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 |
|---|---|
| nano-banana-mcp fahmidme/nano-banana-mcp MCP server that generates images using Gemini 3 Pro Image on Vertex AI, with support for reference images, task management, and GCS integration. | |
| deploy-check fahmiwol/deploy-check-mcp Enables agents to verify that a deploy actually worked by checking pages, links, and comparing environments, catching blank 200 responses, broken links, stray noindex, and staging that never updated. | |
| Weather MCP fahrenheitresearch/weather-mcp Provides 12 weather tools for conditions, forecasts, alerts, model imagery, radar, and 205 meteorological calculations, enabling weather data access and analysis through Claude Code. | |
| SOL Forge fahrur-rozi-dev/sol-forge An MCP server that enables AI agents to interact with the Solana blockchain through 20 tools for wallet management, SPL token operations, blockchain exploration, and DeFi integration via Jupiter. | |
| Codex ↔ Claude Code / DeepSeek MCP Bridge fahuikongjian/codex-claude-mcp-bridge Enables bidirectional, asynchronous task delegation between Codex and Claude Code, plus optional DeepSeek API consultations, with workspace locking, recursion protection, and bounded permissions. | |
| fuzzy-match-mcp faiaz000/fuzzy_match_mcp A Python MCP server for deterministic fuzzy text matching using RapidFuzz. It enables text normalization, string comparison, best-match ranking, duplicate grouping, and match explanation via configurable profiles and strategies. | |
| financial-assistant faiez123tariq/financial-assistant Enables natural language stock price queries, leveraging MCP tools to fetch real-time market data from EODHD and present results through a Gradio interface. | |
| nice fainir/nice Provides a secure MCP gateway for AI agents to access APIs without exposing raw credentials, with scoped access, audit logging, and OAuth support. | |
| Materials Project MCP fair2wise/materials_project_mcp A tool for querying and analyzing materials data from the Materials Project database using natural language prompts, enabling materials scientists to explore properties, structures, and compositions of materials through conversational inter | |
| procurement-mailer-mcp fairconsult-corp/procurement-mailer-mcp Enables an SAP Joule agent to read and send email from a scoped Microsoft Exchange mailbox via MCP tools, translating tool calls into Microsoft Graph requests. | |
| ssh-mcp fairmont77/ssh-mcp Provides persistent SSH access to servers using OpenSSH ControlMaster multiplexing, allowing AI agents to run commands on registered hosts by name without re-entering credentials. | |
| Suricata MCP fairyming/suricata_mcp An MCP server for validating Suricata rule syntax and testing rules against pcap files to verify alert matching. It automates the testing process by running Suricata and parsing generated alert logs to confirm signature IDs. | |
| TShark MCP fairyming/tshark_mcp An MCP server for analyzing network traffic and pcap files using tshark. It enables users to list TCP streams, extract application-layer payloads, and perform packet analysis with BPF filters. | |
| mesh fais649/paseo-mesh Enables agents to discover peers on the same host or across connected hosts, exchange messages with them, wait for their replies, and spin up new agents with a task. Messages are tagged with the sender's address so recipients can answer bac | |
| VaultPilot faisal-hn/vaultpilot Enables Cursor and Claude to search and read an Obsidian vault, capture inbox/learning/work notes, append daily logs, distill chats, and manage structured bug sessions with safety controls. | |
| IMAP Mail MCP faisalfehad/imap-mail-mcp Enables LLM clients to read and search email via IMAP with tools for listing folders, searching messages, and fetching message content. It supports pagination, snippets, and thread context, and is designed for local AI workflows. | |
| Termux Notification List MCP Server faisalhakim47/termux-notification-list-mcp Enables AI agents to monitor and read Android notifications in real-time via Termux. Provides access to current notifications with filtering capabilities and real-time streaming of new notifications as they arrive. | |
| Obsidian MCP Server faisalhossainnyc/obsidian-mcp-server Enables AI assistants to manage Obsidian vaults programmatically with 28 tools for reading, writing, editing, and analyzing notes. | |
| Spec Forge MCP faisalkcmvp/spec-forge-mcp A NestJS MCP server that extracts tables from documents (PDF, etc.) into a single JSON file using OpenRouter's Claude Haiku model. | |
| multi-site-monitor faisibash-oss/multi-site-monitor An MCP server that pulls PageSpeed Insights and Google Search Console data across multiple owned sites, enabling cross-site performance reports and synthesis via Claude. | |
| EU Open Banking MCP faisonhd/ing-mcp Enables read-only access to personal European bank accounts through Enable Banking, allowing MCP clients to list accounts, retrieve balances, search and summarize transactions, and estimate spending with bounded, privacy-preserving tools. | |
| Echo Prayer MCP Server faith-tools/echo-mcp-server Provides guided prayers, semantic search, and pastoral care tools (encouragement, condolence, advice) via a read-only database without authentication. | |
| TuskPoint Checkpoints faithabiodun/tuskpoint MCP server for managing verifiable LangGraph agent state on Walrus, enabling exact checkpoint save/load/resume and semantic search via MemWal. | |
| NicePay MCP Server faithcoderlab/nicepay-mcp Enables developers to search and access NicePay payment API documentation, including endpoint details, code samples, and SDK method information through natural language queries. | |
| psirt-exposure faithere1/psirt-exposure Enables AI assistants to list devices and rules, check each device against Cisco PSIRT advisories using IOS XE configurations, and produce evidence-backed reports through the MCP stdio interface. | |
