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 |
|---|---|
| Semantic Scholar MCP Server denizo86/semantic-scholar-fastmcp-mcp-server Enables users to search and retrieve academic paper data, author profiles, citation networks, references, recommendations, and snippet excerpts, with batch operations and customizable field selection. | |
| LeetCode MCP Server denizolsson359/leetcode-mcp-server Enables automated access to LeetCode's problems, contests, solutions, and public or authenticated user data across leetcode.com and leetcode.cn, with search, daily challenge, submission, notes, and progress tools. | |
| Claude Patent Creator denizschroder43/claude-patent-creator Enables MCP-compatible clients to search patent rules and over 100 million patents, perform prior-art and 35 USC 112 compliance checks, and generate patent-style diagrams. | |
| loop-reader-mcp denizv/loop-reader-mcp A read-only MCP server that enables AI assistants to search and read Microsoft Loop content through the Microsoft Graph API, with per-user permission trimming ensuring each user only sees pages they already have access to. | |
| Insider Design System MCP denizzeybek-fe/design-system-mcp Automated MCP server for the Insider Design System. Enables AI assistants to discover, understand, and generate code for over 60 Design System components with automated extraction from source code. | |
| Baton MCP Server denki-san/baton Enables a personal AI agent to exchange structured relay messages with another person's agent, check inboxes and history, manage pairs and invites, and coordinate free times while requiring each owner to confirm settlements. | |
| Funnel Calibrator denkor1015-debug/funnel-calibrator Enables agents to measure product-specific funnel rates from historical order data, recalibrate cost-per-lead bounds, and audit proposed advertising decisions against corrected figures. | |
| hh-radar denmurzik/hh-radar Enables LLM agents to query and analyze hh.ru job vacancies via full-text and semantic search, with tools for vacancy lookup, skill statistics, market overview, and candidate profile comparison. | |
| Oracle Context MCP Server dennesssy/oci-context-mcp Provides AI agents with secure, natural-language access to Oracle Cloud Infrastructure through 69 tools covering services like compute, storage, networking, and databases. It features deep IAM integration and supports deployment across plat | |
| memex dennis60331/memex Enables AI coding agents to save and recall atomic markdown knowledge cards connected by bidirectional links, giving them persistent memory that carries insights across sessions instead of starting from scratch. Works with Claude Code, Curs | |
| synauth-mcp dennischoubot-glitch/synauth-mcp Biometric authorization for AI agent actions via Face ID on iPhone, enabling secure approval of sensitive actions and credential-safe API calls through vault execution. | |
| ltm dennisdevulder/ltm Portable memory protocol for AI coding sessions. Push the state of a session (goal, decisions, attempts, next step) from one MCP-capable agent and pull it back from another. | |
| efood-mcp dennisdgr/efood-mcp An unofficial Model Context Protocol server for the efood.gr consumer app API that lets you discover restaurants, browse menus, build a cart, and place real orders on efood.gr. | |
| arxiv-latex-mcp dennisferreira59598/arxiv-latex-mcp Enables MCP clients such as Claude Desktop, Claude Code, and Cursor to access and process arXiv papers by fetching their LaTeX sources for accurate interpretation of mathematical expressions. It provides tools to retrieve a paper's full fla | |
| clinicaltrialsgov-mcp-server dennisferreira59598/clinicaltrialsgov-mcp-server Enables searching ClinicalTrials.gov studies, fetching full protocol records, posted results, and field definitions, and matching patient profiles to candidate recruiting trials through MCP. Runs over STDIO or Streamable HTTP with no API ke | |
| neobrutalism-mcp-server dennisimoo/neobrutalism-mcp-server Provides AI assistants with access to neobrutalism-styled React components, enabling them to generate UI code and prototypes using components like buttons, cards, dialogs, and star decorations. | |
| Agentdocs dennisjaved/python-mcp-server-client Enables querying and retrieving current technical documentation for major agent frameworks such as LangChain, LlamaIndex, AutoGen, Agno, OpenAI Agents SDK, MCP docs, Camel-AI, and CrewAI via stdio or SSE. | |
| MS 365-21V MCP Server dennisjimenez75407/ms-365-21v-mcp-server Enables MCP-capable AI clients to use a 21Vianet Microsoft 365 tenant on the user's behalf, including querying mail, managing calendars, and searching OneDrive and SharePoint through Microsoft Graph China. | |
| dndbeyond-mcp denniskonrad/dndbeyond-mcp Enables AI assistants to manage D&D Beyond characters, access campaigns, and look up spells, monsters, items, and more through a reverse-engineered API. | |
| ReActMCP Web Search dennislefebvre31297/reactmcp Enables AI assistants to perform basic and advanced real-time web searches through the Exa API, with domain, required-text, and date filters, returning Markdown-formatted titles, URLs, publication dates, and content summaries. | |
| Coding Todo Server dennismartis/mcp-todo An MCP server that provides tools and resources for managing a coding project's todo list, allowing users to view, add, update, and delete todo items with details like priority, status, and tags. | |
| MCP SQL Server dennismartis/sql_mcp_server A FastMCP server that provides natural language interaction with MS SQL databases, enabling users to query data, list tables, describe structures, and execute database operations through a conversational AI interface. | |
| BuchhaltungsButler MCP-Server dennismenken/buchhaltungsbutler-mcp Connects an AI assistant to a BuchhaltungsButler tenant through 59 German-language tools — 54 endpoint tools (one per API v1 endpoint) plus 5 bundle tools — covering documents, payments, invoices, postings, master data, cost centers, and re | |
