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 |
|---|---|
| paprika-mcp aarons22/paprika-tools An MCP server that provides read-only access to the Paprika Recipe Manager, allowing users to list and retrieve recipes, grocery items, and meal plans. It enables seamless interaction with recipe details and category information through the | |
| Azure DevOps MCP Server aaronsb/ado-mcp Enables AI assistants to interact with Azure DevOps entities like projects, repositories, work items, pull requests, and pipelines. | |
| Targetprocess MCP Server aaronsb/apptio-target-process-mcp Provides tools for interacting with Targetprocess, a project management and agile planning platform, enabling AI assistants to search, create, and update project entities with proper validation. | |
| Confluence MCP Server aaronsb/confluence-cloud-mcp Enables AI assistants to interact with Confluence Cloud for managing spaces, pages, and content via the Model Context Protocol (MCP). | |
| D-Bus MCP Server aaronsb/dbus-mcp Bridges AI assistants to Linux D-Bus for system interaction, enabling clipboard, notifications, screenshots, and service discovery with configurable security levels. | |
| Jira Insights MCP aaronsb/jira-insights-mcp An MCP server that allows management of Jira Insights (JSM) asset schemas, enabling CRUD operations for object schemas, object types, and objects through the Model Context Protocol. | |
| Semantic Notes Vault MCP aaronsb/obsidian-mcp-plugin Connects AI assistants to an Obsidian vault as a semantic knowledge graph, enabling graph navigation, semantic search, and content operations through MCP. | |
| Obsidian Semantic MCP Server aaronsb/obsidian-semantic-mcp A server that consolidates 21+ Obsidian tools into 5 intelligent operations (vault, edit, view, workflow, system) with contextual workflow hints to help AI agents effectively interact with Obsidian. | |
| TeXFlow aaronsb/texflow-mcp Enables collaborative document authoring and composition with project-based organization, transforming Markdown and LaTeX content into professional PDFs with conflict-free multi-agent editing capabilities. | |
| Think Strategies aaronsb/think-strategies Provides 10 structured reasoning strategies (Chain of Thought, ReAct, Tree of Thoughts, etc.) for complex problem-solving with session persistence, branching, and tool integration capabilities. | |
| WordPress Author MCP Server aaronsb/wordpress-mcp A personality-based MCP server that enables AI assistants to manage WordPress content through natural language by mapping human intents to semantic operations. It provides role-appropriate tools for drafting, editing, and publishing while h | |
| Jimdo docs MCP aaronspring/jimdo-docs-mcp Enables semantic search over Jimdo help documentation to find relevant information and answers. | |
| cindex aarontrmartin/code-indexer Provides a search_code tool for coding agents to perform local, offline semantic code search on a tree-sitter AST indexed codebase using GGUF embeddings, with no network calls or API keys. | |
| cv-tailor-mcp aaronugalde/cv-tailor-mcp Enables users to tailor a one-page LaTeX CV to a job posting by fetching relevant facts from a YAML file, rendering a LaTeX document from id-based selections, and compiling it to PDF, without wasting tokens on repetitive CV reads or compile | |
| Agent Fables aaronvick/agent_fables Provides offline, evidence-based preflight risk assessment for agent actions, returning revision-pinned incident patterns and unresolved verification gates to help prevent past failures from recurring. | |
| HubSpot Extended MCP Server aaronwfv/hubspotmcpextended A standalone MCP server that extends HubSpot functionality for post-call processing and pre-call preparation workflows. | |
| AWS Cost Explorer MCP Server aarora79/aws-cost-explorer-mcp-server A command-line interface and API that allows users to analyze and visualize AWS cloud spending data by enabling Claude to query AWS Cost Explorer through natural language conversations. | |
| AARO ERP MCP Server aaroyazilim/aaro-erp-mcp-server A Model Context Protocol server that enables Claude Desktop integration with AARO ERP system, allowing users to perform stock management, customer management, order processing, and other core ERP operations through natural language commands | |
| Shipi MCP aarsiv-groups/shipi-mcp-server Manage shipping workflows by creating labels, tracking packages, and scheduling carrier pickups. Compare live rates from major carriers like FedEx and UPS to optimize costs for every shipment. Organize logistical operations with a centraliz | |
| NowAIKit aartiq/nowaikit Enables AI to interact with ServiceNow instances via MCP, providing 400+ tools across all modules for automation, development, and management. | |
| jira-pilot aarul5/jira-pilot Jira Pilot is an MCP server that provides 14 tools for AI assistants to manage Jira issues, sprints, boards, and more. It enables natural language interaction with Jira through the Model Context Protocol. | |
| Google Docs & Gmail MCP Server aarushig09/aargee-mcp-server Enables appending text to Google Docs and creating Gmail drafts with interactive approval via terminal. | |
| a2a-mcp-bridge aarushitandon0/a2a-mcp-bridge Bridges Agent2Agent (A2A) remote agents to MCP clients by projecting each agent skill as a namespaced MCP tool. Enables stateless, task-oriented invocation of A2A agents through the MCP Tasks extension. | |
| weather-mcp-server aarvijayanand/weather-mcp-server A Python MCP server that provides current weather conditions and multi-day forecasts for cities worldwide using the Open-Meteo API. It exposes tools to get current weather and forecasts without requiring an API key. | |
| india-markets-mcp aarya-mhatre69/india-markets-mcp Enables AI agents and MCP clients to look up Indian equities, retrieve transparent technical signals and trend regimes, and compare symbols using public Yahoo Finance data without API keys. | |
