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 |
|---|---|
| dbv-pdf2md davidbuenov/dbv-pdf2md MCP server that converts PDFs to Markdown, reconstructing hidden hyperlinks and extracting images in reading order for AI agents. | |
| obsidian-mcp davidburckhardt/obsidian-mcp MCP server that gives AI assistants access to an Obsidian vault, enabling folder navigation and note creation, reading, editing, moving, renaming, and deletion. | |
| kungfu-mcp davidcai/kungfu-mcp A humorous MCP server that catalogs martial-arts factions and narrates sparring matches between them. | |
| Case Study Generator MCP Server davidcaraman/custom-client-case-study-mcp Processes documents, analyzes GitHub repositories, and researches companies using local Gemma3 AI to extract structured business insights for generating compelling case studies. | |
| AE-MCP davidcasan/mcp-ae An MCP server that enables AI assistants to control Adobe After Effects with 70+ tools for compositing, animation, effects, and motion graphics. | |
| AE-MCP davidcasan/mcp-ae2 Automate Adobe After Effects with AI through 70+ MCP tools. | |
| dsh-google-chrome-search davidcastilloalvarado/dsh-google-chrome-search Enables AI agents to perform real Google web searches and render web pages for content extraction using a local Chrome browser, with human-in-the-loop CAPTCHA verification, requiring no API keys. | |
| mcp-geoes davidcervigonluna/ign-igme-mcp Enables AI agents to query Spanish geology and cartography from IGME and IGN, composing aligned maps with combined legends and provenance. | |
| Revit MCP Server davidchin0/revit-mcp-stdio MCP server for Autodesk Revit 2024/2025/2026/2027 via pyRevit — 48 tools for building design, editing, analysis, clash detection, MEP, interop, documentation, and model persistence. | |
| Canadian Building Code MCP Server davidcho1999/canada_building_code_mcp Enables users to search and navigate over 22,500 indexed sections across 16 Canadian building codes and user guides. It supports keyword searches, hierarchy navigation, and optional full-text extraction from user-provided PDF documents. | |
| cleat-mcp davidcleat/cleat-mcp Enables an assistant to read SMS texts and transcribed calls on a Cleat US mobile line, including waiting for the next verification code to arrive. | |
| CVE MCP Server davidculver/cve-mcp-server Provides conversational access to a local CVE (Common Vulnerabilities and Exposures) database, enabling natural language queries to search vulnerabilities, retrieve detailed CVE information, and view security statistics. | |
| fhir-ig-rag davidcumming/fhir-ig-rag Provides FHIR Implementation Guide facts via MCP tools, enabling querying of must-support, bindings, constraints, and value-set usage from StructureDefinition artifacts for conformance and testing support. | |
| DB MCP (HR CSV to SQLite) daviddata-cloud/mcp_db An open-source MCP server that imports HR CSV data into an in-memory SQLite database for structured querying and metadata retrieval. It enables users to perform read-only SQL queries and structured searches on employee data through natural | |
| DB MCP (HR CSV → SQLite) daviddata-cloud/mcp_doc This MCP server imports HR CSV data into an in-memory SQLite database to enable structured querying and metadata retrieval. It provides tools for executing read-only SQL queries and searching employee records through a standardized JSON-RPC | |
| TradePoli MCP daviddme/capitol-alpha-terminal Enables querying U.S. politician stock trades from public disclosures, running backtests, and generating daily briefings via MCP tools. | |
| TradingView Alerts MCP Server daviddme/tradingview-alerts-mcp-server Enables programmatic management of TradingView alerts via MCP, including creating, listing, pausing, resuming, and deleting alerts with optional webhooks and bulk operations. Authenticates using session cookies and works with strategy alert | |
| TradingView Unified MCP daviddme/tradingview-unified-mcp Enables an MCP client to drive a local Chrome, Chromium, or Edge browser session to read and modify TradingView charts — saved layouts, alerts, Pine scripts, Strategy Tester reports, OHLCV and quote data, watchlists, drawings, replay, plus | |
| Construction Reference MCP Remote Server daviddominguez-11/construction-reference-mcp-remote Enables users to look up reference information for construction materials, including price ranges and aliases, for small projects in Guatemala through a remote MCP endpoint. | |
| construction-supervision-mcp daviddominguez-11/construction-supervision-mcp Provides construction-supervision tools for small-to-medium building projects, including stage guidance, inspection checklists, progress tracking, next-stage recommendations, and quotation analysis. It enables local, standards-based MCP int | |
| MCP Server daviddraiumbrella/invoice-monitoring Provides read-only access to Umbrella Cost finops platform, enabling natural language querying of multi-cloud cost data, optimization recommendations, anomaly detection, and budget tracking across AWS, Azure, and GCP. | |
| Tagging MCP daviddrummond95/tagging_mcp Enables parallel tagging and classification of CSV data using multiple LLM providers with structured output, confidence scores, and optional reasoning for batch classification tasks. | |
| seomcp davide-cik/seomcp Enables Claude and other MCP clients to read Google Search Console and Bing Webmaster Tools data, analyze query/page performance, compare periods, inspect indexing and canonical status, and retrieve sitemap and keyword statistics. | |
| knowledge-base-server davide7690/knowledge-base-server Gives AI agents a shared persistent memory by ingesting Obsidian vaults, code, transcripts, web clips, and session or bug-fix captures, then serving token-optimized context briefings, keyword and semantic search, and cross-source synthesis. | |
| Claude Telegram Supercharged davideburke/claude-telegram-supercharged Enables running Claude Code around the clock from Telegram with two-way voice messages, persistent memory, live tool-call progress, permission approvals, scheduling, and a self-healing daemon. | |
