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 |
|---|---|
| AdWhispr Ads MCP Server adwhispr/mcp-server See who is running ads in your space, clone a winning ad for your brand as an image or video, and launch it on Meta, Google, TikTok, X, or ChatGPT Ads. The full research, clone, launch loop from one chat in Claude, ChatGPT, or Cursor. Flat | |
| Meridian Health Claims MCP Server adwitiya-pandey/claims-mcp-server-2 Enables AI assistants to query a synthetic health-insurance claims database through five strictly read-only, parameterized MCP tools, with API-key authentication, per-tool authorization, rate limiting, and fail-closed audit logging. All acc | |
| claims-mcp-server adwitiya-pandey/claims-mcp-server-flash-baseline Enables AI assistants to securely query a synthetic health-insurance claims database through read-only, parameterized tools for claims, member histories, coverage rules, and year-to-date summaries. Includes API-key authentication, per-tool | |
| footnote adwitiyashukla/llmfeeder Enables agents to verify their own output mid-task by checking every claim against provided sources, returning supported, partial, unsupported, or contradicted verdicts with exact citations. | |
| Cloudflare Memory MCP ady133t/cloudflare-memory-mcp Provides a per-project memory layer with plain notes, semantic vector recall, and a knowledge graph, all hosted on Cloudflare's free tier. It includes a web dashboard for browsing projects and deleting them. | |
| Cortex Intelligent adyoi/mcp-cortex-intelligent Enables ordinary LLMs to be augmented fully offline — with no API keys or external services — through model-aware guardrails, exemplar retrieval, structured self-critique, compliance scoring, and an allowlisted verification runner. Also pro | |
| Adyvance MCP adyvanceofficial/adyvance-mcp Enables AI apps to search shop orders, products, customers, and stock and, with explicit approval, update orders, products, and inventory through the Model Context Protocol. | |
| ui-toolkit-mcp adzukyat/ui-toolkit-mcp Enables AI agents to inspect Unity UI Toolkit screens, examine element structure and styles, and capture screenshots without entering Play Mode or building a Player. | |
| funnelkeeper-mcp ae-labs-inc/funnelkeeper-client Exposes a Model Context Protocol interface to a growth and revenue API, enabling MCP clients to manage account data and interact with platform tools through natural-language-driven tool calls. | |
| kairosdb-mcp-server ae3e/kairosdb-mcp-server Enables querying and exploring KairosDB time-series data through natural language, including range/absolute queries, aggregations, last values, metric and tag listing, and health checks. | |
| fl-mcp ae5n/fl-mcp Local MCP server for FL Studio on macOS, enabling control of projects, transport, mixer, plugins, automation, and piano roll operations. | |
| ArkUIBuilder MCP aea91/arkuibuilder-mcp Enables AI assistants to search a catalog of ready-made HarmonyOS ArkUI components and have the server copy tested widget code and imports directly into a project, so the model writes only the page-level calls. It also surfaces the user's o | |
| bimq aec-platform/bimq Read-only BIM query server for agents: structured, policy-bounded queries on IFC/gbXML models with deterministic cited results. | |
| Teams Messenger MCP App aech-ai/mcp-teams-test A Model Context Protocol server that bridges Microsoft Teams with MCP-compatible clients (LLMs, agentic frameworks, CLI), enabling chat integration, message search, and event streaming without traditional REST API endpoints. | |
| Codex Capability Bridge aecru/codex-capability-bridge An MCP server that enables Claude to discover and delegate tasks to local Codex Skills and plugins, bridging Claude's natural language understanding with Codex's execution capabilities. | |
| PubMed MCP Server aeghnnsw/pubmed-mcp Enables searching PubMed's biomedical literature database and retrieving article metadata, abstracts, and full content through the E-utilities API. Supports advanced queries, batch operations, and multiple output formats with automatic rate | |
