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 |
|---|---|
| flickr-mcp-server chochinlu/flickr-mcp-server An MCP server that integrates AI assistants with the Flickr API, enabling management of photos, albums, groups, and contacts via natural language commands. | |
| PIPA MCP choco9527/pipa-mcp Enables AI agents to manage to-dos, lists, schedules, recurring tasks, and notes through standard stdio MCP tools, sharing authentication with the companion CLI and discovering business tools after login. | |
| Mi-Mi-Mi MCP chocoboy-dev/-mi-mi-mi-mcp- Adds emotional reactions (emojis, text, sounds) to code generation in opencode, with automatic or manual selection based on user sentiment. | |
| chocodata-mcp chocodata-com/chocodata-mcp MCP server for the Chocodata web scraping API. Enables agents to scrape live product prices, search results, and social profiles without writing glue code. | |
| FatSecret MCP Server chocotonic/fatsecret-mcp-server Enables interaction with the FatSecret Platform API and member recipe/RDI workflows, including food data, diaries, and recipe operations through profile-based tool exposure. | |
| otterai-mcp chocotonic/otterai-mcp Enables inspecting and organizing Otter.ai conversations, including listing folders, retrieving unsorted speeches and transcripts, and moving speeches with verification. | |
| Exa Ultra MCP chocowarsky/exa-ultra-mcp Enables AI agents to search the web, fetch page contents, find similar pages, get cited answers, and run research agent jobs across the full Exa API. Adds multi-key failover, per-key budget guarding, shared cross-process state, and selectab | |
| NCP MCP Server choec77/mcp Enables conversational management of Naver Cloud Platform infrastructure through Claude Desktop, allowing users to create, query, and manage cloud resources like servers, VPCs, load balancers, and databases using natural language. | |
| IDA Pro MCP Server choffmann743/mcp-server-idapro Enables AI assistants to interact with IDA Pro for reverse engineering and binary analysis, including executing Python scripts, retrieving strings/imports/exports/functions, searching immediates/text/byte sequences, and getting disassembly. | |
| Simple MCP Server chohi22/mcp A Python Flask-based Model Context Protocol server that provides basic tools including hello_world, calculate, and get_time functions through stable HTTP endpoints. | |
| filter-mcp-server chohirin/filter-mcp-server Compares approximate filter data structures (Bloom, Counting Bloom, Cuckoo, SuRF) via MCP | |
| searxNcrawl choi77333/searxncrawl Enables AI agents to search the web through configured providers and crawl single pages or entire sites into clean Markdown or JSON, including authenticated crawls, filtering, CLI/Python use, and STDIO or HTTP transport. | |
| nse-bse-indian-stock-market-data-mcp choi79656/nse-bse-indian-stock-market-data-mcp Gives AI assistants live, structured coverage of 8,200+ Indian listed equities through 55 tools for quotes, financials, a 326-ratio screener, technicals, FII/DII flows, option chains and IV, corporate filings, IPOs and portfolio P&L. It con | |
| Choice Wiki MCP choice-hub/choice-wiki-mcp Provides Claude with a knowledge base about the Choice restaurant platform, enabling natural language queries about products, pricing, integrations, and features. | |
| Lens choidonghee/ktds_lens Integrated web search MCP server with multi-engine parallel execution, automatic fallback, BM25 relevance filtering, and content extraction. Supports DuckDuckGo and Naver (news, web, encyclopedia) searches. | |
| startup-law-mcp choihello/startup-law-mcp Integrates Korean startup laws (19 curated laws) and K-Startup support programs, enabling legal article search, citation verification, reference tracking, and program lookup with real-time status. | |
| n2-qln choihyunsus/n2-qln QLN is a semantic tool router that enables AI agents to access thousands of tools through a single MCP interface, with sub-5ms search and automatic fallback. | |
| Soul choihyunsus/soul Gives AI agents persistent memory, handoffs, and shared context across sessions, enabling seamless continuity and multi-agent collaboration. | |
| Packet Analyzer MCP choihyuunmin/packet-analyzer-mcp Enables network packet capture, analysis, and threat detection via distributed client-server architecture with RabbitMQ, PostgreSQL, and external security APIs (NVD CVE, MITRE ATT&CK, AbuseIPDB). | |
| Wedding Manager MCP choijay0310-spec/wedding-manager-mcp Enables users to manage wedding preparation tasks including timeline generation, budget review, vendor quote comparison, role assignment briefs, and drafting messages for family, vendors, and friends. | |
| MySQL Hub MCP Server choijun-0613/mysql-hub-mcp A Model Context Protocol server that enables natural language querying of MySQL databases, supporting both HTTP-based communication and MCP stdio protocol. | |
| jira-mcp choing-dev/jira-mcp Enables AI agents to interact with Jira Cloud and Confluence through natural language, performing JQL searches, issue management, and Confluence page creation. | |
| MCP File Contents Reader choipureum/mcp-file-contents-reader Enables reading and analysis of PDF, Excel, Word, and PowerPoint files through the Model Context Protocol, supporting content extraction, document search, and file upload. | |
| blender-fx-mcp choisam4u-creator/blender-fx-mcp Enables AI assistants to create Blender FX such as destruction, explosions, water, fire, particles, wind, ocean, and cloth from natural language instructions, including physics simulation and preview rendering. | |
| jade-mcp choiyounggi/jade-mcp Enables MCP clients such as Claude Code to query JADE eHR attendance, leave balances, and recent applications, and to prepare, preview, and commit punch records, vacation requests, birthday half-days, and monthly work schedules. | |