| Axial Coach aaryaa8/axial-coach-sauna MCP server that exposes a student's cognitive profile as read-only tools for Sauna, enabling proactive coaching with gamified quests and holistic parent reports. | |
| ctfd-mcp aaryabhusal/ctfd-mcp Enables users to list CTFd challenges, read details, start/stop dynamic Docker instances, and submit flags through natural language. | |
| uktrains aaryan-gulia/uktrains MCP server for UK train journeys that resolves station names, builds journey intents, and generates pre-filled booking links, with optional fare-aware ranking. | |
| MCP Character Tools aaryan-kapoor/mcp-character-tools Provides 14+ character-level text analysis tools that give LLMs the ability to accurately count letters, analyze individual characters, and work with text at the character level—overcoming tokenization limitations. | |
| Simple Ntfy MCP Server aaryan-kapoor/simple-ntfy-mcp A lightweight MCP server for sending push notifications via ntfy.sh, supporting customizable titles, priorities, tags, and action buttons. | |
| TraceLens MCP aaryanmadan54/tracelens-mcp Enables MCP clients to query bundled synthetic logs, service metrics, and traces through three bounded read-only tools for evidence-first incident investigation. | |
| rulebook-mcp aaryanpallath/rulebook-ai Enables MCP clients to search, retrieve, and list citable sections of the official NBA rulebook, so natural-language questions can be answered with grounded rule citations. | |
| tracewise-mcp aaryanpallath/tracewise Enables MCP clients to retrieve requirements, search and read code, explore related classes, propose validated trace links, and inspect the trace matrix and coverage gaps. It supports AI-assisted requirements-to-code tracing while keeping a | |
| github-mcp aaryanptl/github-mcp Provides four GitHub superpowers (repo-scorecard, compare-repos, commit-heatmap, trending-mcp) as MCP tools with React widgets for repository health analysis, comparison, commit activity visualization, and trending MCP servers. | |
| openrouter-mcp aaryanptl/openrouter-mcp Enables AI assistants like Claude or ChatGPT to query OpenRouter's 300+ models for pricing, context length, capabilities, and rankings through tools such as model-card, compare-models, cheapest-for, cost-estimator, and usage-rankings, using | |
| Aedile aaryanrwt/aedile Enables AI coding assistants to analyze codebases locally before generating code, reducing duplication and enforcing architecture boundaries. | |
| MindGate MCP aaserag1/mindgate-mcp Enables AI coding agents to share a persistent, local-first memory of architectural decisions, conventions, bug root causes, and session handoffs, searchable via full-text ranking, so context carries across tools and sessions without any cl | |
| codex-delegate aashahin/claude-codex-delegate Enables Claude to hand off implementation tasks to OpenAI Codex models running through the Codex CLI, with tools for listing models, delegating work synchronously or in the background, collecting results, and continuing past sessions, while | |
| opencode-delegate aashahin/claude-opencode-delegate Enables Claude Code and Claude Desktop to delegate coding tasks to any model available in OpenCode while Claude remains the orchestrator, planning work, reviewing diffs, and running tests. Supports synchronous and async delegation, model se | |
| codex-opencode-orchestrator aashahin/codex-opencode-orchestrator Enables Codex to delegate bounded tasks to multiple AI model workers through a persistent OpenCode 2 service, with isolated Git worktrees and safe patch review and application. | |
| Boilerplate MCP Server aashari/boilerplate-mcp-server A production-ready foundation for developing custom Model Context Protocol (MCP) servers in TypeScript. Provides a complete layered architecture pattern, working example implementation, and comprehensive developer infrastructure to connect | |
| cve-lookup-mcp aashish-32/cve-lookup-mcp Provides live CVE data from NVD and EPSS without API key, enabling AI assistants to look up CVSS scores, search vulnerabilities, and check product CVEs. | |
| Microsoft To Do MCP aashish079/g6-mstodomcp A hardened MCP server that lets you manage Microsoft To Do tasks via natural language in Claude Desktop, with OS-keychain token storage and no client secret. | |
| Logpoint MCP Server aashish079/mcpserver-logpoint Logpoint MCP Server provides MCP endpoints for Logpoint SIEM, enabling search, incident management, alert rules, and integrations with n8n and Claude for SIEM operations. | |
| fastf1-mcp aashnakunk/fastf1-mcp A local MCP server that gives Claude (or any MCP-compatible AI client) access to Formula 1 race data. Load any session from 2018 onwards, ask questions in natural language, and get answers backed by real telemetry, timing, and strategy data | |
| Figma MCP Server aashraf09/figma-mcp Enables AI assistants to read Figma design files and automatically map responsive relationships between mobile and desktop screens to generate accurate frontend code. Eliminates manual copy-pasting by providing direct access to design token | |
| Robinhood Chain EVM MCP aashu91/robinhood-evm-mcp A zero-dependency MCP server that bridges AI agents to Robinhood Chain and Arbitrum Orbit L2 networks, enabling querying balances, simulating transactions, and signing/broadcasting EVM transactions via JSON-RPC tools. | |
| creatoros-mcp aashuchahal4-crypto/creatoros-mcp Sub-150ms clean Web-to-Markdown extraction, autonomous agent live web search, and neural speech synthesis for Claude Desktop, Cursor, and Windsurf. | |
| RecallDesk aashutoshtara/recalldesk Enables a household to move from a possible U.S. consumer-product recall match to a source-backed follow-up plan that can be reopened later, keeping product-label evidence, source dates, explicit confirmation, and user-reported progress in | |
| Amazon Orders MCP aasper03/amazon-orders-mcp Enables importing and querying historical Amazon consumer order data from multiple accounts, with tools for syncing orders, retrieving filtered order details, and managing account sessions. |
22,751–22,800 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.