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 |
|---|---|
| otolawn-mcp dmitriyalergant/otolawn-mcp Enables control of OtO Lawn smart sprinkler devices from MCP clients by listing devices, zones, schedules, weather, diagnostics, and starting or stopping watering on demand. | |
| MCP Codebase Server dmitriyot/mcp-codebase MCP server for semantic codebase navigation that builds an AST index of symbols, imports, and exports, providing AI agents with tools to search, explore, and understand code. | |
| MCP Web Search Server dmitriyot/mcp-web-search MCP server for web search with LLM-optimized results and anti-detection mechanisms. | |
| Codex–ChatGPT Bridge dmitriysergeyev88/codex-chatgpt-bridge-win-macos Enables a planning assistant to submit, inspect, and review project-scoped coding tasks while a local coding agent runs them in isolated workspaces through durable queues and read-only source access. | |
| jbv-sdlc dmitry-506/sdlc-mcp Enables managing SDLC artifacts (create, resolve, entomb) with automatic commits and pushes to main branch, designed for use with Cursor. | |
| Truthrail LLM MCP adapter dmitry-dev-pet/truthrail-llm-mcp Enables authenticated MCP clients to check adapter status and, when explicitly enabled, run bounded correctness reviews of owner-consented public Python code through an existing gateway while keeping secrets and model calls gated. | |
| knowledge-gateway-mcp dmitry-kaleykin/skill-retrieval Enables semantic search and retrieval of eligible Pi skills through two read-only tools, while hiding the full skill catalog and enforcing invocation policy. | |
| Weather MCP Server dmitry-melnishin/mcp-weather Provides weather forecasts and alerts for US locations using the National Weather Service API. Features secure access via GitHub authentication and supports coordinate-based forecasts and state-specific weather alerts. | |
| AutoCAD MCP Pro dmitry5666/autocad-mcp Enables AI agents to create, read, critique and take off from CAD drawings through one typed contract served by two engines — live AutoCAD over COM on Windows or headless DXF via ezdxf anywhere. It covers ISO-standard mechanical parts and s | |
| mcp-optimizer dmitryanchikov/mcp-optimizer Mathematical Optimization MCP Server with PuLP and OR-Tools support | |
| Anfisa OS MCP Server dmitryborovoy-bot/anfisa-os A universal MCP layer for Russian-speaking America, enabling AI agents to access trucking, rideshare, insurance, tax, business, immigration, banking, credit, legal, and compliance services. | |
| U.S. Census Bureau Data API MCP dmitryf93/us-census-bureau-data-api-mcp Enables AI assistants to discover and query official Census Bureau datasets, geography levels, aggregate statistics, FIPS codes, and population data through MCP tools and prompts. | |
| url-download-mcp dmitryglhf/url-download-mcp A Model Context Protocol (MCP) server that enables AI assistants to download files from URLs to the local filesystem. | |
| confluence-mcp dmitrykhali/confluence-mcp Provides read access to Confluence Server/Data Center pages, sections, tables, and search via the Confluence REST API v1. | |
| Codex Control Plane MCP dmitrymalik8328/codex-control-plane-mcp Enables MCP clients to drive Codex Desktop and codex-app-server as a durable async worker for long-running tasks: submit work and get an operation or workflow ID immediately, then poll status, handle approvals and Plan Mode, and read final | |
| MCP-PostgreSQL-Ops dmitrypereira/mcp-postgresql-ops Enables AI assistants to inspect and monitor PostgreSQL 12-18 databases through natural language, covering performance analysis, slow-query identification, bloat and lock detection, autovacuum health, replication/WAL status, and schema expl | |
| mem0-mcp-selfhosted dmitryray1458/mem0-mcp-selfhosted Enables Claude Code to store, search, update, and delete persistent memories and knowledge-graph entities across sessions, backed by self-hosted Qdrant, Neo4j, and Ollama with optional Anthropic or fully local LLM inference. It also provide | |
| Gitingest-MCP dmitrys340/gitingest-mcp Enables MCP clients to quickly retrieve GitHub repository summaries, project directory structures, and file contents. | |
| mcp-1c-com dmitryskrypkin/mcp-1c-com Enables MCP clients such as Cursor and Claude to query and inspect 1C:Enterprise infobase data via COM without configuration extensions or changes, using 1C query language and metadata tools. | |
| Agent Harness Kit (AHK) dmitrywatanabe34/agent-harness-kit Enables AI coding providers to run structured multi-agent workflows by claiming tasks, logging actions, managing handoffs, and enforcing server-side health gates across explorer, consultant, builder, and reviewer roles. Specifications stay | |
| heroui-v2-mcp dmjacas/heroui-v2-mcp A standalone local MCP server that serves HeroUI v2 component documentation, source code, style definitions, and theme tokens by fetching directly from the official GitHub repository. | |
| Django Styleguide MCP Server dmmeteo/django-styleguide-mcp Provides AI assistants easy access to Django best practices by splitting comprehensive styleguide documentation into AI-friendly sections accessible through the Model Context Protocol. | |
| minga-graph dmminga1983/minga-graph Enables Claude Code and other MCP clients to query a local, explainable knowledge graph of a codebase: answering questions, explaining symbols, tracing paths between them, and computing blast-radius impact, with every edge backed by file:li | |
| Zorko dmminga1983/zorko Enables AI agents to drive a real Chromium browser by receiving compact, token-efficient page maps and only the changes after each action. It guards against hidden prompt injections, blocks payments, sends and deletions until the user appro | |