| tiny-loki-mcp aegir-tech/tiny-loki-mcp Enables read-only querying of Grafana Loki logs through tools like label discovery, LogQL queries, and recent log retrieval, without requiring knowledge of the Loki API. | |
| @aegis-ai/mcp-scraper aegis-ai-cooperative/mcp-scraper Enables intelligent web scraping with support for static pages, JavaScript-rendered SPAs, and natural language data extraction. | |
| mcp-toolselect aegis-ai-cooperative/mcp-toolselect An MCP server that recommends specific tools for tasks by learning from usage patterns and historical success rates. It enables users to register tool capabilities and provides ranked recommendations that adapt based on feedback and executi | |
| Aegis-ZK aegis-zk/aegisprotocol On-chain trust verification for AI agent tools. Agents query skill attestations, audit levels, and risk scores before running third-party MCP servers, so you know what's safe before you execute. | |
| TS-MCP aegisnetinc/ts-mcp An MCP server for conversational FHIR testing that integrates with the Touchstone platform. It enables users to launch test executions, monitor status, and retrieve detailed results through natural language commands. | |
| AEGIS MCP Server aegisprivacy/aegis-mcp Provides AI agents with private, pay-per-request internet access through residential/datacenter exit nodes, settling payments in USDC on Solana, along with key governance and self-audit tools. | |
| AegisX MCP aegisx-platform/aegisx-mcp Provides AI assistants with access to AegisX UI components, CRUD generator commands, development patterns, and API contract discovery tools. It enables developers to browse component documentation, build generation commands, and test authen | |
| Obsidian Elite RAG MCP Server aegntic/aegntic-mcp Transforms Obsidian vaults into AI-powered knowledge bases using multi-layer RAG with advanced knowledge graph integration, enabling semantic search, entity extraction, and relationship mapping across personal notes. | |
| swagger-codegen-mcp aehyok/swagger-codegen-mcp Automatically generates TypeScript API code from Swagger/OpenAPI documentation. Supports listing services, tags, endpoints, and generating code by tag or endpoint. | |
| HSK Studio MCP aeither/hsk-studio-mcp Enables AI agents to look up HSK vocabulary, retrieve graded Chinese readings, and estimate the HSK level of Chinese text, with no API key required. | |
| PostgreSQL MCP Server aeiyannn/postgree-mcp Enables AI assistants to query and manage local PostgreSQL databases through SQL execution and schema exploration tools. It supports both read-only queries and write operations including table creation and data modification via natural lang | |
| MSSQL MCP Server (Streamable HTTP) aekanun2020/fixed-2026-mssql-mcp-server-streamablehttp Provides MCP tools to query and inspect Microsoft SQL Server databases via a Streamable HTTP transport, including tools for running T-SQL queries, previewing tables, and retrieving schema context. | |
| RAG MCP Server with Streamable HTTP aekanun2020/fixed-2026-rag-mcp-server-streamablehttp Enables hybrid search (BM25 + semantic with RRF) over documentation, with Thai language support. It exposes MCP tools for adding documents and searching via Qdrant and Ollama/OpenAI, using a stateless Streamable HTTP transport. | |
| PDPA GraphRAG MCP Server aekanun2020/pdpa-graphrag-mcp Enables agents to answer questions about Thailand's Personal Data Protection Act by combining hybrid dense/sparse vector retrieval with knowledge-graph traversal over a 190-node graph of the statute's 96 sections. Exposes tools for hybrid s | |
| TaskFlow MCP aekkaratjerasuk/taskflow-mcp A task management Model Context Protocol server that helps break down user requests into manageable tasks with subtasks, dependencies, and notes, while enforcing a structured workflow with user approval steps. | |
| herdr-mcp aelaguiz/herdr-mcp Enables coding agents to control and inspect a running Herdr terminal session, including listing workspaces, tabs, panes, and agents, reading pane output, prompting agents, sending keys and commands, waiting for output or state, and splitti | |
