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 |
|---|---|
| Sort Lines Tool Sort lines of text alphabetically or numerically. Use for data organization, list management, and text file preparation. | |
| Sort Tool Sort lines of text files alphabetically or numerically. Use for data preparation, list organization, and output formatting. | |
| Split Tool Split files into smaller pieces by size, line count, or number of chunks. Use for breaking large files into manageable parts. | |
| Ssh Tool Securely connect to remote systems via the SSH protocol. Use for remote server management, file transfer, and tunneling. | |
| Stat Tool Display detailed file or filesystem status information. Use for checking file permissions, sizes, timestamps, and metadata. | |
| Sudo Tool Execute commands with superuser privileges. Use for system administration tasks requiring elevated permissions. | |
| System Monitor Monitor system metrics like CPU, memory, disk, and network. Use when user needs to track server performance, set up alerts for high resource usage, monitor u... | |
| Sysinfo Tool Display comprehensive system hardware and software information. Use for diagnostics, inventory, and system profiling. | |
| Table Tool Format data into aligned table columns. Use for displaying structured data with organized rows and columns. | |
| Tac Tool Concatenate and display files in reverse line order (last line first). Use for viewing log files from newest entries and reversing file content. | |
| Tail Tool Display the last lines of files. Use for monitoring log files, checking recent entries, and following file growth in real-time. | |
| Tar Tool Create and extract tar archives with optional compression. Use for file bundling, backup, and distribution. | |
| Tee Tool Read from stdin and write to both stdout and files. Use for saving pipe output while still displaying it on screen. | |
| Telegram Bot Create and manage Telegram bots. Use when user wants to build a Telegram bot for notifications, automation, customer support, group management, or interactiv... | |
| Template Tool Process text templates with variable substitution. Use for generating dynamic content from template files. | |
| Test Tool Evaluate conditional expressions for file testing, string comparison, and arithmetic checks. Use for shell script conditionals. | |
| Time Tool Measure execution time of commands. Use for performance benchmarking, script optimization, and timing analysis. | |
| Timestamp Tool Convert between Unix timestamps and human-readable dates. Use for time conversion, log analysis, and date arithmetic. | |
| Top Tool Display real-time view of running processes. Use for system monitoring, performance debugging, and resource management. | |
| Touch Tool Create empty files or update file timestamps. Use for file creation, timestamp management, and build system operations. | |
| Tr Tool Translate or delete characters from input streams. Use for character substitution, deletion, and squeezing repeated characters. | |
| Traceroute Tool Trace network path to a destination host. Use for network diagnostics, latency analysis, and routing path discovery. | |
| Transform Tool Apply data transformations like case changes, encoding conversion, and format conversion. Use for text processing and data cleaning. | |
| Tree Tool Display directory structure as an indented tree. Use for visualizing folder hierarchies and project structure. | |
| True Tool Return exit code 0 indicating success. Use as a no-op command that always succeeds in scripts and conditional expressions. | |
| Umask Tool Set or display file creation permission mask. Use for controlling default file permissions on new files and directories. | |
| Unexpand Tool Convert spaces to tabs in text files. Use for consistent indentation and reducing file size by replacing spaces with tabs. | |
| Uniq Tool Report or filter repeated lines in sorted text. Use for deduplication, frequency counting, and data cleanup. | |
| Unzip Tool List, test, and extract files from ZIP archives. Use when you need to decompress or inspect ZIP file contents. | |
| Uptime Tool Show system uptime, load average, active user count, and boot time. Use for system health checks, monitoring, and diagnostics. | |
| Url Shortener Create and manage short URLs with custom aliases and tracking. Use when user needs to shorten long URLs, create memorable custom links, track click statistic... | |
| Urlencode Tool URL-encode or decode text for safe transmission in URLs and query strings, with support for form data, partial encoding, and batch file processing. | |
| Uuid Tool Generate universally unique identifiers (UUIDs) in versions v1, v4, v5, v7, and nil format, with bulk generation and namespace-based deterministic IDs. | |
| Validator Tool Validate data formats including JSON, email, URL, file paths, IP addresses, and phone numbers with detailed error reporting and batch processing. | |
| Video Downloader Download videos from YouTube and other video platforms. Use when user needs to download videos for offline viewing, extract audio from videos, or save video... | |
| Wc Chars Tool Count characters in text input — total, non-whitespace, CJK, and Unicode-aware character counts. Useful for text analysis, content length limits, and i18n va... | |
| Wc Lines Tool Count lines, blank lines, code lines, and comment lines in text files. Useful for code statistics, log file sizing, and document analysis. | |
| Wc Tool Count lines, words, characters, and bytes in one or more files with per-file and total summary. Use for document statistics, code analysis, and data volume e... | |
| Wc Words Tool Count words in text — total, unique, per-line, with frequency analysis. Useful for readability metrics, content analysis, translation estimation, and documen... | |
| Weather Tool Get current weather and forecasts. Use when user needs to check current weather, get forecast for travel planning, or monitor weather conditions. | |
| Web Monitor Monitor web pages for content changes with CSS selector targeting, change detection via hashing, and notification integration. Use for price tracking, conten... | |
| Wget Tool Download files from the web via HTTP/HTTPS/FTP with resume support, recursive mirroring, rate limiting, and progress feedback. | |
| Which Tool Locate the full path of executable commands in the system PATH. Find command locations, verify installation, and resolve command conflicts. | |
| Whoami Tool Print the current effective username. Simple identity query for scripts, session tracking, and access control verification. | |
| Whoami Tool Check Identity verification utility — validate current user against expected roles, check sudo access, and audit user capabilities. Extended whoami for security an... | |
| Xargs Tool Build and execute command lines from standard input — batch process arguments, parallel execution, argument substitution, and delimiter control. | |
| Xxd Tool Create hex dumps of binary files, convert hex dumps back to binary, and perform bit-level analysis and patching. Essential for reverse engineering, binary an... | |
| Yes Tool Repeatedly output a string (or 'y' by default) for automated scripts, batch confirmation, and pipeline input generation. | |
| Zip Tool Package and compress files into ZIP archives with configurable compression levels, password protection, directory recursion, and cross-platform compatibility... | |
| Xiaohongshu Automation Suite A complete automation suite for Xiaohongshu (Little Red Book). Includes long-text publishing, comment management (reply/check), and stealth login helpers. |
26,001–26,050 of 108,824
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.