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 |
|---|---|
| WithSeismic MCP dougwithseismic/withseismic-mcp A TypeScript implementation of a Model Context Protocol server that provides a frictionless framework for developers to build and deploy AI tools and prompts, focusing on developer experience with zero boilerplate and automatic tool registr | |
| MkDocs MCP Plugin douinc/mkdocs-mcp-plugin Enables AI agents to interact with MkDocs documentation through intelligent search (keyword, vector, and hybrid), document retrieval, and automatic indexing. Automatically detects and launches MkDocs projects for seamless documentation quer | |
| Omni-Doc-MCP doujiaozh/omni-doc-mcp Enables AI agents to extract text and structure from PDF, Word, and Excel documents as LLM-friendly Markdown or JSON, with tools for parsing files and listing supported formats. | |
| K8s_MCP dousery/k8s_mcp An Model Context Protocol server that lets language models directly manage and visualize Kubernetes clusters through safe, high-level operational tools. | |
| zhihu-mcp douyh123/zhihu-mcp Enables AI assistants to directly operate Zhihu, including login, publishing articles and videos, searching content, getting recommendations, and commenting. | |
| mcp-mail-server dove-yang/mcp-mail-server-enhanced Enables natural language email operations (send, search, read, manage) via IMAP/SMTP, with support for attachments, multiple mailboxes, and secure configuration. | |
| yuque-cookie-mcp dove-yang/yuque-cookie-mcp Enables AI assistants to manage Yuque (语雀) documents via MCP protocol, with cookie-based login that does not require a super membership. | |
| Dovetail MCP Server dovetail/dovetail-mcp Connects AI tools to the Dovetail API, enabling them to interact with Dovetail features. | |
| Rebrain MCP Server dovgiya/mcp Enables developers to check system service status, retrieve project documentation, search files, and run whitelisted commands (git, pytest, etc.) securely via natural language. | |
| cds-kb-mcp dovoanhtruong/cds-kb-mcp A dataless MCP server that searches the SAP CDS knowledge base, allowing users to query view metadata and retrieve full view details using local or remote data sources. | |
| onenote-mcp dovrosenberg/onenote-mcp Enables interaction with Microsoft OneNote through Microsoft Graph, exposing notebooks, sections, and pages, including handwriting rendered to an image. | |
| LionScraper dowant/lionscraper-mcp LionScraper MCP + CLI + API service | |
| BrunoSan AI News MCP Server dowellug/brunosan-ai-news-mcp A Model Context Protocol server that exposes real-time AI news intelligence to AI agents and MCP-compatible clients, with 9 deterministic tools for search, trending, signals, and risk analysis. | |
| librechat-mnemonic dowlings/librechat-mnemonic Enables automatic, project-scoped long-term memory for LibreChat conversations by recalling relevant memories before each turn and writing durable facts after each turn. It integrates via a proxy that resolves project context from MongoDB a | |
| Text-to-SQL MCP Server down530/sql-mcp Enables secure SQL query execution on MySQL databases with authentication and permission control, allowing users to explore database tables and run read-only queries. | |
| terraform-best-practices-mcp-server downatthebottomofthemolehole/terraform-best-practices-mcp A Model Context Protocol (MCP) server for producing better Terraform through CLI analysis (tflint, checkov, trivy, kics, infracost), best-practice guidance from terraform-best-practices.com, cloud provider recommendations (Azure, AWS, GCP), | |
| vCenter MCP Server downeyou/vcenter-mcp-stack Enables interaction with VMware vCenter 8.0 REST API via a reverse proxy, providing read-only and write tools with dry-run protection and automatic session management. | |
| Dowon Insurance Judgment MCP Server dowon-comsup/4-repo Evaluates employment status exemption for corporate directors, family workers, and non-registered executives using registry and employment data, and calculates refund periods considering statute of limitations. | |
| TOEIC Speaking MCP Server doy00/mcp-toeic-speaking-sentences Enables TOEIC speaking sentence practice with adaptive quizzes, voice input, and instant feedback through keyword matching and mastery scoring. | |
| kb-mcp-server doy369/kb-mcp-server Enables to build and query a knowledge base with retrieval-augmented generation, supporting document ingestion, hybrid search, and live data integration from external APIs via MCP tools. | |
| teguma doyajin174/teguma AI-native design bridge that enables AI agents to read and write Penpot designs while maintaining brand context through its MCP server. | |
| saaspo-mcp doziben/saaspo-mcp An MCP server that gives AI coding agents access to saaspo.com's SaaS web design inspiration library, enabling them to search pages and sections by style, industry, and type for grounded design decisions. | |
| Guardian MCP dozie2001/guardian-mcp Enables AI agents to propose stock, ETF, and crypto trades through Alpaca paper trading while enforcing deterministic policy rules and recording every decision in an audit trail. | |
| abap-adt-doZimple dozimple-labs/abap-adt-dozimple Grants AI agents secure, verifiable access to SAP ABAP systems (ECC 6.0 and S/4HANA) so they can review code and transport orders, run ATC and ABAP Unit checks, trace where-used relationships, query tables with read-only ABAP SQL, diagnose | |
| SonarCloud MCP Server dozzman/sonarcloud-mcp A server that enables fetching and filtering SonarCloud issues related to pull requests, making it easier to identify and fix code quality problems. | |