| chem-inventory-mcp choizeus02/chem-inventory-mcp MCP server for managing chemical inventory with SQLite. Enables search, detail view, stock deduction, usage history, and communication testing. | |
| timesfm-mcp chokukil/timesfm-mcp Local MCP server for GPU-backed TimesFM 2.5 forecasting, enabling zero-shot time-series forecasting, covariate forecasting, anomaly detection, and CSV forecasting via MCP tools. | |
| Claude Desktop Research MCP Server cholhwanjung/research-mcp Enables searching, retrieving, and reading academic papers from arXiv while analyzing citation networks via Semantic Scholar. It allows users to extract full-text content from PDFs and explore references or citations sorted by impact. | |
| Engram cholland00/engram Enables AI coding agents to query a local structural code graph, inspect code relationships and recorded mistakes, and retrieve focused project context before reading entire files. | |
| zhihui-xiezuo-mcp chongming1994/zhihui-xiezuo Lets external MCP clients attach to an already-running local DeepSeek Harness web instance to list and inspect sessions, explicitly bind a target, deliver a task, and wait for that turn's final reply. Read-only tools are always available, w | |
| AI Humanizer MCP Server chongzixuan-ai/humanizer-mcp-server Detects AI-generated content and transforms robotic text into natural, human-like writing while improving grammar, readability, and preserving key terminology. | |
| Screenshot Website Fast chongzixuan-ai/mcp-server-website Captures high-quality screenshots and screencasts of web pages, automatically tiling full pages into 1072x1072 chunks optimized for Claude Vision API and other AI vision models. | |
| Bing Flights MCP Server chonseng/bing-flights-mcp Enables flight search and price comparison by scraping flight information from Bing Flights. Supports one-way and round-trip searches with customizable passenger counts, cabin classes, and booking details. | |
| peacelingo-stt-bench chopeace/peacelingo-stt-bench Enables AI agents to send the same short audio clip to multiple speech-to-text providers and compare transcripts, CER/WER, latency, and estimated cost. It also lets agents check which providers are configured and estimate costs from a built | |
| agent-native-crm chopinfeng/agent-native-crm Enables AI sales agents to interact with a CRM via event-sourced actions, identity resolution, guard checks, and an approval inbox, managing communications and tasks while adhering to compliance rules. | |
| jira-cli-mcp choplin/jira-cli-mcp MCP server that wraps the jira-cli command-line tool to enable AI assistants to interact with Jira. | |
| MCP Gemini CLI choplin/mcp-gemini-cli Wraps Google's Gemini CLI to expose search, chat, and file analysis tools via the Model Context Protocol for AI assistants. | |
| Sophia Stack MCP chorozion/sophia-stack Enables external AI agents to edit and manage a self-hosted website via a token-gated MCP server, including page content, data, media, and sandboxed functions with validation and rollback. | |
| claude-opencode-mcp-v2 choruzo/claude-opencode-mcp-v2 Enables Claude Code to delegate software-engineering tasks to OpenCode agents running in the same workspace/worktree, with the model and provider chosen per agent. Exposes tools for task delegation, persistent sessions, diffs, and agent lis | |
| EWS Mailbox MCP Server chosomeister/ews-mailbox-mcp Gives AI clients controlled access to one or more Microsoft Exchange mailboxes over EWS to read, search, file, flag, send, and manage inbox rules and calendars. Multiple mailboxes are served from one endpoint with per-account read-only, sen | |
| collectui-mcp choterifa/collectui-mcp Enables discovery, exploration, and inspection of mobile app UI designs, microinteractions, animations, and UX/UI flows from Collect UI, with fast direct access to video variants and metadata. | |
| Azure Security MCP Agent chouaieb161/security-mcp-agent An AI-powered security agent that utilizes MCP tools and Groq LLMs to analyze Azure infrastructure, audit security groups, and identify storage misconfigurations. It enables users to perform natural language security assessments and ensure | |
| Haloscan MCP Server chouayb123/mcp A Model Context Protocol server that exposes Haloscan SEO API functionality, allowing users to access keyword insights, domain analysis, and competitor research through Claude for Desktop and other MCP-compatible clients. | |
| MD3-Docs MCP chouchiu/md3-docs-mcp Provides AI assistants access to live Material Design 3 documentation including Foundations, Styles, and Components, returning official content as Markdown. | |
| SysMLEdge MCP chouswei/sysmledge Exposes a SysML model as a GQL-queryable graph projection over streamable HTTP, letting agents read the live model at a specific git revision without grep dumps or stale trees. Agents can check revision status, run GQL reads, and propose ch | |
| RemoteShell MCP chouzz/remoteshell-mcp A server that enables LLMs to securely manage and execute commands on remote SSH servers. | |
| @munispot/mcp chowdhury-raj/munispot-mcp Enables AI assistants to search, profile, and compare 20,000+ U.S. municipalities, returning financial health scores, budget and debt figures, and economic or demographic indicators. Supports historical score trends across fiscal years and | |
| faq-rag chowgi/glean-rag-mcp Enables answering natural-language questions from FAQ documents using vector search and LLM generation via an MCP tool. | |
| planpatch chowol0309/planpatch Enables reading a household's tasks, availability, and saved schedule, previewing alternative recovery plans when a work shift changes, and retrieving saved proposals for review. | |
| manusia chozzz/manusia Enables AI agents to request vetted human assistance over MCP, including estimating, posting, polling, canceling, listing tasks, and uploading files for answers. |
38,551–38,600 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.