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 |
|---|---|
| PDF Manipulation MCP Server andr3medeiros/pdf-manipulation-mcp-server Enables comprehensive PDF operations including text/image manipulation, annotations, form fields, page merging/splitting/cropping, and metadata management using PyMuPDF. | |
| Dokploy MCP Server andradehenrique/dokploy-mcp Exposes Dokploy functionalities as tools consumable via the Model Context Protocol, allowing AI models and other applications to programmatically manage projects and applications on a Dokploy server. | |
| league-of-legends andraderaul/mcp-server-lol Provides real-time access to League of Legends esports data including live matches, schedules, leagues, event details, and VODs through a standardized interface. | |
| laya-mcp andragon3110/laya-mcp Enables coding agents to make confident decisions using calibrated probabilistic tools for screening, verification, ranking, classification, and gating, fully self-hosted as an optional MCP server. | |
| noteker andras-tkcs/noteker Converts handwritten PDF notes into clean Markdown using Claude Vision, with tools for PDF processing and status checks. | |
| EdgePilot andrasbogdanandrei/edgepilot An MCP server that lets AI agents automate Microsoft Edge, organizing sessions into labelled tab-group workspaces or separate profiles and providing tools for browser control, screenshots, extraction, and secure sign-in through Edge's passw | |
| genetic-mcp andrasfe/genetic-mcp Enables evolutionary idea generation using genetic algorithms with LLM workers, multi-objective fitness evaluation, and advanced genetic operations. | |
| remote-mcp-server-authless andrassama/remote-mcp-server-authless Deploys a stateless, authentication-free remote MCP server on Cloudflare Workers, enabling custom tool registration and seamless connection from clients like Cloudflare AI Playground or Claude Desktop via mcp-remote. | |
| Git MCP andre-buzeli/git-mcp Enables comprehensive Git and GitHub operations through 30 DevOps tools including repository management, file operations, workflows, and advanced Git features. Provides complete Git functionality without external dependencies for seamless i | |
| pg-mcp andre-c-andersen/pg-mcp A lightweight Postgres MCP server for safe database exploration and query analysis, read-only by default, with multi-database support. | |
| affinity-mcp-bridge andre-carbajal/affinity-mcp-bridge Bridges MCP clients to Affinity by Canva's local MCP server, exposing tools for script execution, rendering, and SDK documentation. | |
| Claude Fleet Monitor andre-motta/claude-fleet-monitor Enables Claude Code sessions to query fleet status, focus terminals, and manage sessions programmatically via MCP tools. | |
| Bitcoin Staking MCP andre-stacks/bitcoin-staking-mcp Enables agents to discover, understand, and plan native Bitcoin staking on Stacks through a read-only interface combining live PoX state, bond manifests, yield scenarios, security guidance, and compatibility checks. It includes a goal-first | |
| Threads MCP Server andre-wyap/threads-mcp Enables AI assistants to manage a Threads posting schedule through natural language, allowing them to view, add, update, reschedule, and skip posts in a local CSV schedule. | |
| TradingView MCP Bridge andre20356/tradingview-mcp Connects Claude Code to your locally running TradingView app via Chrome DevTools Protocol for AI-assisted chart analysis, Pine Script development, and workflow automation. | |
| PocketBase MCP Server andre22498/pocketbase-mcp Enables advanced database operations, schema and collection management, record CRUD, user authentication, and backups through the Model Context Protocol. It supports interacting with PocketBase databases via configurable tools. | |
| Perforce P4 MCP Server andre35304/p4mcp-server Enables MCP-compatible AI assistants to safely read and write Perforce P4 data—files, changelists, shelves, workspaces, jobs, code reviews, streams, and server metadata—through structured tools, with read-only mode by default and confirmati | |
| mcp-shodan andre3619/mcp-shodan Gives AI agents access to the Shodan API and Shodan CVEDB for internet reconnaissance, including host and port/banner details, TLS certificates, device search with facets, DNS and reverse DNS lookups, and CVE/CPE vulnerability intelligence | |
