |
| OpenAlex MCP deyangliu123/openalex-mcp Enables scholarly search, paper metadata, citation graphs, author and venue resolution, candidate harvesting, API quota visibility, and guarded full-text downloads through the OpenAlex API. | |
| ContextWeave deyavinaba597-pixel/contextweave Universal project memory engine that extracts knowledge from code and git history, enabling AI assistants to query full project context via MCP. | |
| openwhispr-mcp dezer32/openwhispr-mcp MCP server that exposes OpenWhispr desktop app data—notes, folders, meeting transcripts, dictation history, and custom dictionary—to AI agents, with read and limited write operations. | |
| anythingllm-mcp dezgdny/anythingllm-mcp Enables AI assistants to search and ask questions about documents stored in AnythingLLM workspaces through MCP tools. | |
| quill-flowy dezgdny/quill-flowy Enables AI agents to read and write a self-hosted AppFlowy instance, decoding its Yjs CRDT pages into Markdown. | |
| nws-mcp dezinerdudes/nws-mcp Enables Claude and other MCP clients to read and manage a congregation's New World Scheduler data headlessly, covering people, schedules, assignments, territories, public witnessing, speaker sharing, NWP app publishing and backups. Every wr | |
| Security Intelligence MCP Server df4u1t/kb-mcp Provides a unified interface for security analysts to gather threat intelligence from multiple sources including VirusTotal, Shodan, NVD, AnyRun, AlienVault OTX, and GitHub. | |
| insta-pilot dfadify-web/insta-pilot Enables Claude to manage Instagram professional accounts through the official API: exporting account data, publishing reels, photos, carousels and stories, reading and replying to comments and DMs, and pulling analytics, plus a unified inbo | |
| BNCC MCP dfdb76/bncc-mcp MCP server that exposes skills from the Brazilian National Common Curricular Base (BNCC) with thematic units, knowledge objects, and prioritization layer from Mapa de Foco, enabling lookup, search, listing, and statistics of educational ski | |
| Gemini Image MCP dfeirstein/gemini-image-mcp An MCP server that enables AI image generation, editing, and analysis using Google's Gemini 3.0 models. It supports high-resolution outputs up to 4K, style transfers, and multi-image mixing through specialized tools. | |
| notebooklm dfelix-net/notebook-mcp Enables Claude to list/create research notebooks, add text or URL sources, ask source-grounded questions, and generate studio outputs such as podcasts, videos, slides, mind maps, quizzes, flashcards, reports, and data tables. | |
| chiclana-avisos-mcp dfernandezdaw/chiclana-avisos-mcp Enables an AI agent to file municipal incidents and street-damage reports with a GECOR-based town council, attaching a photo (extracting GPS from EXIF when present), previewing the exact summary for explicit human confirmation before anythi | |
| lcf-strain-life-mcp dfieser/lcf-strain-life Enables conversational low cycle fatigue analysis with standardized reduction, material constants fitting, and life predictions from strain-controlled test data. | |
| io.github.dfieser/thermocouple-its90 dfieser/thermocouple-its90 MCP server for NIST ITS-90 thermocouple conversions, providing tools to convert between temperature and emf for all eight thermocouple types with cold-junction compensation. | |
| dfine-semantic dfine-io/dfine-semantic-mcp Enables natural-language semantic search of a project's code through a local vector index, so questions that plain grep cannot match return ranked file:line references. It also indexes or refreshes projects on demand, reports index status, | |
| XTQuantAI dfkai/xtquantai An MCP server that integrates the XTQuant quantitative trading platform with AI assistants, allowing AI to directly access and operate on trading data and functionality. | |
| omada-mcp dfla-me/omada-mcp A Model Context Protocol server that enables AI assistants to read and safely modify TP-Link Omada networks through capability-gated tools, with a default read-only profile and dry-run writes for security. | |
| HopperPyMCP dflatline/hopperpymcp A FastMCP server plugin for the Hopper disassembler that enables AI assistants to analyze binary files, disassemble procedures, generate call graphs, search strings, and manage reverse engineering tasks. Provides comprehensive binary analys | |
| LINE Local MCP dfordennies/line-local-mcp Enables MCP-capable AI clients to search both sides of a user's own macOS LINE Desktop chat history — listing chats, reading messages, searching text, and pulling recent activity from local read-only database snapshots. It never sends messa | |
