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 |
|---|---|
| Tidio MCP Server adrmrn/tidio-mcp Integrates the Tidio customer service platform with LLMs, enabling management of conversations, contacts, tickets, and operators through natural language. | |
| volc-aibot adrninistrator/volcengine_aibot_scripts Enables AI assistants to manage Volcengine AI outbound call scripts through natural language, including querying, importing, exporting, publishing, variable editing, and running text-based conversation tests. | |
| Web3 MCP adroamccullinp/web3-mcp Enables users to interact with multiple blockchains including Solana, Ethereum, Cardano, THORChain, XRP Ledger, TON, and UTXO chains through simple RPC endpoints for balances, transactions, swaps, and network queries. | |
| tracecat-mcp-community adrojis/tracecat-mcp-community Enables AI assistants to fully control a Tracecat SOAR platform instance through natural language, managing workflows, actions, cases, secrets, tables, schedules, graphs, and more. | |
| MCPWeather adry22/mcpweather Enables processing and handling of weather-related data requests through the Model Context Protocol, providing meteorological information via a configured MCP server. | |
| orca-cli-mcp adryanrr/orca-cli-mcp Lets MCP-capable AI agents drive Orca through its official CLI: creating git worktrees, launching coding agents like Claude or Codex, sending input to and reading terminal output, and tracking orchestration tasks and messages. It also expos | |
| NASA SciX MCP Server adsabs/scix-mcp Enables LLMs to search astronomical literature, retrieve paper metadata, analyze citation metrics, and export bibliographic data via the NASA Astrophysics Data System (SciX) API. | |
| mcp-server-contentgate adsandcode/contentgate Provides content guard checks as MCP tools, enabling an assistant to verify keyword coverage, translation drift, internal links, regulated claims, and sitemap lastmod while writing pages. | |
| MCP JSON Navigator adsdworld/mcp-json-navigator Enables efficient navigation and search of large JSON files (>10MB) through intelligent path exploration and fuzzy search capabilities, designed to save tokens by avoiding loading entire files into context. | |
| MemPalace JS adshaa/mempalacejs A local-first, zero-LLM memory system and MCP server that gives AI assistants a searchable, structured persistent memory using a spatial metaphor. | |
| Salla MCP Server adshaa/salla-mcp-server Bridges AI assistants to Salla e-commerce stores for natural language operations on products, orders, and analytics. | |
| YouTube MCP adshaa/youtube-mcp An MCP server that enables users to retrieve YouTube transcripts and perform video or channel searches without requiring Google API keys. It supports transcript chunking and provides tools for detailed video content analysis and channel met | |
| agentinbox-mcp adsman888/agentinbox-mcp Enables AI agents to manage a customer-support inbox with guardrails, including replying safely, handling escalations, and leveraging upsell opportunities for e-commerce stores. | |
| latam-market adsonpleal/latam-market Enables querying item prices, offers, and market analysis for the LATAM Ragnarok Online server (FREYA) via an MCP interface. | |
| claude-reviewer-for-codex adsorce/claude-reviewer-for-codex Uses Claude as an independent second-model reviewer inside Codex, performing reviews on disposable Git snapshots with structured findings. | |
| AdsPower LocalAPI MCP Server adspower/adspower-browser A Model Context Protocol server that enables LLMs to interact with AdsPower browser LocalAPI, allowing for operations like creating, opening, updating, and managing browser profiles with custom fingerprints. | |
| Adsroid MCP adsroid/adsroid-mcp Adsroid MCP connects Claude, ChatGPT, Cursor, or any MCP-compatible client directly to your advertising and marketing accounts, Google Ads, Meta Ads, Microsoft Ads, TikTok Ads, LinkedIn Ads, Google Search Console, Google Analytics 4, and Hu | |
| reflect-mcp adstastic/reflect-mcp Enables AI assistants to create notes, save links, append to daily notes, and manage knowledge graphs in Reflect via the Reflect Notes API, with OAuth2 authentication and token management. | |
| personal-mcp adta7/personal-mcp Enables agents to access a personal homepage's content graph through MCP tools, resources, and prompts, including retrieving profile, projects, resume, current status, searching content, and leaving messages. | |
| analytics-mcp adtechnacity/ga-mcp MCP server for querying Google Analytics accounts, properties, reports, and realtime data using the Data API and Admin API. | |
| flowindex adu3110/flowindex Enables AI coding agents to analyze codebase behavior through entrypoints, call paths, and tests, providing impact analysis and context packs for code changes. | |
| Time MCP Server adubovik/test-mcp-server Provides current time and timezone conversion using IANA timezone names, enabling LLMs to get system time or convert times between timezones. | |
| dejavu aduthekaddu/dejavu Provides a shared, repo-local memory that lets coding agents recall relevant decisions, conventions, gotchas, and open threads, save new entries, coordinate file claims, and cache file summaries across tools and sessions. | |
| Arbor advaitgore/arbor AgentPay is the authorization layer between an AI agent and real spending. You define the rules — spending caps, allowed merchants, time windows — and every purchase attempt the agent makes is checked against them in real time. Approved tra | |
| SQLGuard MCP advaith789/ast-level-sql-mcp Enforces safety and governance for SQL queries executed by AI agents, providing read-only enforcement, cost estimation, and audit trails. | |
