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 |
|---|---|
| YWM MCP dveresov/dv-ywm-mcp Enables pulling Yandex Webmaster data into Claude, including backlinks, queries, indexing, diagnostics, and CSV export, so users can analyze SEO metrics without paid tools. | |
| neptunesoftware-dxp-mcp-goods-receipt dvieira-neptune/neptunesoftware-dxp-mcp-goods-receipt Demonstrates a SAP Goods Receipt workflow, enabling AI Agents to interact with production orders and post goods receipts to SAP. | |
| neptunesoftware-dxp-mcp-inventory-counting dvieira-neptune/neptunesoftware-dxp-mcp-inventory-counting MCP server for SAP Physical Inventory Counting, enabling materials retrieval, stock display, quantity entry, and posting counts to SAP. | |
| Flutter MCP Service dvillegastech/flutter_mcp_2 Provides advanced Flutter development tools via Model Context Protocol with features including widget analysis, documentation search, performance optimization, and code generation. | |
| mcp-chess dvip1/chess_mcp An MCP server that exposes Stockfish chess analysis to LLM chat clients, enabling move analysis, game review, and explanation of engine choices. | |
| mcp-convention-gate dvir-shamay/mcp-convention-gate Enforces named review gates before commits by refusing commits until required reviews are registered. It exposes tools to create gate sessions, register review results, check commit readiness, and audit the process. | |
| Snippy dvisser22/snippy Enables AI assistants to save and retrieve code snippets, perform semantic vector search over stored code, and generate code style guides and wiki documentation. It also orchestrates multi-agent workflows that combine specialized agents to | |
| Model Control Plane (MCP) Server dvladimirov/mcp A server implementation that provides a unified interface for OpenAI services, Git repository analysis, and local filesystem operations through REST API endpoints. | |
| tempmail-mcp dvlop/tempmail-mcp MCP server for disposable email. Gives an assistant its own throwaway inbox, then hands back the confirmation code out of the message that arrives. | |
| video-probe-mcp dvnc-labs/video-probe-mcp Inspect local video and audio files with ffprobe, returning structured metadata such as format, duration, bitrate, and stream info. | |
| MCP Jenkins dvolkov312/mcp-jenkins Provides secure, contextual AI interactions with Jenkins, enabling users to inspect and manage jobs, builds, nodes, queues, views, plugins, and artifacts through natural language while honoring authentication and read-only settings. | |
| opendrive-mcp-server dvorak/opendrive-mcp Enables querying OpenDRIVE road network files through structured MCP tools for summarizing maps, listing roads and lanes, converting coordinates, and validating files. | |
| Israel Weather MCP Agent dvori9359-blip/mcp-with-playwright Enables users to retrieve real-time weather forecasts for Israeli cities by autonomously browsing a weather website using Playwright. | |
| NTLite MCP Server dvow/ntlite-mcp Enables MCP-compatible clients to inspect Windows images, edit NTLite presets, and run apply, save, and ISO creation operations through the running NTLite window. | |
| Stage dvrshil/stage Enables AI agents to build, validate, query, and render 3D homes and object scenes from a single JSON scene file over MCP, with browser walkthroughs for people. | |
| siglent-mcp dvsproductions/siglent-mcp Control a Siglent SPD1305X (or SPD1000X series) programmable DC power supply from Claude Code over Ethernet using SCPI commands, with safety limits and monitoring tools. | |
| VergeOS MCP Server dvvincent/vergeos-mcp-server Enables AI assistants to manage and monitor VergeOS virtualization platforms through natural language, including VM operations, network management, tenant administration, and cluster monitoring. | |
| Human Design MCP Server dvvolkovv/mcp_human_design Calculates Human Design charts based on birth date, time, and location, providing type, strategy, authority, profile, gates, defined centers, and incarnation cross information. | |
| kaiten-mcp dvzak/kaiten-mcp MCP server for interacting with Kaiten project management through its REST API. Enables managing spaces, boards, cards, comments, checklists, tags, and time logs. | |
| Design System MCP Server dw18031988/ds_mcp_server Self-hosted MCP server that enables ChatGPT agents to perform health checks, fetch design request context, and submit agent results back to a design system backend. | |
| fuel-prices-mcp dwain-barnes/fuel-prices-mcp MCP server for UK fuel prices, enabling queries for cheapest stations, nearby forecourts, and area price summaries using official government open data. | |
| Environment Agency Flood Monitoring MCP Server dwain-barnes/mcp-server-environment-agency Provides access to UK Environment Agency's real-time flood monitoring data, enabling users to check flood warnings, monitor water levels and flow rates, and access historical measurements from monitoring stations across the UK. | |
| MCP Server Police UK dwain-barnes/police-uk-api-mcp-server Provides access to the police.uk API with 21 tools to query UK crime data, police forces, neighbourhoods, and stop-and-search incidents. Enables retrieval of street-level crimes, force details, neighbourhood teams, and policing priorities a | |
| UK ONS MCP Server dwain-barnes/uk-ons-mcp-server Enables access to official UK Office for National Statistics data including demographics, economics, and social statistics through the ONS Beta API. Supports browsing, searching, and querying datasets with built-in shortcuts for popular sta | |
| MCP Database Server dwarvesf/mcp-db A Model Context Protocol server that provides tools for interacting with databases, including PostgreSQL, DuckDB, and Google Cloud Storage Parquet files. | |
