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 |
|---|---|
| OPTIX: Operational Platform for Threat Intelligence Exploration adamwaldie/optix-mcp A standalone Python/FastAPI server that implements the Model Context Protocol (MCP) for the OPTIX threat intelligence platform. It exposes 26 analyst-friendly tools that AI assistants and programmatic consumers can use to query threat feeds | |
| MyFitnessPal MCP Server adamwalt/myfitnesspal-mcp-python Enables AI assistants to interact with MyFitnessPal data including food diary, exercises, body measurements, nutrition goals, and water intake through natural language. | |
| Oura MCP Server (Python) adamwalt/oura-ring-mcp-python Enables AI assistants to access Oura Ring health data including sleep, readiness, activity, heart rate, and workouts through MCP tools with OAuth2 authentication. | |
| JobHunt Tracker adamwardecki/job-tracker-mcp Provides a local, append-only SQLite tracker for a disciplined job search, exposing narrow tools that move roles through a found-to-offer state machine while recording events, verification evidence, application confirmations and daily repor | |
| MCP Proxy Server adamwattis/mcp-proxy-server A central hub that aggregates multiple MCP resource servers into a single unified interface, enabling users to access tools and capabilities from multiple backend servers through one connection point. | |
| Resource Hub Server adamwattis/resource-hub-server An MCP server that connects to the Resource Hub, allowing centralized configuration and management of tools and resources across different MCP environments. | |
| NanoBananaPro adamydwang/genai-mcp Use Nano Banana Pro to generate image from text prompt and edit image | |
| alma-corpus-mcp adamzacharia/alma-mcp Enables users to search and compare ALMA papers’ methods, recipes, settings, software usage, and parameter statistics, with citations and evidence pointers for verification. | |
| GW MCP Server adamzacharia/gw_mcp An MCP server providing tools to query gravitational wave data from GraceDB and GWOSC, enabling natural language queries about GW events. | |
| quasar-mcp adamzacharia/quasar-mcp It equips LLM clients with roughly 200 live astronomy research tools spanning ALMA/NRAO, MAST, ESO, VO archives, SIMBAD/NED/VizieR, Splatalogue, NASA ADS, Data Lab, ZTF and imaging, with plots and images returned inline. Users can search an | |
| icloud-mcp adamzaidi/icloud-mcp An MCP server that connects Claude to iCloud Mail for reading, searching, sending, and organizing emails through natural language. It supports advanced management tasks like bulk operations, mailbox organization, and automated rules for inb | |
| kingdee-k3cloud-mcp adamzhang1987/kingdee-k3cloud-mcp MCP server for Kingdee K3Cloud ERP that enables AI assistants to query and operate ERP data via natural language through the Model Context Protocol. | |
| MCP Contractor adaniki-dev/contract-mcp A contract linter for AI agents that uses structured YAML contracts to define dependencies, business rules, and exports, enabling agents to work without breaking project conventions. | |
| CoolPlugz adaoctopus/coreflows-mcp Enables autonomous Jira-to-PR workflows in Claude Code by fetching context from Jira, GitHub, Notion, and Slack, building structured prompts, and handling branch pushes, PR creation, CI polling, and task completion. | |
| OpenWebUI MCP Server adaofeliz/open-webui-mcp A bridge between LLMs and OpenWebUI workspaces that enables managing projects, notes, and knowledge bases. It supports safe project configuration updates through a propose-evaluate-apply workflow and direct file uploads to knowledge bases. | |
| obsidian-vault-mcp adaptive-edge/obsidian-vault-mcp Enables Claude to read, write, search, and manage an Obsidian vault with tools for notes, tags, folders, and full-text search. | |
| skills-master-mcp adarc8/skills-master-mcp Connects AI coding agents to the SkillsMP marketplace, allowing users to search, read, and install over 8,000 community-made skills. It enables agents to gain new capabilities either through on-the-spot instruction or permanent installation | |
| MCP SQL Server Pro adarsh-bhayani-simform/mcp-sqlserver-pro Provides direct SQL query access to Microsoft SQL Server databases with full CRUD operations, enabling AI assistants to execute queries, modify data, and manage database objects through a simplified interface. | |
| devctl-mcp adarsh-devappsys/devctl-mcp An MCP server that lets Claude manage long-running development processes across frameworks like Flutter, Next.js, Spring Boot, and Vite, with lifecycle control, log streaming, and hot reload support. | |
| Aegis adarsh14734/aegis Local security layer for AI coding agents: MCP policy proxy, kernel sandbox, tamper-evident audit log | |
| Groq MCP Document Assistant adarsh152004/mcp-pdf A persistent document management and research assistant powered by Groq, enabling AI-driven document analysis, professional formatting, and long-term memory across sessions. | |
| IMDB MCP Server adarsh2001-dot/imdb-mcp Enables LLMs to search movies and people, retrieve movie details, cast lists, and the IMDB Top 250 through JSON-RPC or MCP protocol. | |
| Chess Detective MCP Server adarsh4777/chess-detective-agent Enables chess position analysis, legal move investigation, move comparison, and PGN game reconstruction through MCP tools. | |
| OpenObserve MCP Server adarshba/openobserve-mcp Enables querying logs, traces, and metrics from multiple OpenObserve instances via MCP tools, with parallel execution, batching, and caching. | |
| Resume MCP Server adarshcharjan/resume-mcp-server Exposes a structured professional resume as a set of AI-queryable tools, enabling AI clients like Claude Desktop to query summary, experience, skills, projects, and tailor resumes to job descriptions. | |