| Firecrawl MCP Multiple Keys advaitr7/firecrawl-mcp-multiple-keys A Firecrawl MCP server with built-in support for multiple API key rotation, enabling web search, scraping, crawling, extraction, and more via MCP clients. | |
| Avanza MCP advance-xd/avanza-mcp Local Streamable HTTP MCP server for Avanza that provides authentication, account data, instruments, market data, and order tools. Order tools can affect real money, so requires approval and safe configuration. | |
| Placera MCP advance-xd/placera-mcp Read-only MCP server for accessing Placera headlines, articles, company tags, and Telegram search data. | |
| codeql-development-mcp-server advanced-security/codeql-development-mcp-server Enables AI-assisted development of CodeQL queries for security analysis through the Model Context Protocol. Provides tools for compiling, testing, and executing CodeQL queries across multiple programming languages. | |
| Salesforce MCP Server advancedcommunities/salesforce-mcp-server Enables AI assistants to interact with Salesforce organizations, allowing them to execute Apex code, query data, describe objects, and manage org connections through natural language. | |
| Google Calendar MCP Server advancednolik22-dev/google-calendar-mcp Enables AI assistants to manage Google Calendar events, check availability, handle recurring events, and coordinate across multiple accounts and calendars through natural language. | |
| n8n-mcp advancednolik22-dev/n8n-mcp Provides AI assistants with comprehensive access to n8n node documentation, properties, operations, templates, and workflow validation for building and managing n8n workflows. | |
| Telegram MCP Server advancednolik22-dev/telegram-mcp Lets you search personal messages and contacts, and send messages to individuals or groups through Claude. | |
| Catalog MCP Server advayc/procurement-agent Enables users to retrieve supplier catalog and price-history data, and to write comparison sheets through MCP tools. | |
| Conduit advenimus/conduit-desktop AI-powered connection manager with 60+ MCP tools for SSH terminal execution, RDP desktop control, VNC interaction, web session automation, and encrypted credential vault management. Works with Claude Code, Cursor, Windsurf, and any MCP-comp | |
| JW MCP Server advenimus/jw-mcp Provides access to JW.org content including Christian Life and Ministry workbook materials, Watchtower study articles, and video captions with subtitles across multiple languages. | |
| SyncroMSP MCP Server advenimus/syncromsp-mcp Enables AI assistants to fully access and manage SyncroMSP resources including tickets, customers, assets, invoices, and over 30 resource types through 180+ API endpoints. | |
| ligeia-mcp-server adventure1670-creator/cell001_day1 Enables AI agents to discover and invoke x402-monetized computational engines for media geometry, measurements, JSON hygiene, and ComfyUI preflight audits, with USDC settlement on Base Mainnet. | |
| @expertcustom/funilaria-mcp adventureandre/funilaria-mcp Enables AI assistants to interact with the Funilaria & Pintura portal through typed MCP tools, covering news publishing, supplier searches, stock and balance inquiries, and WhatsApp webhook operations. | |
| TopologicPy MCP Server adventurous-systems/topologicpy_mcp Enables LLMs to perform architectural spatial modeling through natural language, including creating, manipulating, and analyzing 3D building models using TopologicPy. | |
| Advernue MCP advernue/advernue-mcp Exposes the Advernue API's ~200 ad platforms as MCP tools, letting clients list campaigns, compare analytics, and crosspost or otherwise manage ads with dry-run-safe writes. | |
| AdvinPay MCP advinpay/advinpay-mcp MCP server to connect AI assistants to the AdvinPay payment API, enabling PIX charges, transaction queries, and documentation search. | |
| claude-workman advisoragi/claude-workman Enables MCP clients to control a Linux/X11 desktop like a human: see the screen, move the mouse, click UI elements via the accessibility tree, type text, and manage windows. | |
| Notion Query MCP Server advitrocks9/notion-query Provides structured, SQL-style query access to Notion databases, allowing Claude to filter, sort, and update pages through the Notion REST API. It enables advanced property-based filtering and database schema discovery beyond the capabiliti | |
| PSLRA Case Tracker advocentral/pslra-case-tracker-mcp Enables Claude to refresh and query a deduplicated record of newly filed US securities class actions, including lead plaintiff deadlines, class periods, announcing law firms, and matched federal court dockets. Supports filtering cases by de | |
| autor-texto-seguro advogadotuliosilveira/text-tool-mcp Enables secure text authoring and privacy-focused document processing through MCP. Provides tools for style analysis, conservative text revision, comparison with author samples, and removal of metadata from DOCX/PDF files. | |
| GPT MCP App - User & Loan Info Tools adw1029/gpt_mcp An MCP server hosted on AWS Lambda that provides tools for retrieving user profiles and loan details via API Gateway. It enables GPT models to interact with structured user and financial data using the Streamable HTTP transport. | |
| havenware-support-mcp adwaitasathe/privacy_aware_mcp_server Enables customer support agents to answer order-related queries with minimal data exposure, returning only necessary fields and sanitizing logs. | |
| hello-mcp adwaithsanthoshh/hello-mcp A minimal template for learning NitroStack with a calculator-focused MCP server and basic widgets. | |
| AdWeave Meta Ads adweave-ai/adweave-mcp Meta Ads MCP server with 47 tools for campaigns, creatives, audiences, and insights — plus AI-powered campaign diagnosis and buyer personas. |
24,001–24,050 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.