| MCP Playbook Server dwarvesf/mcp-playbook Manages project documentation and saves conversation logs within a target project directory, providing tools for creating specs, ADRs, changelogs, runbooks, and syncing prompts/logs to GitHub repositories. | |
| samsung-tv-mcp dwdas9/samsungtvmcp Enables Claude to control a Samsung Tizen smart TV over the local network without cloud services, covering power on/off, launching and closing apps, casting YouTube videos, sending remote keys, adjusting volume, and checking TV status and h | |
| OC Transpo MCP Server dwdraju/octranspomcp Provides real-time transit data for OC Transpo in Ottawa, including live vehicle positions and trip updates via GTFS-RT feeds. It enables AI agents to monitor arrival delays, schedule changes, and transit telemetry through the Model Context | |
| Marketing Analytics MCP Server dweeb1578/marketing-analytics-mcp Enables natural language querying of marketing analytics across Google Search Console, GA4, Google Ads, HubSpot, and Bing. Provides tools for search queries, traffic, campaign performance, and composite cross-platform rollups. | |
| Joplin MCP Server dweigend/joplin-mcp-server A server that enables AI assistants to access and manipulate Joplin notes through the Model Context Protocol, allowing search, reading, editing, and management of notes using natural language. | |
| Cheesecube MCP Server dwellis/cheesecube-mcp Exposes the Cheesecube Agent API as MCP tools, enabling listing engines and templates, searching assets, and creating, previewing, and publishing cheese and templates. Designed for use with MCP clients like Claude Desktop and Cursor. | |
| MCP Omni-Tool dwflickinger/mcp-omni-tool A single MCP server that provides dynamic access to thousands of APIs through discovery and proxy, eliminating the need to install and configure multiple separate MCP servers. | |
| chrome-downloader dwgfaker/chrome-dl-bridge Enables AI agents and CLI tools to dispatch downloads through Chrome's native download engine over the MCP protocol, automatically inheriting browser cookies, login sessions, and proxy settings. Supports submitting, monitoring, pausing, res | |
| Blender Copilot MCP Server dwgx/blender-copilot Comprehensive MCP server for Blender with 308 tools across 25 modules, enabling AI-powered 3D creation and full VRChat avatar pipeline. | |
| SimpleMCP dwhite-sys/simplemcp A lightweight MCP server that auto-discovers tool kits, enabling tools like SQLite queries and web searches via Tavily API. | |
| MCP MongoDB Server dwhyte/mcp-mongodb An MCP server that provides tools to query and interact with MongoDB user collections, supporting filtering, sorting, and retrieval operations. | |
| HWC Growth Center MCP Extension dwight2458/developer-grow-mcp-extension Enables daily check-in, points and task queries for Huawei Cloud Developer Growth Center via a Chrome extension and Node.js bridge. | |
| Littlebird Obsidian MCP dwightpeaster/littlebird-obsidian-mcp A local-first MCP server that routes Littlebird daily context into structured Obsidian notes, connecting daily work to a durable knowledge base. | |
| alopeyk-mcp dwin-gharibi/alopeyk-mcp A self-hostable MCP server for Alopeyk (الوپیک), an Iranian on-demand delivery and logistics company, enabling LLM agents to geocode addresses, quote and track deliveries, manage parcels, and optionally create/cancel real orders. | |
| ArvanCloud MCP Server dwin-gharibi/arvancloud-mcp Enables AI agents to manage the entire ArvanCloud platform (compute, networking, storage, CDN, DNS, etc.) plus a cloud-DevOps toolbox for provisioning, Kubernetes, IaC, security, and networking through natural language. | |
| ramzinex-mcp dwin-gharibi/ramzinex-mcp Self-hostable MCP server for the Ramzinex cryptocurrency exchange, providing tools for market data, account management, and trading with safety flags. | |
| Repovive MCP Server dwin-gharibi/repovive-mcp Connects AI assistants to the Repovive competitive-programming platform, enabling them to browse problems and contests, judge and submit code for real verdicts, track ratings, communicate with users, and author verified problems and rounds. | |
| roshan-alefba-mcp dwin-gharibi/roshan-alefba-mcp A self-hostable MCP server that exposes Roshan AI's Alefba OCR service as tools, enabling document reading, page extraction, status polling, and export to PDF/Word/Excel for Persian, Arabic, and English text. | |
| roshan-baaz-mcp dwin-gharibi/roshan-baaz-mcp Enables semantic search and retrieval for Persian content through Roshan AI's Baaz service, wrapped as MCP tools with support for multi-instance self-hosted deployments. | |
| roshan-fahm-mcp dwin-gharibi/roshan-fahm-mcp MCP server wrapping Roshan AI's Fahm Persian language service, enabling chat, translation, summarization, and more for Persian text. | |
| roshan-harf-mcp dwin-gharibi/roshan-harf-mcp A self-hostable MCP server for Roshan AI's Persian speech service, Harf, enabling transcription, forced alignment, real-time streaming, and speaker analysis through natural language. | |
| OAPT MCP Extension dwinter3/oapt-mcp-extension Connects Claude Desktop to the OAPT MCP server for natural-language queries across Dynamics CRM, AWS ACE, Partner Central, and more via a hosted endpoint, with per-user API key authentication. | |
| SlideCraft MCP dwinter3/slidecraft-mcp Creates AI-powered slide decks directly from Claude Desktop with live progress and QA scores. | |
| Delve MCP dwisiswant0/delve-mcp A TypeScript-based MCP server providing a complete interface to the Delve debugger for Go programs, enabling debugging, tracing, and analyzing Go code through natural language commands. | |
| Budget Broker MCP dwk601/near-budget-broker-mcp Enables isolated agents to preview and request native NEAR testnet transfers through a keyless MCP bridge, with custody-enforced per-agent and wallet limits, approvals, fee budgets, signed receipts, and owner/agent kill switches. |
46,501–46,550 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.