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 |
|---|---|
| VibeBridge assishmoncs/vibebridge Enables Gemini Spark to securely read, edit, and search a selected local workspace, execute shell commands, and integrate development tools via MCP with user approval safeguards. | |
| Zileo Docs assistance-micro-design/zileo-docs MCP server for indexing, semantic search, and generation of multi-format documents. Exposes 13 tools over JSON-RPC 2.0 so an LLM can search your local PDF, Excel, and Word files, and create or edit Excel and Word documents. | |
| cocos-mcp-server association-of-stupid-people/cocos-mcp-server Enables AI assistants to interact with the Cocos Creator editor through the Model Context Protocol, providing 50 core tools for editor functionality. | |
| Google Analytics MCP Server ast-consulting/gsc-mcp Enables interaction with Google Analytics APIs to fetch reports, manage properties, data streams, conversion events, and custom dimensions/metrics through OAuth2 authentication. | |
| ast-grep MCP Server ast-grep/ast-grep-mcp Enables AI assistants to search and analyze codebases using Abstract Syntax Tree (AST) pattern matching with ast-grep. Supports structural code search, pattern testing, and AST visualization across multiple programming languages. | |
| elog-mcp ast0815/elog-mcp Provides read-only access to ELOG electronic logbooks, enabling full-text and attribute search, reading entries with attachments, and listing logbooks over HTTP. | |
| jabref-mcp ast0815/jabref-mcp Enables MCP clients to search, read, and add entries to JabRef 5.x bibliographies, including resolving attached PDFs for summarization. | |
| basiclocalmcpservertools astanciulescu03-sys/basiclocaltoolsmcp Provides local Windows utilities to MCP clients, enabling file explorer and notepad actions, hardware/process inspection, and network connection details with geolocation. | |
| Astatide Conductor astatide1337/conductor Orchestrates persistent task graphs and enforces approval policies for MCP-driven agent workflows, coordinating with Agents Gateway for execution. | |
| Nexoraa MCP Server astatiners/nexoraa-tree Exposes 36 skills covering 137 AI jobs across 7 departments, enabling AI workforce deployment and management through any MCP client. | |
| veilform asteby/veil Enables AI agents to ask users for credentials, secrets, and sensitive data through local browser forms that the model never sees, then resolve and use those values only at approved points of use. Also supports blind web capture, SSH key pr | |
| NinjaONE MCP Server astecit-admin/ninjaonemcp Enables managing NinjaONE RMM platforms, including devices, patches, alerts, users, policies, and backups, through natural language MCP interactions. | |
| mcp-ticketmaster aster-god/mcp-ticketmaster Enables AI agents to search events, check ticket availability, select seats, manage carts, and purchase tickets on Ticketmaster through browser automation with session persistence and bot-detection handling. | |
| aster-guard aster-works/aster-guard Enables scanning MCP server configurations for security risks like prompt injection, hardcoded secrets, and dangerous commands, providing risk scores and detailed reports before connecting to an AI coding assistant. | |
| Aster MCP Server asterdex/aster-mcp An MCP server for Aster Futures and Spot APIs, enabling AI agents to query market data, place orders, and check positions and accounts securely. | |
| deep-research-mcp asteriii123/deep-research-mcp Enables users to create and refine a research outline, queue report generation in the background, and retrieve progress or completed Markdown reports, with automatic checkpointing so unfinished work can resume after a restart. | |
| Polish Academic MCP asterixix/polish-academic-mcp Provides tools for AI models to search and retrieve information from five major Polish academic and government databases, including scientific articles and research datasets. It enables users to query platforms like Biblioteka Nauki and Rep | |
| mcp_server_document_manager asthasoni22/mcp_server_document_manager An MCP server that manages documents, enabling retrieval and command-based operations within AI chat interfaces using the Anthropic API. | |
| mewcp-jev asthetech/mewcp-jev Enables structured, rubric-based evaluation of text or structured state using TypeSafe AI's Jev System One API, supporting yes/no, single-choice, and rubric-scored questions in parallel. | |
| Polymarket MCP Server asthetech/mewcp-polymarket Enables interaction with Polymarket prediction markets through read-only access to market data, events, orderbooks, and user positions, plus authenticated trading capabilities for creating and managing orders. | |
| CL Razorpay MCP Server asthetech/mewcp-razorpay Integrates with Razorpay's payment infrastructure to manage orders, process payments, handle refunds, and query settlements via the Model Context Protocol. Features stateless, multi-tenant architecture with secure per-request authentication | |
| txt-to-md-mcp astly123/txt-to-md-mcp Enables writing text content to Markdown files with folder organization and overwrite control, and listing recent Markdown files. | |
| changelog aston-cook/changelog-mcp It enables solo builders to automatically log product changes to PostHog and later get statistically honest verdicts on whether those changes moved key metrics, without needing enough traffic for A/B tests. | |
| dbt-doctor astoriel/dbt-doctor AI-driven MCP server that audits, profiles, detects schema drift, and auto-generates documentation for dbt projects, enabling natural language interaction with your dbt project's health. | |
| GrowthOS astoriel/growthos Enables AI assistants to answer growth questions in plain English by connecting to marketing and product data via 49 MCP tools. | |
| aws-mcp astormspirit/aws-mcp Runs on Cloudflare Workers to let MCP clients execute AWS API commands with your own credentials via SigV4-signed HTTPS requests. Supports common S3, EC2, IAM, Lambda, and STS operations plus a generic escape-hatch for any AWS API call. | |