| PT Tutor faithere1/pt-tutor-mcp Enables an MCP client to inspect a live Cisco Packet Tracer lab read-only — topology, device state, and reachability diagnoses — and to deliver graduated hints that guide students to locate and fix faults themselves rather than having the l | |
| SDN Guardian MCP faithere1/sdn-guardian-mcp Enables an LLM agent to defend a software-defined Cisco network through an OODA loop of tools: it summarizes traffic anomalies, detects configuration drift, dry-runs candidate flow rules for conflicts and lockouts, and pushes validated poli | |
| discoveree-desktop faithfourstar/discoveree-desktop Provides a local, agent-maintained product context layer over MCP, serving structured strategy, competitor, customer feedback, and feature inventory data to any AI tool such as Claude, Cursor, or ChatGPT, with local data storage, bring-your | |
| Palm92 Governed Agent MCP faithfulord1/palm92-governed-agent-mcp Provides governed tools for evaluating proposed agent actions against policy, classifying risk, and creating structured governance and audit records, while pausing consequential steps for explicit human approval. This lets agentic workflows | |
| global-hybrid-mcp faithlegend1995/global-hybrid-mcp Enables stable, traceable hybrid AI workflows through MCP, with deterministic task contracts, bounded specialists, independent visual judging, persistent evidence, and local run tracing for image and fact tasks. | |
| mail-mcp faixiang/mail-mcp Enables AI agents to access and, when explicitly enabled, send email across multiple accounts and providers through unified tools with configurable read-only or full-write profiles, sanitized inbound content, and policy-controlled outbound | |
| Dify MCP Server faiz-gear/dify-mcp-server-ts Enables the conversion of Dify applications into Model Context Protocol tools, supporting streaming responses and configured via YAML. | |
| result-analyzer-mcp faiz746/result-analyzer-mcp MCP server for querying student information, validating result data, and analyzing student results from a local database. | |
| Google Classroom MCP Server faizan45640/google-classroom-mcp-server An MCP server that enables AI assistants to access and interact with Google Classroom data, allowing users to view courses, course details, and assignments through natural language commands. | |
| PostEx MCP Server faizan45640/postex-mcp-server Provides tools to interact with the PostEx Merchant API for order creation, tracking, and management. | |
| prompt-studio-mcp faizanahmedsy/prompt-studio-mcp Lets Claude read and write Prompt Studio projects as Flow text, with version history and a repo-synced .flow file. | |
| muhawir faizanakhan786/muhawir Enables bilingual Arabic/English knowledge assistance through MCP, including knowledge base inspection, document retrieval, arithmetic evaluation, and Hijri-Gregorian calendar conversion. | |
| MCP Tools Server faizannasim/first-mcp-project This server enables basic arithmetic addition, random number generation, in-memory todo task management, and access to server information over the Model Context Protocol. | |
| Pharma MCP faizanreza-cs/pharma-mcp Enables AI assistants to query FDA drug labels, FAERS adverse event reports, recalls, and ClinicalTrials.gov trials, and to compute pharmacovigilance signal metrics such as PRR/ROR with confidence intervals and flags. It also provides a dru | |
| workspace-ai faizansid3/mcp-integration-platform Enables AI assistants to interact with Gmail accounts via MCP, providing tools for listing labels, searching, reading, drafting, and sending emails with OAuth2 authentication. | |
| mcp-beaker faizbawa/mcp-beaker MCP server for Beaker lab automation, enabling system provisioning, job management, distro discovery, and failure diagnosis through 25 tools. | |
| agentcart faiziimam/agentcart An open-source MCP server that lets an AI agent read product pages, fill carts, and reach payment, then hands the user a UPI QR to approve; it also supports optional capped auto-pay from a pre-funded balance while keeping payment credential | |
| Flyrel MCP faiznazeer/flyrel-mcp Enables agents to inspect brokerage data through read-only Zerodha Kite and Alpaca adapters and exercise order lifecycle workflows in a local synthetic paper sandbox for Indian and US cash equities. | |
| result-analyzer-mcp faizullahbalti29/result-analyzer-mcp MCP server for querying, validating, and analyzing student result data from a local database. | |
| AetherServe faizzansiddiq/aetherserve An operations layer for MCP servers that adds metrics, health checks, rate limiting, structured logging, and lifecycle hooks. | |
| GearTrade MCP Server fajararrizki/mcp-technical-analysis Enables AI assistants to perform cryptocurrency trading analysis and execution with 38+ tools including real-time market data, technical indicators, risk management, and support for both paper trading and live execution on Hyperliquid. | |
| Selat fajarhide/selat Centralizes OAuth connections and tool access for AI agents, providing a single credential to call multiple services via MCP and REST with consistent errors and pagination. | |
| jira-mcp fajarmf/jira-mcp A Model Context Protocol (MCP) server that integrates with Atlassian Jira to search issues, retrieve details, access comments, create new issues, and update issues. | |
| slite-mcp fajarmf/slite-mcp Integrates with Slite's API to search, retrieve, create, and edit notes via the MCP protocol. | |
| MyDot MCP fakeamirulhakim/mydot_mcp Enables Claude clients to connect to an ERPNext site as a remote MCP server with OAuth sign-in, exposing tools to discover DocTypes, read and write documents, run reports, and call whitelisted methods under the signed-in user's permissions. |
49,451–49,500 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.