| URL Fetch MCP aelaguiz/mcp-url-fetch A Model Context Protocol (MCP) server that enables Claude or other LLMs to fetch content from URLs, supporting HTML, JSON, text, and images with configurable request parameters. | |
| aigently aelbuni/aigently-catalog Securely feeds summarized expert security rules into your coding assistance Claude Code, Cursor, etc — zero config, no API key. | |
| aelf-node-skill aelfproject/aelf-node-skill Enables interaction with AElf blockchain nodes, allowing users to read chain status, execute contract transactions, and manage custom nodes through MCP, CLI, or SDK. | |
| cap-mcp-apps aelghanam/mcp-apps Enriches CAP Node.js MCP query tool results with an interactive UI5 Web Components table when the host supports MCP Apps, and lets annotated service actions appear as toolbar or row buttons that invoke the MCP call tool. | |
| socseal aeliana139/socseal-mcp MCP server for the SOCseal sovereign rail — verify atomic SOC⇄BTC settlement proofs, read
oracle/venue state, walk the no-KYC trade door. Live: socseal.xyz/proof | |
| sophia-house-mcp aeliana139/sophia-house-mcp Read-only MCP (stdio) server for the socseal settlement venue — prove a payment MINED on-chain, read
the public settlement book, anchor receipts. No KYC, no custody, fail-closed. Experimental, R=0
external payers. | |
| Aelios aelios-project/aelios Self-hosted long-term memory gateway for AI clients, deployed to your own Cloudflare account (Workers + D1 + Vectorize). It captures conversations, consolidates them overnight, and exposes MCP tools to search, recall and write memories from | |
| MCP Math Server aem-edge-delivery/mcp A Node.js server that processes mathematical calculations and natural language math queries through RESTful API endpoints. | |
| gpt-image-mcp aemeath-projects/gpt-image-mcp Enables LLM clients to invoke standardized MCP tools across stdio, HTTP, and Cloudflare Workers, returning Markdown and structured results; the current scaffold includes an echo tool, with GPT Image generation and editing tools planned. | |
| TextIn xParse MCP Server aenron/textin-mcp Enables document parsing via TextIn xParse API, supporting synchronous and asynchronous jobs with configurable options. | |
| aeo-engine-aeo-report aeoengine/best-ai-search-agency-aeo-report Enables agents to run free Answer Engine Optimization and AI visibility audits for a domain across platforms such as ChatGPT, Google AI Overviews, and Perplexity, then poll status and retrieve a shareable report URL plus structured summary. | |
| Repomix MCP Server aeolun/repomix-mcp An MCP server that packs repositories into AI-friendly files using the Repomix tool, supporting local and remote repositories with size estimation and compression. It enables users to efficiently feed entire codebases into AI models while m | |
| SearXNG Model Context Protocol Server aeon-seraph/searxng-mcp A server that enables language models to perform web searches through SearXNG using the Model Context Protocol standard. | |
| htb-app-mcp aeondave/htb-app-mcp Enables interaction with Hack The Box App services including machines, challenges, sherlocks, and more through the HTB API v4. | |
| cocktail-recipes-mcp aephir/cocktail-recipes-mcp A Dockerized Python MCP server that provides tools to manage cocktail recipes, ingredients, and related operations via the Aephir/cocktail-recipes REST API, with dry-run safety defaults and automatic re-authentication. | |
| Trello MCP Server aepod/trello-mcp Enables interaction with Trello boards, lists, and cards through the Trello REST API. Supports board management, card operations, member management, labels, and checklists through natural language. | |
| mcp-netcoredbg aerialbyte/mcp-netcoredbg An MCP server that enables AI agents to debug .NET applications using netcoredbg. It supports core debugging tasks like setting breakpoints, stepping through code, and inspecting variables or stack traces. | |
| Fixwise aeriesagi/fixwise Enables an Alexa+ user to report a household or street fault by voice and walk through safety shut-off steps, a municipal case, priced repair quotes from local suppliers, and a booking that is only confirmed after explicit approval. It also |
24,051–24,100 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.