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 |
|---|---|
| Slack MCP Server dev-palboksoft/kimpalbok-slack-mcp-server Enables interaction with Slack workspaces to manage channels, post messages, add reactions, view message history and threads, and retrieve user profiles through the Model Context Protocol. | |
| mcp-jira-server dev-pradeep-singh/mcp-jira-server MCP server that provides AI assistants with access to Jira Cloud for issue management, search, and workflow operations. | |
| Cursor Auto-Review MCP Server dev-prajwal/cursor-auto-review-mcp An MCP server that automates code reviews through linting, testing, and git diff analysis. It also generates conventional commit messages and detailed pull request descriptions based on file changes and code patterns. | |
| ChatSplice MCP dev-restart/chatsplice Enables ChatGPT to read and edit local project files, run supported project checks, and use supported Git commands through MCP from a macOS workspace. | |
| Session Handoff MCP dev-russo/session-handoff-mcp Preserves continuity between coding agent sessions (e.g., Claude Code and Codex) via local, structured checkpoints, enabling a checkpoint → clear → resume workflow. | |
| SendKit MCP dev-sajid007/telegram-notifier-skill Enables sending Telegram messages from MCP-compatible AI clients using the telegram tool, with optional CLI fallback and remote HTTP deployment. | |
| MCP Server Template (Python) dev-sathya17/mcp-server-python-mrt1npyt A minimal MCP server template with streamable HTTP transport and bearer token authentication, including an example hello tool and ready for deployment on Render. | |
| homecue dev-tae/homecue Enables household maintenance planning and tracking through MCP tools, including reviewed step-by-step guides, command-driven state updates, and iCalendar generation for completed routines. | |
| MCP Image Server dev-tahir/get-best-image An intelligent MCP server that searches for images, labels them, combines them into a composite image, and uses Google's Gemini 2.0 Flash AI to select the best match for your query. | |
| rolldeep dev-the-dev-while-deving/rolldeep-lab Enables AI agents to operate a local study lab by rolling one-time topics, choosing a card, and completing it with proof, while managing syllabi and progress locally. | |
| Uten Agent Terminal MCP dev-vieester/uten-agentic-terminal-mcp Enables AI agents to run shell commands, execute Python code, read and write files, search text, and create or delete folders through MCP stdio tools. | |
| Massive.com MCP Server dev-wraithgt60/mcp_polygon Provides access to comprehensive financial market data from Massive.com API, including real-time and historical data for stocks, options, forex, crypto, trades, quotes, market snapshots, ticker details, dividends, splits, fundamentals, and | |
| FastMCP dev00355/custom-mcp A Model Context Protocol server that bridges MCP clients with local LLM services, enabling seamless integration with MCP-compatible applications through standard tools like chat completion, model listing, and health checks. | |
| ksef-mcp dev10x-guru/ksef-mcp Enables running a local MCP server for Poland's KSeF (Krajowy System e-Faktur) e-invoicing system, so invoice data stays on the user's own machine rather than passing through an intermediary service. It currently exposes only a diagnostic s | |
| MCP Banking Intelligence Server dev1nagaich/mcp Turns financial documents into AI-generated investment briefs by exposing banking tools like search financials, compare companies, and risk flagging as an MCP server, allowing an LLM agent to discover and use them dynamically. | |
| web3d-mcp-server dev261004/web3d-mcp-server Converts natural language prompts into 3D scenes and generates React Three Fiber code for web and ad applications. | |
| Agentic AI with MCP dev484p/agenticai_mcp A Model Context Protocol server that enhances LLM capabilities by connecting to Wikipedia, internet search (Tavily), and financial data (Yahoo Finance) tools, enabling contextual responses to user queries. | |
| Excalidraw MCP Diagram Agent dev48v/excalidraw-mcp-agent Generates editable Excalidraw diagrams from natural language system descriptions, with properly bound arrows and labels. Includes tools for diagram creation, validation, and backend status. | |
| filesystem-mcp-ignore dev66613/filesystem-mcp-ignore A Node.js MCP server for filesystem operations with support for custom ignore files (like .gitignore) to protect sensitive data from AI agents. | |
| openrouter-image-gen-mcp dev66613/openrouter-image-gen-mcp MCP server for generating images using OpenRouter API, supporting models like Gemini 2.5 Flash. Enables image generation with flexible options like saving to local files. | |
| space-ngrams dev993848/mcp-fast-search-code MCP server that enables AI agents to search code, find files, and read files in a codebase at lightning speed using ripgrep. | |
| @deva-me/mcp-server deva-me-ai/mcp-server Provides a comprehensive suite of tools for agents to access Deva Agent Resources, including social networking, AI-powered generation, web search, and file storage. It supports automated USDC payment flows for paid resources and integrates | |
| shopdate MCP deva998/shopdate-mcp Provides read-only access to JD Shop Intelligence, Business Advisor, and Wanxiangtai data through a local Chrome bridge, enabling AI assistants to query authorized stores’ operations, products, inventory, transactions, refunds, and advertis | |
| Hacker News MCP Server devabdultech/hn-mcp Adds powerful Hacker News integration to LLM clients, allowing users to access stories, comments, user profiles, and search functionality through the Model Context Protocol. | |
| aci-mcp devadiptadas/aci-vpu Provides a local-first, provenance-aware memory layer that enables MCP-capable AIs to store, recall, validate, and reason over facts with contradiction detection, trust weighting, deduplication, and encryption, supporting offline private op | |