| Ponte davideconte/ponte Enables coding agents on different machines to exchange end-to-end encrypted messages through a shared, self-hosted relay, exposing inboxes, room history, and notifications to Claude Code, Codex, or any MCP client. Peers' messages arrive au | |
| mcp-mongodb davidedantonio/mcp-mongodb Enables LLM clients to query MongoDB collections read-only through a small set of guarded operations, exposing only declared fields and enforcing scoped filters, projections, and limits. | |
| tmux-bridge-mcp davideguo8194/tmux-bridge-mcp Enables AI coding agents running in separate tmux panes to see each other's output, send tasks and messages across panes, and coordinate multi-agent workflows through standard MCP tool calls. It talks to tmux directly, so Claude Code, Codex | |
| LINE OA MCP Ultimate davidekose97/line-oa-mcp-ultimate Enables AI agents to run one or many LINE Official Accounts through natural language — sending broadcasts, Flex, Rich, and coupon messages, managing rich menus, audiences, coupons, webhooks, insights, and LINE Shopping operations. Includes | |
| KaaS davideleclerc3767/kaas Enables MCP-capable coding agents to query a self-hosted, LLM-compiled Markdown knowledge base through a single ask tool that answers from whole wiki articles and returns citations back to the source pages. Supports both local stdio and rem | |
| local_ai_gen davidemodolo/local-asset-gen-mcp Local AI generation for images, audio, speech, and 3D models using open source models. | |
| ART MCP Server davidesg/art-python Enables time series analysis following Box-Jenkins-Treadway methodology, supporting guided or autonomous modes for model identification, estimation, and diagnosis via an LLM. | |
| sima davidesg/sima-python Enables analysts to build and evaluate simultaneous VARMA models for systems of time series via exact maximum likelihood on the ATSW ladder, using univariate models as the yardstick. It guides users through loading univariate fits, identify | |
| keboola-cli-mcp-server davidesner/keboola-cli-mcp-server A deterministic proxy for Keboola CLI operations with automatic git-to-Keboola branch mapping, enabling branch management, CLI command execution, and optional proxy to remote Keboola MCP tools with automatic branch injection. | |
| whoop-ai-mcp davidewilson816/whoop-mcp Enables Claude, Codex, and GitHub Copilot to query WHOOP recovery, sleep, HRV, strain, and workout data read-only, with personal baselines, trends, and HYROX/triathlon race analysis tools. Also provides a local chart-first dashboard for rev | |
| gx-mcp-server davidf9999/gx-mcp-server Exposes Great Expectations data-quality checks as MCP tools for LLM agents, enabling data loading, expectation definition, validation, and result interpretation. | |
| Altaviz davidfertube/altaviz Enables monitoring and managing multi-platform media buying accounts via natural language, detecting anomalies like creative fatigue and spend spikes, with AI-powered recommendations and a human-in-the-loop approval queue. | |
| MCP Debugger Tools davidfirst/vscode-mcp-debugger A VSCode extension that enables AI agents to programmatically control VSCode's debugging features through the Model Context Protocol (MCP). | |
| ClinicalTrials.gov MCP Server davidfromkansas/clinical_trials_mcp_server Enables AI assistants to search and retrieve clinical trial data from ClinicalTrials.gov, supporting filters, study details, metadata, and statistics. | |
| Revise MCP davidfstr/revise-mcp Provides tools to revise and refactor code via MCP, including moving code, indenting/dedenting, outlining file structure, and optional symbol renaming. | |
| Playwright MCP davidg-blw/mcp_docs A browser automation MCP server that enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or vision models. | |
| cba davidgeorgehope/cba MCP server for semantic code search and explanation. Allows AI agents to search, ask questions, and manage memory about a codebase with local embeddings and LLM integration. | |
| tandoor-mcp davidgibbons/tandoor-mcp Provides recipe search and authoring, meal planning, shopping lists, and pantry tracking via task-shaped MCP tools. | |
| appsmith-mcp davidgraciano/appsmith-mcp MCP server for interacting with a self-hosted Appsmith instance via its REST API, enabling read/update/create of pages, queries, JS objects, widgets, datasources, and applications with lazy session management and destructive-operation gatin | |
| iMessage MCP Server davidgreigqc/imessage-mcp-server Enables Claude to read and search through iMessage, SMS, and RCS conversations, including mixed-protocol group chats with Android users. It decodes binary message data from the macOS Messages database to provide a comprehensive view of mess | |
| Artificial Analysis MCP Server davidhariri/artificial-analysis-mcp Provides access to real-time LLM pricing, speed metrics, and performance benchmarks for over 300 models from Artificial Analysis. It enables users to list, filter, and compare models based on costs, tokens per second, and intelligence indic | |
| Archicad MCP Connector davidharutyunyan/archicad-mcp-connector Gives Claude full read/write control of a live Graphisoft Archicad 26 project through roughly 260 tools, spanning modeling, drafting, annotation, queries, documentation and exports. Also lets the model capture views to visually verify its w | |
| FastAPI MCP Server davidholguin/mcpeam Enables interaction with Supabase databases and n8n workflows through a JSON-RPC 2.0 MCP server. Provides database operations, vector search capabilities, and webhook-based workflow automation with secure API token authentication. | |
| Aegis Jail MCP davidi0x/aegis-jail-mcp Enables running AI coding agents and MCP servers inside an OS-level least-privilege sandbox that hides credentials and blocks network access by default, with tool firewalling, rug-pull protection, audit logging, and boundary verification. | |
| WordPress MCP Server davidi18/wordpress-mcp An MCP server that enables AI agents to manage WordPress sites, including Elementor page building, content CRUD, plugin management, and site configuration via the WordPress REST API. |
42,701–42,750 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.