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 |
|---|---|
| Hacker News MCP dhanush-git/hacker-news-mcp Enables AI agents to access Hacker News data including stories, items, users, and comments via MCP tools. | |
| HR-ASSIST dhanush-ts/hrms-mcp Agentic AI system that automates HR workflows like employee onboarding, enabling HR teams to streamline tasks through natural language interactions with Claude Desktop. | |
| sharepoint-excel-mcp dhanushkacc/sharepoint-excel-mcp Enables AI agents to read and query Excel files stored in SharePoint and OneDrive for Business, converting permission-matrix spreadsheets into structured JSON for automated QA workflows. | |
| Flight Booking MCP Server dhanyahegdek/flight_booking_mcp_server Enables AI assistants to search for flights, book them, check booking status, and cancel bookings using mock flight data with no API keys required. | |
| LeaveManager dhanyahegdek/mcp-leave-manager Enables managing employee leave requests including checking balance, applying for leave, and viewing history. | |
| terraform-test-mcp dharani-sowndharya/terraform-test-mcp Generates structured prompts for Claude Code to create comprehensive Terraform test cases including unit, integration, and mock tests. | |
| Autonomous Documentation Discovery Engine dharanidasari/custom-mcp Enables AI agents to search, fetch, and clean live documentation from LangChain, LlamaIndex, and OpenAI via Model Context Protocol, with token-optimized extraction. | |
| MCP E-commerce Server dharatiwankhade/mcp-server-db Enables AI clients to perform full CRUD operations on e-commerce products stored in MySQL, including search with pagination, AI-powered description generation via sampling, and low-stock inventory monitoring. It also exposes product catalog | |
| mongo-mcp dharhshinivj/mongo-mcp A local MCP server that connects Claude Desktop to a MongoDB database, enabling listing, finding, adding, and deleting users via natural language. | |
| recall-mcp dhari-q/recall-mcp A shared, local-first memory layer for AI CLIs, providing persistent, layered memory across Claude Code, Gemini CLI, and other MCP-aware clients. | |
| pi-controller dharklol/pi-controller Enables ChatGPT to securely manage a Raspberry Pi's Kalshi live-recorder project through MCP, including file operations under /srv/kalshi, Git pulls, service control, and health inspection, while deliberately restricting access to the rest | |
| Obsidian Remote MCP Server dharmikbhesaniya/obsidian-mcp Connects AI assistants and agents to Obsidian vaults through strongly typed tools and resources for reading, creating, searching, organizing, and analyzing notes, tasks, properties, tags, and knowledge-graph data. Supports secure remote acc | |
| locklens dharrison07326/locklens Enables auditing npm, Yarn, and pnpm lockfiles from local project directories or remote Git repositories, returning vulnerability results in text or JSON with configurable thresholds and dev dependency skipping. | |
| memex dharrison07326/memex Gives AI coding agents persistent memory across sessions by writing each task's insights as atomic markdown knowledge cards with bidirectional links and recalling relevant ones before new work begins. Cards are shared across Claude Code, Cu | |
| Blog-MCP dharshini195/blog-mcp Provides MCP tools to interact with Dev.to, enabling searching, browsing, and publishing articles through natural language. | |
| CockroachDB MCP Server dhartunian/cockroachdb-mcp-server Connects to CockroachDB instances and exposes database structures as resources, enabling SQL query execution and analysis through Claude's interface. | |
| carryforward dharun-cohere/jev-carryforward Enables saving project facts as they occur and retrieving only task-relevant entries when starting new work, using Jev evaluation to rank them while preserving all stored context. | |
| sortwell dharun-cohere/jev-sortwell Enables automatic filing of notes, links, and meeting lines by classifying each item’s kind, project, urgency, and duplicates, while storing your original text unchanged in an append-only inbox. | |
| Obsidian Second Brain MCP dhaseeb-proj/obsidian-second-brain-mcp-and-skill Enables AI agents to store and retrieve project context, bugs, decisions, and session logs by reading and appending markdown files in a local Obsidian vault, without requiring any cloud services. | |
| blender-mcp dhautarchor/blender-mcp Connects Blender to Claude AI via the Model Context Protocol, enabling natural language-driven 3D modeling, scene creation, and manipulation. | |
| zepp-mcp dhavalbhimani44/zepp-mcp MCP server that reads Zepp/Amazfit health and workout data, exposing tools for daily summaries, sleep, heart rate, and workout details to any MCP client. | |
| Explore MCP dhavaleswar/explore-mcp A demonstration MCP server that exposes basic arithmetic tools (add, subtract, ping) through FastAPI and shows how to integrate them with OpenAI's tool-calling API for LLM orchestration. | |
| chartbrew-mcp dhavanikgithub/chartbrew-mcp Enables AI agents to manage Chartbrew resources like teams, connections, datasets, dashboards, and charts via natural language. | |
| google-ads-mcp dhawalshah/google-ads-mcp Multi-user Google Ads MCP server with OAuth-per-user auth, Firestore token storage, raw GAQL queries, and 10+ extra reporting tools beyond the official server. | |
| google-analytics-mcp dhawalshah/google-analytics-mcp Google Analytics 4 MCP server with local STDIO and shared team Cloud Run modes, realtime visitor counts, metadata discovery, and funnel analysis. | |