| ./README.md of https://github.com/Andre4983/serpapi-mcp andre4983/serpapi-mcp Integrates SerpApi so users can run real-time searches across Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and other engines from an MCP client. It returns structured results such as answer boxes, organic links, news, images, shopping lis | |
| Codex Control Plane MCP andrea055/codex-control-plane-mcp Turns Codex Desktop and codex-app-server into a durable async worker that MCP clients can drive by submitting tasks, receiving an operationId or workflowId immediately, and polling until the work finishes. It handles approvals, Plan Mode wo | |
| retention andrea13235/retention Enables AI agents to autonomously edit raw video footage into publish-ready videos with millisecond-accurate cuts, Whisper transcription, karaoke captions, motion graphics, and high-CTR thumbnails. | |
| Claude Patent Creator MCP Server andrea25790/claude-patent-creator Enables MCP-compatible clients to search MPEP/USC/CFR patent rules, perform prior-art searches across 100M+ patents via BigQuery, run 35 USC 112 compliance checks, and generate patent-style diagrams through programmatic tools. | |
| AKIMCP andrea35216/aki-mcp-sv Exposes an OAuth-gated suite of 38 tools that lets web-based AI clients read and edit files, run whitelisted shell commands, search content, use Git and SQLite, drive browsers and DevTools, and reach localhost or LAN services, clipboard, no | |
| slop-guard andrea52160/slop-guard Enables agents to analyze prose for formulaic AI writing patterns and return a 0–100 score, band label, violations with context, and concrete advice through its MCP tools. | |
| Niblet andrea6050/niblet-skill-mcp Gives coding agents real product-screen references, design materials, and recorded design references so UI work is grounded in actual surfaces rather than generic templates. It also serves the bundled design workflow, command playbooks, and | |
| lattice-mcp andreaaktas30888/matryoshka Enables analysis of documents far larger than an LLM's context window by letting the model issue constrained symbolic commands that execute server-side against in-memory handles, so only compact result stubs—rather than raw text—travel thro | |
| llm-file-operations-agent andreabcontarini/file_operations_agent Enables natural language file operations and intelligent file analysis via MCP, supporting CRUD actions and multi-step reasoning for directory management. | |
| mcp-anac-crawler andreac3p0/mcp-anac-crawler Enables searching, inspecting, and downloading Italian public tender notices from the ANAC Pubblicità Legale platform, supporting offset and cursor pagination, reference data lookup, and safe third-party document retrieval. | |
| Cover Letter MCP Server andreacadonna/cover-letter-mcp Generates professional PDF cover letters using LaTeX with advanced folder management capabilities. Integrates with Claude Desktop to create beautifully formatted cover letters with customizable organization by company, role, or industry. | |
| redmine-mcp andreacadonna/redmine-mcp Provides read-only MCP tools over stdio for interacting with a Redmine instance, enabling users to list and retrieve projects, issues, queries, wiki pages, and other Redmine resources via the REST API. | |
| Resume Generator MCP Server andreacadonna/resumake-mcp Generates professional PDF resumes using LaTeX templates through natural language descriptions. Supports 9 professional templates, AI-powered resume tailoring, and organized folder management for job applications. | |
| NALLAR MCP Server andreacentauri-sketch/nallar-mcp-server Provides read-only access to NALLAR engineering evidence and portfolio artifacts over MCP, exposing tools, resources, and prompts via stdio JSON-RPC. | |
| Hyros MCP Server andreacrowder/hyros-mcp Bridges Hyros attribution data to Claude via MCP tools, enabling real ROAS/revenue reconciliation by campaign and ad account. | |
| GABI MCP Server andreadecorte/gabi-mcp An MCP server that exposes GABI functionality, allowing users to run queries against a target endpoint with proper authentication. | |