| TaskFrame MCP Server dozzzer/vertical-unit-mcp HTTP MCP server for TaskFrame that enables AI agents to manage projects, tasks, comments, and documents through the TaskFrame API. | |
| Trilogy AI MCP Server dp-pcs/trilogy-ai-mcp-server An MCP server that analyzes Trilogy AI Center of Excellence Substack publications, allowing users to list, search, and analyze trends in the AI content. | |
| Workflowy MCP Server dp-pcs/workflowy-mcp-server Provides LLM access to Workflowy's API, enabling agents to create, read, update, delete, and reorganize nodes in a Workflowy outline. | |
| Obsidian MCP Tools dp-veritas/mcp-obsidian-tools A read-only toolkit for searching and analyzing Markdown note directories and Obsidian vaults through AI clients. It enables metadata extraction, full-text search, and natural language querying of note content, tags, and backlinks. | |
| OpenSTAAD MCP Server dp065u/staad-mcp Enables AI agents to interact with Bentley STAAD.Pro models for tasks like load case definition, data extraction, and property setting, running locally with multi-instance support and no cloud dependency. | |
| Ember dp177/ember Provides coding agents with persistent, queryable repository memory over MCP, enabling code search, cited question answering, repo maps, decision logs, and cross-session notes through local-first tools. | |
| MCP Claude Desktop dpaluy/mcp-claude-desktop Enables Claude Code to send prompts to Claude Desktop using macOS automation and AppleScript. Supports conversation management and configurable response polling, though reading responses back is limited by Electron's accessibility APIs. | |
| VideoReceiverMCP dpansumisra/mcp MCP server that receives base64-encoded video files, saves them locally, and supports listing and deletion; works via stdio for local agents and HTTP for remote clients. | |
| QAcito dpaul20/qacito Autonomous QA platform powered by Claude + Playwright that allows AI to write, run, and fix tests for any project. | |
| chatgpt-codex-local-mcp dpaula/chatgpt-codex-local-mcp A secure MCP server that exposes local repository context to ChatGPT/Codex with read-only access, path validation, and no generic shell. | |
| acm_mcp dpbeahr-rok/acm_mcp MCP server for building Rockwell Automation PLC project plans by browsing the ACM catalog, resolving library dependencies, and assembling project hierarchies with automatic placement. | |
| Android Development MCP Server dpconde/android-dev-mcp Provides Android development assistance following NowInAndroid best practices, including architecture patterns, code generation for feature modules/ViewModels/repositories, and searchable documentation for Jetpack Compose and modularization | |
| mcp-server-quint dpdanpittman/mcp-server-quint Integrates the Quint formal specification language into LLM workflows for accessible formal verification. It provides tools for type-checking, random simulation, exhaustive model checking, and syntax documentation. | |
| pico-mcp dperezcabrera/pico-mcp Enables developers to expose pico-ioc component methods as Model Context Protocol tools, resources, and prompts, deriving input schemas from method signatures and resolving every call through the dependency-injection container. Supports std | |
| Microsoft SQL Server MCP Server (MSSQL) dperussina/mssql-mcp-server An easy-to-use bridge that lets AI assistants like Claude and Cursor IDE directly query and explore Microsoft SQL Server databases. No coding experience required! | |
| MantisBT MCP Server dpesch/mantisbt-mcp-server Integrates MantisBT bug tracker into Claude and other MCP clients via the REST API. Read and manage issues, notes, file attachments, tags, relationships, and monitors — with optional offline semantic search across all issues. | |
| nova.mcp-bcp-counting dpetruz/nova.mcp-bcp-counting Enables Claude to guide developers through structured complexity estimation using BCP Plus methodology, counting 13 dimensions and persisting results for H/BCP tracking. | |
| DPF dpf-admin/dpf-claude-plugin AI-powered data integration platform. Onboard users and run DPF data workflows. | |
| MySQL Database Access dpflucas/mysql-mcp-server An MCP server that provides read-only access to MySQL databases. | |
| App Factory MCP dpgs-oss/app-factory-mcp An orchestrator MCP server that takes a plain-language app description and guides agents through a full workflow from intake to deployment, including design, audit, and maintenance. | |
| FHIR MCP Server dpham02711/fhir-mcp-server Enables LLM-based agents and MCP-compatible clients to interact with FHIR-compliant backends, performing full CRUD operations on clinical resources through natural-language prompts, with document ingestion, semantic search, and LOINC termin | |
| Bible Research MCP Server dpirek/bible Enables local reading, searching, and scholarly study of the Bible through MCP tools, including passage lookup, literal search, topical research, word study, related-passage discovery, passage comparison, and corpus overviews. | |
| Seattle Fire Department MCP Server dpkirschner/mcp-sfd Enables real-time monitoring of Seattle Fire Department incident data, allowing users to check for active fires, evacuation orders, and retrieve live emergency response information through natural language queries. | |
| multimodels-mcp dpmadsen/multimodels-mcp Delegate tasks from Claude Code to other models (Codex CLI, DeepSeek, OpenRouter, etc.) without leaving the app. | |
| MCP Server dpoitrast/mcp A FastAPI-based Model Context Protocol server that exposes herd data through a discoverable API, with local and containerized deployment options. |
45,751–45,800 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.