| Tesla Agent Bridge astposeidon/tesla-agent-bridge Enables chat agents and automation tools to query Tesla vehicle status and, when explicitly enabled, send signed vehicle commands via MCP over Streamable HTTP or local stdio. | |
| MCP X++ Server astra-bright/mcp_xpp An MCP server for Microsoft Dynamics 365 Finance & Operations that enables the creation, modification, and analysis of D365 objects like classes, tables, and forms. It integrates with Visual Studio 2022 to provide tools for X++ code extract | |
| lax-mcp-server astra-tc/lax-mcp-server Enables agents to search the Kognai LAX registry for agents, retrieve offers and jobs, list jobs, and submit job submissions over stdio or Streamable HTTP. | |
| scpr astrabert/scpr A web scraping CLI tool that converts web pages to markdown and also runs as an MCP server for agent integration. | |
| agent-computer-use-mcp astraclawteam/agent-computer-use-mcp Local MCP server for Gateway-managed computer use that exposes computer.* tools with desktop control, OCR, and user-visible safety overlays. | |
| Astraeus Governed Postgres MCP astraeus-business-solutions/astraeus-postgres-mcp Enables AI agents to query a Postgres database read-only through a policy layer rather than a raw connection string. Enforces table and column allowlists, row limits, mandatory predicates, PII masking and append-only audit logging, while re | |
| AstraMemory Local astragenie/astramem-local Local-first memory daemon for AI coding agents that captures session transcripts, distills typed memories (decisions, facts, lessons, commands, todos), and serves them via hybrid search through MCP tools. | |
| StickyInc astralchemist/stickyinc Captures commitments from LLM conversations into a persistent local task list shown on an edge strip, with tools to add, list, and complete tasks. | |
| Rive MCP Server astralisone/rive-mcp-server-core Orchestrates Rive animations by enabling discovery, integration, and composition across frameworks like React and Vue, with code generation and multi-backend storage. | |
| cosplay-vp astralrc/cosplay-vp Enables an AI agent to run a CG cosplay virtual production pipeline on real footage: probe and conform clips, extract frames, chroma key or apply an installed matting model, solve camera moves with COLMAP, convert them into Unreal Engine ca | |
| Stealthee MCP astraltrekkin/stealthee-mcp-tools Enables detection and analysis of pre-public product launches through web search, content extraction, AI-powered scoring, and automated alerting. Provides comprehensive tools for surfacing stealth startup signals before they trend publicly. | |
| Prophet MCP astralumelan/prophet-toolkit Enables AI agents to invoke the toolkit’s offline divination and astrology calculations—including Bazi, Ziwei, Liuyao, Meihua, Qimen, Huangli, Western, Vedic, and Tarot—through MCP JSON-RPC over stdio, with JSON tool discovery, schemas, loc | |
| pipeflow-mcp astralvoidz/pipeflow-mcp PiPeFlow passively tracks AI agent workflow states using a finite state machine, providing tools for declaring, advancing, and auditing pipelines with annotations and reports. | |
| ppsspp-dfx astralvoidz/ppsspp-dfx-mcp Enables AI agents to debug and control the PPSSPP PSP emulator, providing tools for memory access, disassembly, breakpoints, CPU control, input automation, screenshots, and diagnostic scripting. | |
| Omni MCP Suite astrat999/omni-mcp-suite A collection of uncensored, API-free data acquisition tools for AI agents, featuring anti-corporate web search, image scraping, and OSINT framework that bypass filters via alternative indexers and deep web scanning. | |
| Astrax astraxof/astrax-mcp Gives AI assistants eyes and hands on your desktop, letting them view and capture the screen, click, type, use the clipboard, run shell commands, and execute multi-step tasks with a single per-task authorization while keeping context small | |
| Web MCP Bridge astraxof/web-mcp-bridge A local Python WebSocket bridge and browser extension that securely connects web AI chats to local Model Context Protocol (MCP) servers. It enables web-based AIs to execute local tools with granular permission controls, providing the same p | |
| astrbot-mcp astrbot-for-xiaozhiai-server/astrbot-mcp An MCP server that exposes unified tools for HTTP requests, web search and fetching, weather/time/currency, file and SQLite sandboxes, GitHub, email, calendars, and a self-learning SQLite FTS5 knowledge base. It supports stdio, SSE, and str | |
| contabilidad-mcp astrid3333/contabilidad-mcp Double-entry accounting MCP server for Claude Desktop. Supports accounts, transactions, ledgers, profit & loss, balance sheet, IVA summary, and QIF export using SQLite. | |
| structuresynth-mcp astrid3333/structuresynth-mcp Enables LLM agents to author EisenScript procedural grammars and render them headlessly into Wavefront OBJ meshes, returning vertex/face counts and bounding boxes alongside validation, linting, PNG previews, mesh-format conversion, batch ga | |
| mcp-shodan astrid43/mcp-shodan Gives AI agents access to the Shodan API and Shodan CVEDB for host reconnaissance, device search, DNS lookups, and CVE/CPE vulnerability intelligence. It returns open ports, banners, TLS certificates, subdomains, and CVSS/EPSS/KEV severity | |
| Frappe MCP astridhwang76699/mcp Enables Frappe Framework apps to act as Streamable HTTP MCP servers by registering tools and exposing an MCP endpoint, with current support for tools usable by LLMs. | |
| Codexless astridneumann6814/codexless Enables ChatGPT to access a reviewed local toolbox for project inspection, file editing, bounded terminal commands, Chrome/Edge browsing, live Excel control, and explicit Codex model calls only when needed. | |
| TrainingPeaks MCP Server astridzawadzki/trainingpeaks-mcp Enables querying and managing TrainingPeaks workouts, structured intervals, calendar events, health metrics, and CTL/ATL/TSB fitness data through natural language, using cookie-based authentication that needs no API approval. |
31,351–31,400 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.