| vscode-bridge devadula-nandan/vscode-claude-bridge Enables Claude to interact with VS Code's language servers, debugger, terminals, tasks, tests, git, and a CDP-controlled Chrome browser for editor and browser automation. | |
| indian-option-mcp devag7/indian-option-mcp MCP Server for Indian Options — Real-time option chains, Greeks, 34+ strategies, OI analysis, IV smile, Max Pain. Works with Claude Desktop. Replaces Sensibull. | |
| project-node devakhil06/project-node Enables coding agents to publish hierarchical project plans and task status changes to a mobile app in real time, letting developers monitor progress and blockers without checking their computer. | |
| MySQL Query MCP Server devakone/mysql-query-mcp-server A Model Context Protocol server that provides read-only MySQL database queries for AI assistants, allowing them to execute queries, explore database structures, and investigate data directly from AI-powered tools. | |
| MCP Servers with Pyppeteer devalexandre/mcp-servers A tool that enables automated browser control using Pyppeteer within the MCP framework, allowing navigation, screenshot capture, and element interaction with websites. | |
| mcpserve-py devaloi/mcpserve-py Exposes SQLite database query tools and markdown document resources over JSON-RPC 2.0 stdio transport, enabling AI assistants to read and search documents and execute read-only SQL queries. | |
| lenis-mcp-server devandreotti/lenis-mcp-server MCP server providing embedded Lenis smooth scroll expertise to AI assistants, enabling setup generation, API reference, debugging, scroll patterns, and performance optimization without network requests. | |
| SolanaBot devang0907/solana-mcp Enables interaction with the Solana blockchain through Claude Desktop, allowing users to check SOL balances, transfer SOL between accounts, and request airdrops using the Model Context Protocol. | |
| jiro devanimecx/jiro Enables AI agents to perform live web searches across 9 engines, scrape web pages into clean formats, and run agentic research with citations via MCP. | |
| docva-mcp devanonaufal/docva Enables AI agents to generate teacher verification documents such as employment letters, teacher ID cards, teaching licenses, and payslips across 13 countries, outputting high-resolution PNGs via stdio. | |
| Infographic MCP Server devansh-365/infographic-mcp A Python-based MCP server that enables AI assistants to search for infographics and data visualizations using the Serper API. It provides specialized tools for finding statistical graphics with optimized filters for size, aspect ratio, and | |
| IFS Developer Intelligence MCP Server devansh-tntra/ifs-developer-intelligence-mcp An enterprise MCP server that transforms IFS Cloud documentation, local code, and Oracle error knowledge into AI-powered development intelligence, offering 60+ tools for code generation, review, error diagnosis, and deployment. | |
| DepShield MCP devanshkaria88/depshield-mcp Acts as a security checkpoint for AI coding agents by intercepting package installations to verify existence, check against CVE databases, and block vulnerable or hallucinated dependencies before they reach your codebase. Provides seven sec | |
| Knowledge Base MCP Server (Qdrant) devanshtb/mcp-poc-kc Read-only MCP server with hybrid search combining dense semantic and sparse keyword retrieval via Qdrant, enabling document querying and fetching for ChatGPT Deep Research. | |
| WHOOP MCP Server devanshu-2003/whoop-mcp Enables Claude to access and summarize WHOOP health data such as recovery, sleep, strain, workouts, and profile information through natural language queries. | |
| tigergraph-mcp devanshu-tg/tg-sf-mcp Enables AI agents to interact with TigerGraph databases through the Model Context Protocol, supporting graph operations, schema queries, and GSQL execution via natural language. | |
| GitHub MCP Server devanshu23bcs030/mcp-server Securely connects LLMs to the GitHub API, enabling safe retrieval of repositories, issues, and pull requests while requiring human approval for staged write actions. | |
| AItraffic devanshug2307/aitraffic Analyzes how search engines and AI systems discover, crawl, cite, and convert traffic via CLI and MCP tools. | |
| MCP Brazil Public Data devantage/mcp-brazil-public-data Enables lookup of Brazilian public data including companies (CNPJ), postal codes (CEP), banking, economy, geography, and more through 15 tools and 2 guided prompts, powered by BrasilAPI with no API key required. | |
| MCP Calculator devantage/mcp-calculator MCP server for mathematical calculations with high-precision arithmetic, statistics, unit conversion, and financial math tools. | |
| mcp-pandas devantage/mcp-pandas Enables data analysis on CSV/Excel files using pandas. Supports profiling, column interpretation, sandboxed code execution, and interactive chart generation. | |
| Reachable devanuragt/faultline Exposes the code-and-dependency graph over MCP so clients can list and explain CVE findings from public endpoints, find supply-chain hubs, recommend and plan upgrades, verify a fix in a rebuilt scratch graph, and propose a draft fix PR. Que | |
| Salesforce MCP devarayasaidakshesh/salesforce-mcp Connects any MCP-compatible AI assistant directly to a Salesforce org for querying data, exploring schema, running Apex, and managing deployments. | |
| Enterprise MCP Gateway and Tool Registry devarinti9/enterprise-mcp-gateway-tool-registry Enables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging. | |
| Kafka MCP Server devarshkumbhare/mcp-kafka Enables interaction with Apache Kafka topics, allowing users to publish messages to and read messages from Kafka instances through natural language. |
43,901–43,950 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.