| MCP Server Deployment Demo adarshchaudhary03/mcp-server-deployment A demonstration MCP server that provides a simple addition tool for learning how to create and deploy servers following the Model-Context-Protocol specification. Serves as a basic example for developers getting started with MCP server devel | |
| AGENTIQ adarshcod30/agentiq Enables AI agents to perform API testing and security validation through a permission-gated, SSRF-protected, audited MCP tool layer. | |
| MCP Weather Server adarshem/mcp-server-learn A Model Context Protocol server that provides tools to fetch weather alerts for US states and forecasts based on latitude/longitude coordinates using the US National Weather Service API. | |
| RishiAI MCP Server adarshj322/rishi-ai-mcp A Vedic astrology MCP server providing tools for natal charts, transits, compatibility, muhurtha, and career analysis using the DashaFlow engine. | |
| Relay adarshp14/relay Enables AI agents to access a unified catalog of tools from various APIs (OpenAPI, GraphQL, MCP, Google Discovery) through the MCP protocol. | |
| PPAP Review Workbench adarshrajds/ppap-review-mcp An MCP server that enables deterministic supplier quality engineer review of PPAP cases through structured state management, tools, and an interactive workbench UI within Langdock, with human approval authority. | |
| AI-Scholarly-Mode adarshrkumar/ai-scholarly-mode Enables AI assistants to search and retrieve peer-reviewed academic articles exclusively from Springer Nature's open access collection. It provides a specialized mode for research-driven conversations, allowing users to toggle scholarly-onl | |
| TaskFlow MCP adarshvijay101/taskflow-mcp A production-ready MCP server for task management, enabling LLMs to create, list, and manage tasks via tools and resources, with support for local stdio and cloud Streamable HTTP deployment. | |
| Capillus Hermes MCP adastra-labs/capillus-hermes-mcp Enables tracking and monitoring of Capillus Bluetooth caps for treatment sessions, adherence, and device status using local BLE data, without requiring cloud APIs. | |
| cdgmcp adathouse/cdgmcp Exposes a Congress.gov-style legislative GraphQL API to MCP clients, enabling querying bills, actions, committee activities, and cosponsors via natural language. | |
| Browser Bridge MCP adbarc92/mcp-browser-bridge MCP server that gives AI coding assistants direct access to the browser — navigate, click, fill forms, run JavaScript, take screenshots, and read page content. | |
| meta-ads-mcp adbloop/meta-ads-mcp Create and manage Facebook & Instagram (Meta) ad campaigns from Claude, ChatGPT & Cursor — bulk creation, multi-account, and spend guardrails. Hosted, Meta Verified Tech Provider. | |
| localizely-mcp adborroto/localizely-mcp MCP server for Localizely that enables managing translation files and projects from any MCP client via natural language. | |
| semantic-search-mcp adborroto/semantic-search-mcp A tiny RAG-lite retrieval engine that indexes files on disk and provides semantic search via MCP, returning relevant text chunks (file, line, score) without generating answers. | |
| QRadar MCP Server addanuj/qradar-mcp-server Bridges LLMs with IBM QRadar SIEM by providing access to over 728 REST API endpoints through four intelligent tool definitions. It enables security analysts to interact with offenses, assets, and rules using natural language while maintaini | |
| gcloud MCP Cloud Run addhe/gcloud-mcp-cloudrun Enables interaction with Google Cloud Platform services through gcloud CLI commands via a Cloud Run deployed MCP server. Supports executing gcloud commands and managing GCP resources through natural language. | |
| Iris addisontech/iris This MCP server enables AI agents to read MQTT and Sparkplug B data via tools like list_topics, get_latest, and read_all, providing read-only access to latest sensor values. | |
| Supabase MCP Server addity3/supabase-mcp Enables AI assistants to interact with Supabase databases through standardized CRUD operations including querying, inserting, updating, and deleting records with support for filtering, pagination, and column selection. | |
| gh-attach addono/gh-attach Enables AI applications to upload images and videos to GitHub issues, pull requests, and comments through the Model Context Protocol. | |
| BlockMag Public MCP Server addrianc/blockmag-mcp-server Provides zero-authentication access to six free AI tools for discovering verified storefronts, searching live product catalogs by name or EAN-13 barcode, generating printable A4 VAT invoices and timesheet PDFs, and verifying invoice QR code | |
| Jira MCP Server addy-301/mcp Enables MCP clients to read, create, update, comment on, and transition Jira issues using Jira Cloud's free plan. | |
| graphview adecubed/graphview-mcp Enables read-only inspection of graph-shaped memories such as Obsidian vaults, Memory MCP files, or SQLite databases, allowing users to visualize, search, and trace the provenance and recall of an agent's knowledge. | |
| HubSpot MCP Server adeel0x01/hubspot-mcp-tools Integrates with HubSpot CRM APIs via the Model Context Protocol, enabling management of contacts, companies, deals, tickets, notes, engagements, workflows, and more through natural language. | |
| custom-mcp-server adeelahmed1293/custom-mcp-server Enables note management (add, read, latest, summarize), current weather lookup by city, and news search via the Brave Search API, with configuration through environment variables. | |
| MCP Starter adeelahmedkhan/mcp-starter-railway Enables users to create, list, search, and read notes persisted in SQLite, along with basic arithmetic and echo tools, exposed over Streamable HTTP. Notes are also available as JSON resources and through a prompt that asks the calling model |
23,651–23,700 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.