| gsc-mcp dhawalshah/gsc-mcp Google Search Console MCP server connecting Claude to search performance, URL inspection, sitemaps, and quick-win reports via OAuth. | |
| linkedin-ads-mcp dhawalshah/linkedin-ads-mcp LinkedIn Ads MCP server with full read/write campaign management, Ad Library competitive search, and Cloud Run team deployment. | |
| mcp-google-sheets dhawalshah/mcp-google-sheets Enables AI assistants to interact with Google Sheets, allowing CRUD operations, sheet management, and data manipulation through natural language. | |
| meta-ads-mcp dhawalshah/meta-ads-mcp Meta (Facebook/Instagram) Ads MCP server for ad performance reporting, audience analysis, and competitor ad research. | |
| Defect Vision MCP Agent dhayalramesh/defect-vision-mcp-agent Enables users to classify steel surface defect images and retrieve aggregate model performance metrics through MCP tools, while supporting confidence-based human review and drift monitoring in an agent pipeline. | |
| toolfence dhb520cat/toolfence Enables agents and CI pipelines to audit MCP servers and agent tool-chains by statically scanning repositories, local checkouts, tools/list exports, or live endpoints for risks such as destructive actions without confirmation, mismatched sa | |
| appstore-mcp dhbw-appstore-t3/appstore-mcp Enables Claude Code agents to judge AppStore staging rollouts by reading Argo CD, Kubernetes pod/rollout/log/event, CloudNativePG, health, certificate, node, and GitHub Actions/PR data through read-only, redacted tools. | |
| Cross Repo Ops MCP dhcross/cross-repo-ops Enables secure, policy-controlled operations on local git repositories through MCP, including bounded reads, context-checked patches, allowlisted tasks, and guarded git operations. | |
| x4-mcpgen dhe-cruzer69/x4-mcpgen Generates secure, tested MCP server scaffolds with explicit tool allow-lists, unit tests, and production-ready configuration like Dockerfiles and CI workflows. | |
| MCP MediaCrea dheedrichard/mcp-mediacrea Enables image generation, editing, and blending using Gemini 2.5 Flash capabilities, plus text generation for AI-powered creative workflows through MCP tools. | |
| CSV MCP Assistant dheemanth-hub/fastapi-mcp Enables querying CSV or Excel data using natural language through MCP tools, running pandas operations on an uploaded dataset. | |
| invoice-server dheeraj12f/invoice-automation Enables AI assistants to inspect and extract invoice metadata from PDFs, Word documents, Excel files, and images, then synchronize and enrich the extracted data into an Excel ledger. | |
| MCP Configurator Server dheeraj32903/mcpservers Manages, edits, backups, and validates Claude Desktop and other client JSON configurations. | |
| Financial MCP Server dheerajgavhane/mcp Provides mock financial data including bank transactions, credit reports, and EPF details for the Finarrator application through authenticated API endpoints. | |
| Google Docs + Gmail MCP Server dheerajmw/mcp-server Enables appending content to Google Docs and creating Gmail drafts with human-in-the-loop approval, integrating structured AI tool interfaces via MCP-style endpoints. | |
| Weather MCP Server dheerajpatidar212/mcp-server-app-v1 Enables AI assistants to retrieve current weather conditions and multi-day forecasts for any location, with optional natural-language summaries. | |
| Model Context Protocol Multi-Agent Server dheerajprakash/mcp_project Demonstrates custom MCP servers for math and weather operations, enabling multi-agent orchestration using LangChain, Groq, and MCP adapters for both local and remote tool integration. | |
| opencode-mcp-bridge dheerax/opencode_mcp An MCP server that lets any AI tool delegate tasks to the OpenCode CLI as a subagent, with multi-session orchestration, event tracking, and task contracts. | |
| MCP MySQL Server dheersingh1973/mcp-mysql Enables interaction with MySQL databases through MCP, supporting query execution, table operations (insert, update, delete), and schema inspection for natural language database management. | |
| Sleeper MCP dhegadde/sleeper-mcp Enables Claude to query live fantasy football league data and run LightGBM-based player projections, calibrated ranges, matchup simulations, playoff odds, trade evaluations, and waiver/start-sit analysis. | |
| mcpme dheimgartner/mcpme Enables MCP-compatible agents to answer questions about you by exposing your CV through a tool, resource, and prompt. | |
| Axion Planetary MCP dhenenjay/axion-planetary-mcp Enables MCP clients to access Google Earth Engine's satellite imagery and geospatial analysis capabilities. Provides tools for vegetation analysis, crop classification, disaster monitoring, and interactive map creation using petabytes of sa | |
| Earth Engine MCP Server dhenenjay/earth-engine-mcp-new Enables satellite imagery analysis through Google Earth Engine, allowing users to search datasets, calculate vegetation indices like NDVI, filter collections by location and date, and export imagery to cloud storage. Supports major satellit | |
| Planetary MCP dhenenjay/planetary-mcp-deployment Enables deploying an Earth Engine MCP server in Docker, integrating with Claude Desktop to perform geospatial analysis using 11 Earth Engine tools for tasks like wildfire risk, flood risk, and agricultural monitoring. | |
| My Mail MCP dherenj84/my-mail-mcp Enables AI clients to connect to a self-hosted IMAP/SMTP mailbox for searching, reading, sending, organizing, and managing email messages and folders through authenticated MCP tools. |
44,351–44,400 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.