| agid-llm-ui MCP Server andreaderuvo/agid-llm-ui MCP server to help AI assistants generate Italian PA user interfaces by providing components, recipes, accessibility rules, and validation for Bootstrap Italia and Web Components. | |
| banca-dati-merito-mcp andreadorizza/banca-dati-merito-mcp Enables AI assistants to search and read Italian civil decisions and their abstracts from the Ministry of Justice's Banca Dati di Merito using the user's own SPID, CIE, CNS or eIDAS session, which stays on the local machine. Read-only and r | |
| machine-mcp andreagriffiths11/machine-mcp Enables an AI agent to run local tools on the user's own machine via stdio, including command execution, workspace file read/write, and system status checks. | |
| InvoiceExpress MCP andreagroferreira/invoiceexpress-mcp Provides complete Portuguese invoice management with 60+ specialized tools including invoice creation, client management, SAF-T tax compliance, treasury operations, and Portuguese Tax Authority (AT) integration for AI-powered business autom | |
| code-analysis-context-python-mcp andreahaku/code-analysis-context-python-mcp A Model Context Protocol server for deep codebase understanding of Python projects, focusing on data analysis and scientific computing. It provides architectural analysis, pattern detection, dependency mapping, test coverage analysis, and A | |
| Expo iOS Development MCP Server andreahaku/expo_ios_development_mcp Enables LLM tools to control iOS Simulator, manage Expo/Metro development servers, capture screenshots and videos, stream logs, and execute UI automation tests via Detox for React Native/Expo applications. | |
| github-wiki-mcp andreahaku/github_wiki_mcp MCP server for managing GitHub wiki pages programmatically, enabling create, read, update, delete, and list operations via git cloning and pushing. | |
| GPT-5 MCP Server andreahaku/gpt5_mcp Brings OpenAI's GPT-5 capabilities to Claude Code with advanced reasoning, cost management, conversation handling, and automatic GPT-4 fallback. | |
| LLM Memory MCP Server andreahaku/llm_memory_mcp A local-first, team-ready MCP server providing durable memory for LLM-based coding workflows with multiple storage backends and fast search. | |
| expense-tracker andreajrubino/expense-tracker-mcp Enables natural language expense logging, parsing amounts, currencies, and dates, and storing entries in an Excel file. | |
| career-fit-assistant andreak3779/career-fit-assistant Enables AI assistants to run deterministic job-application workflows—fit-checking job descriptions, generating gap analyses, resumes, cover letters, LinkedIn/GitHub copy, and learning-plan PDFs—while refusing document generation when skill | |
| Discogs MCP andreakofman-ui/discogs-mcp-javi Enables AI assistants to search, browse, and update a user's music collection, wantlist, folders, ratings, and custom fields, plus retrieve collection statistics and recommendations through natural-language tools. | |
| Notion MCP Server andrealang7941/notion-mcp-server Enables AI agents and MCP-compatible clients to read and write Notion content—creating pages, querying databases, appending blocks, applying templates, commenting, and uploading files—using a token-based, headless setup. It exposes a compac | |
| piia-engram andrealang7941/piia-engram Gives MCP coding tools a shared, user-owned identity and long-term knowledge store — preferences, quality bar, lessons, decisions, and project context — read from local JSON/Markdown files instead of a cloud account. Users can inspect exact | |
| io.github.morluto/flameox andrealong58302/flameox Enables coding agents to coordinate local profilers, benchmark tools, trace processors, and direct targets, converting explicit artifacts or commands into bounded runtime evidence with provenance, coverage, limitations, and optional durable | |
| Kingdee MCP Server andreamaxwell27/kingdeemcp Enables AI assistants like Claude and Cursor to query and operate Kingdee Cloud Star ERP through natural language, covering purchasing, sales, inventory, production, cost, assets, and financial reporting with dozens of ready-made tools. |
28,601–28,650 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.