| KnowledgeBaseMCP dfoulks1/knowledgebasemcp An MCP server and CLI that checks, maintains, imports, and upgrades Open Knowledge Format bundles — directories of Markdown concepts with YAML frontmatter — reporting findings and applying mechanical repairs locally. It runs one contract fo | |
| recall-mcp dfrancislyondflabc-tech/recall-mcp Enables Claude to retrieve relevant memories from a folder of markdown files using hybrid search (BM25F, dense embeddings, phrase proximity) and to explicitly report when no strong match exists instead of guessing. | |
| MCP Weather Server dfrho/mcp-weather-server Provides real-time weather forecasts and active weather alerts for US locations using the National Weather Service API. It enables users to retrieve detailed local forecasts via coordinates and monitor state-specific weather warnings. | |
| finance-mcp dfrysinger/finance-mcp Local, privacy-first access to bank and credit-card transactions for Copilot, backed by SimpleFIN. | |
| salla-custom-code-mcp dfsf2151/salla-custom-code-mcp Enables reading, replacing, and toggling a Salla store's custom CSS and JavaScript through the theme editor's advanced customization endpoints, using a logged-in local Chromium profile with backups and verification. | |
| MCP Proxy Server dfuplugrwx/mcp-proxy-server Acts as a central hub that connects to and manages multiple backend Model Context Protocol servers, aggregating their tools and resources and exposing them through unified SSE, Streamable HTTP, or Stdio interfaces. It routes requests to the | |
| begemot-traffic-light dfvjgjgjg-commits/begemot-mcp Steers a coding model through a 0→10 step reasoning protocol by injecting a directive into the system prompt before inference, and hooks refusals to retry the request with a reframe and rotate to an open-weight model. Exposes tools, prompts | |
| Buttondown MCP Server dgalarza/buttondown-mcp Enables interaction with the Buttondown newsletter API for managing emails, subscribers, and tags. | |
| YNAB MCP Server dgalarza/ynab-mcp-dgalarza Enables AI assistants to help manage your You Need A Budget (YNAB) finances through comprehensive budget operations. Supports account management, transaction handling, category budgeting, split transactions, scheduled payments, and spending | |
| SageMaker AI MCP Server dgallitelli/sagemaker-ai-mcp-server Enables AI assistants to manage Amazon SageMaker AI resources including endpoints, jobs, pipelines, MLflow tracking servers, domains, models, model cards, and apps. | |
| Benchmark MCP Server dganesh5/claude-mcp-app An industry benchmarking tool that enables users to compare company metrics like revenue and profit against industry averages using interactive visual charts. It supports both Claude and ChatGPT across multiple transport protocols including | |
| Mock MCP Apps Server dganesh5/weather-mcp A local, no-auth MCP server that exposes mocked weather forecast and supported cities tools over Streamable HTTP, enabling developers to test MCP integration with hosts like ChatGPT, Claude, and MCP Inspector. | |
| DX Cluster MCP Server dgarcoe/dx_cluster_mcp Enables interaction with Ham Radio DX Cluster networks to read and create spots, analyze band activity, and track propagation trends through Claude Desktop. It features secure Auth0 authentication and supports various cluster types includin | |
| dd-explain dgb-tools/dd-explain-mcp Enables AI agents to explain DigiDollar transactions recorded on DigiByte, including mints, transfers, redemptions, amounts in cents, lock tiers, burns, and collateral releases, using bundled fixtures or an optional live explorer. | |
| dgb-attest-mcp dgb-tools/dgb-attest-mcp Enables on-chain attestation of any content onto the DigiByte blockchain, providing permanent, timestamped, tamper-evident proofs. Allows AI agents to notarize their outputs or verify attestations using only the blockchain. | |
| dgb-chain-mcp dgb-tools/dgb-chain-mcp MCP server that lets AI agents query live DigiByte blockchain data: network health, DigiDollar stats, oracle status, prices, address balances, transactions, and blocks. | |
| dgb-digidollar-mcp dgb-tools/dgb-digidollar-mcp Enables AI agents to pay for services in DigiByte/DigiDollar on testnet via the x402 pay-and-retry pattern, with spend limits and security policies. | |
| dgb-digiid-mcp dgb-tools/dgb-digiid-mcp Gives AI agents a verifiable identity using Digi-ID passwordless authentication on DigiByte, enabling them to prove who they are by signing challenges without revealing private keys. | |
| Mesh MCP dgdev25/mesh Mesh is an MCP server that lets Claude Code, Codex CLI, and Gemini CLI call other AI models for second opinions and multi-model workflows. It routes requests through local CLIs first, falling back to OpenRouter for any other model. |
44,251–44,300 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.