| opensrc-mcp dmmulroy/opensrc-mcp A codemode MCP server for fetching and querying dependency source code from npm, PyPI, crates.io, and GitHub. It allows agents to execute server-side JavaScript for context-efficient searching and browsing of large codebases without overwhe | |
| EPUB Novel MCP Server dmongrel/epub-mcp-server An MCP server for creating and editing EPUB novels, handling metadata, chapters, navigation, cover, and resources. | |
| fdx-mcp-server dmongrel/fdx-mcp-server Enables reading and writing local files via MCP, supporting Bun, Deno, or Node.js runtimes. | |
| MCP 3D Printer Server dmontgomery40/mcp-3d-printer-server Enables interaction with 3D printer management systems through an MCP server, supporting STL file manipulation, slicing, and control of printers like OctoPrint, Klipper, Duet, and more. | |
| Canvas MCP Server V2.0 dmontgomery40/mcp-canvas-lms A Model Context Protocol server that enables interaction with the Canvas Learning Management System API, allowing users to manage courses, assignments, enrollments, and grades within Canvas. | |
| BirdNet-Pi MCP Server dmontgomery40/mcp-local-server A Python-based server that enables accessing and analyzing bird detection data through the Model Context Protocol, offering features like filtering detections, accessing audio recordings, and generating reports. | |
| mcp-server-birdstats dmontgomery40/mcp-server-birdstats Cross-reference your BirdNET-Pi data with eBird observations using natural language | |
| Meta MCP Server dmontgomery40/meta-mcp-server A tool that dynamically generates and configures MCP servers by automatically creating necessary directories and files according to user specifications. | |
| Pentest MCP dmontgomery40/pentest-mcp A Model Context Protocol server that integrates essential penetration testing tools (Nmap, Gobuster, Nikto, John the Ripper) into a unified natural language interface, allowing security professionals to execute and chain multiple tools thro | |
| m3-inspo dmontinaro/m3-inspo Enables coding agents to query a private, curated design reference library over MCP, retrieving approved screenshots alongside the owner's take-and-avoid notes, marked component regions, and brand kits with colors, typography and CSS. Suppo | |
| onedrive dmoreau69872/onedrive-cli Enables MCP clients to browse and search folders, find files, list albums, read file contents, and retrieve item metadata or storage quota in a read-only manner. | |
| gmail-mcp-multi dmorrill/gmail-mcp-multi A Gmail MCP server with native multi-account support, enabling management of multiple Gmail accounts from a single server instance. | |
| good_honker dmpeters/good_honker A conversational MCP server that provides natural-language access to Goose's live show history, setlists, and song statistics via the ElGoose.net API, including tools like latest show, this day in history, and song stats. | |
| good_wook dmpeters/good_wook A conversational MCP server that provides natural-language access to Phish's show history, setlists, and song statistics via live Phish.net data. | |
| coding-agent-mcp dmrtx/coding-agent-mcp Enables supervising and orchestrating local coding agents like Muse and AGY through a client-agnostic MCP interface, with isolated Git worktrees, safe execution, and deterministic verification. | |
| Bitbucket MCP Server dmtr/bitbucket_mcp Enables interaction with Bitbucket repositories through the Model Context Protocol, supporting code search, repository management, branch creation, pull requests, and more. | |
| tmux-agent dmvevents/tmux-agent-public Enables agents to spawn, monitor, and control CLI coding agents running in isolated tmux sessions, with verified input injection, redacted pane capture, fleet and per-session state classification, lineage tracking, blocking exec with exit c | |
| Cani dmytro-portianka-ddddd/cani Enables an MCP client to ask whether a purchase is affordable and receive an auditable, deterministic YES/NO verdict backed by an append-only ledger, and to attempt a real governed checkout that returns a structured decline without creating | |
| PPTX Generator MCP Server dmytro-ustynov/pptx-generator-mcp Generates professional PowerPoint presentations from Markdown with support for code blocks, tables, custom branding, and mixed formatting. Transforms lesson plans and documentation into styled PPTX files with syntax highlighting and customi | |
| usage-mcp dmytrochygarov/usage-mcp Lets Claude look up your own Claude subscription usage limits — the same 5-hour and weekly percentages shown by /usage — mid-conversation, so it can pace long tasks and warn you before you hit a wall. It reads the local OAuth login, serves | |
| grid-intake dmytromazurev/grid-intake-check Enables an AI assistant to run pre-ingest QA on utility power-grid GIS exports: score readiness, list issues with coordinates, reconcile registers against survey/LiDAR detections, map codes to library types, and draft a data request. It exp | |
| just-prs-mcp dna-seq/just-prs-mcp MCP server for polygenic risk score analysis, wrapping just-prs to enable catalog search, PRS computation, VCF normalization, percentile and risk estimation, and quality assessment. | |
| rig-bridge dna113p/rig-bridge Enables AI assistants to securely operate on a local workstation through MCP by exposing file, shell, and workspace management tools. | |
| MyGenome dnaerys/mygenome Personal Genome Exploration | |
| WhatsApp Channel dnakamura2758/whatsapp-claude-plugin Enables users to drive a Claude Code session from WhatsApp, with bidirectional messaging, media and voice-note handling, access-controlled chats, per-group personalities, and remote approval of tool requests via emoji reactions. | |
| Mavryn dnakitare/mavryn Centralized MCP control plane that proxies multiple upstream MCP servers with tool namespacing, filtering, policy enforcement, audit logging, and health checks. |
45,201–45,250 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.