| MCP Anvil Tools dennisonbertram/mcp-anvil-tools Enables AI agents to interact with Ethereum smart contracts through Anvil, providing capabilities to read Solidity code, simulate and execute transactions, manipulate blockchain state, query events, and test contracts in isolated environmen | |
| Box MCP Server dennisonbertram/mcp-box Enables Large Language Models to securely interact with Box cloud storage, including file upload, retrieval, search, and AI-powered analysis, without storing files locally. | |
| Brex MCP Server dennisonbertram/mcp-brex Enables interaction with Brex financial data including expenses, budgets, transactions, and accounts through read-only API access with support for pagination, filtering, and receipt management. | |
| MCP Ethers Server dennisonbertram/mcp-ethers-v6 A complete ethers.js v6 wrapper for Claude with 40+ tools for Ethereum blockchain interactions, enabling wallet operations, token transfers, and smart contract calls. | |
| MCP Etherscan Server dennisonbertram/mcp-etherscan-server An MCP server providing comprehensive access to Ethereum blockchain data across 72+ networks via Etherscan's V2 API. It enables users to check balances, track transactions, analyze smart contracts, and monitor gas prices through natural lan | |
| Hats Protocol MCP Server dennisonbertram/mcp-hats Enables management of decentralized organizational roles and permissions through Hats Protocol across multiple blockchain networks. Supports creating hierarchical role structures, checking permissions, minting/transferring roles, and analyz | |
| MCP Ledger Server dennisonbertram/mcp-ledger A comprehensive MCP server for secure Ledger hardware wallet integration with Ethereum blockchain operations, enabling AI agents to safely manage crypto assets, sign transactions, and interact with multiple networks. | |
| Rotki MCP Server dennisonbertram/mcp-rotki Integrates with Rotki portfolio tracker to provide portfolio overview, prices, transaction history, and analytics through intuitive tools for AI assistants. | |
| Safe MCP Server dennisonbertram/mcp-safe Enable AI agents to manage Safe multisig wallets across multiple blockchains. | |
| MCP Tally API dennisonbertram/mcp-tally-api An MCP server that enables LLMs to query DAOs, proposals, and voting data from Tally's blockchain governance API across multiple networks. | |
| Web3 Stats Enhanced - Dune + Blockscout MCP Server dennisonbertram/mcp-web3-stats This project implements a Model Context Protocol (MCP) server that combines the power of Dune Analytics and Blockscout APIs, providing comprehensive blockchain data analysis capabilities for LLM agents and MCP clients. | |
| slac-mcp dennisprediger/slac-mcp MCP server exposing SLAC (Simple Logic & Arithmetic Compiler) as tools for LLM agents, enabling evaluation of expressions and retrieval of syntax reference. | |
| Elevate dennisrepa/elevate Enables autonomous AI agents and CI/CD runners to discover repository modules, scan outdated dependencies, fetch version histories, and apply verified dependency updates with major-version safety guardrails across polyglot monorepos. | |
| Vectorize MCP Server dennisvisser4544/vectorize-mcp-server Enables vector search and document retrieval, extraction and chunking of files into Markdown, and generation of private deep research reports from configured pipelines. | |
| coin-scout dennisyilmaz/coin-scout Enables AI agents to perform read-only Solana on-chain financial analysis and fraud investigation through Helius, including wallet and token risk screening, multi-hop fund tracing across bridges, wallet clustering, PnL reconstruction, and p | |
| Foundry Agents MCP Server denniszielke/foundry-agents-mcp-server Exposes Azure AI Foundry agents, workflows, and AI Search vector-database capabilities as MCP tools, enabling natural language interaction with agents, semantic search, and index management. | |
| wissens-enablement-agent denny98-lab/wissens-enablement-agent Enables AI assistants to securely search and list internal company documents via MCP tools, so they can answer employee questions based on current internal documentation. | |
| Date Operations MCP dennypradipta/date-operations-mcp Enables date and time operations including formatting, arithmetic, comparisons, and duration calculations using date-fns library. Provides tools for getting current time, adding/subtracting durations, finding differences between dates, and | |
| DiviDen MCP Server denominator-ventures/dividen Open coordination network for AI agents and their humans. 13 tools for structured coordination, job marketplace, reputation system. Dual-protocol: MCP + A2A. MIT licensed. | |
| m365-organizer denovarix/denovarix-m365-organizer Enables organizing a personal Microsoft account from an MCP client, including Outlook folder trees, sender statistics, bulk moves, inbox rules, and OneDrive folders via Microsoft Graph. | |
| agent-reach-web-mcp denpadokei/agent-reach-web-mcp Enables web search and page reading through MCP tools, returning structured search results and clean markdown page content with a unified result envelope. | |
| play-console-mcp denshinji/play-console-mcp Enables AI agents to manage Google Play store listings, icons, feature graphics, screenshots, app bundle releases, and user reviews, staging every change in a Play edit that stays unpublished until it is explicitly committed. Safety guards | |
| fuga-memory densuke/fuga-memory An MCP server providing long-term memory for LLMs via hybrid search (FTS5 + vector) stored in SQLite, with time-decay scoring and support for multiple AI assistants. | |
| lynceus-mcp densul/lynceus-mcp Enables AI agents to run RU-first web searches through the Yandex index and extract web pages into clean reader-mode Markdown, bypassing anti-bot blocks. | |
| Spokes dente22/spokes Local MCP memory of your GitHub repos for Cursor | |
| Finnhub MCP Server denusenko/ai-eng-mcp-demo Connects Claude Desktop to real-time stock market data via Finnhub API, enabling company profiles, stock quotes, market news, and a customizable watchlist. | |
| SQL Generative MCP denuwanhh/sql-generative-mcp Enables natural language querying of PostgreSQL databases under read-only mode, returning results as structured XML. |
43,651–43,700 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.