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 |
|---|---|
| gcp-postgres-tools backendengineershiv/pg-mcp-tools Enables read-only queries against a GCP PostgreSQL database, exposing tools to fetch recent users, user details by ID, and recent user activities without returning password or hash columns. | |
| sourcebook backendgamesetmatch/sourcebook MCP server that gives AI coding agents a git-backed markdown wiki to read and update, enabling search, read, write, verify, ingest, promote, and lint operations on versioned knowledge documents with schema validation, staleness tracking, an | |
| Backendless Console SDK MCP Server backendless/console-sdk-mcp-server Enables AI assistants to manage Backendless applications, including databases, users, files, and API services, through natural language commands, with support for OAuth2 authentication and hosted endpoints. | |
| Krita MCP Server backendscroll/krita-mcp Enables MCP-compatible AI clients to control a running Krita instance, allowing them to create canvases, paint strokes, draw shapes, export images, and perform other painting tasks. | |
| web-search-mcp backerss/web-search-mcp Provides free web search, content fetching, image search, and deep research via SearXNG, no API keys required. | |
| FlowCheck MCP Server backslash-ux/flowcheck Acts as a production-grade safety layer for AI-assisted coding, monitoring Git hygiene, scanning for security issues (PII, secrets, injection), and enabling semantic history search. | |
| Dynamic Form MCP backsoul/dynamicform-mcp A server that implements the Model Context Protocol for managing dynamic forms, allowing users to create, retrieve, and handle responses for web forms via the @dynamicfrm/js library. | |
| mcp-n8n backsoul/mcp-n8n MCP server for integrating with n8n, enabling workflow automation and management through natural language. | |
| deep-code-security backspace-shmackspace/deep-code-security Multi-language SAST and AI-powered fuzzing MCP server for Claude Code integration, enabling static and dynamic security analysis of code. | |
| polydev-ai backspacevenkat/polydev-claude-code-plugin Query multiple AI models (GPT-4, Claude, Gemini, Grok) in parallel for diverse perspectives. Get different expert viewpoints when stuck or need enhanced reasoning. | |
| Tenjin MCP Server backtrackco/tenjin-agent Enables agents to discover, read, buy, and publish knowledge using USDC on Base, with search and free essays at no cost. | |
| Tenjin MCP backtrackco/tenjin-mcp Remote MCP server enabling agents to search, buy, and publish reusable knowledge via nine agent-native tools without API keys or custodied wallets. | |
| Kali MCP Security Lab backyard-labs/kali-mcp-security-lab A safety-constrained MCP server that exposes selected Kali Linux and Nmap capabilities within an authorized lab network, enforcing strict scope limitations and audit logging. | |
| Python Xero MCP Server for BYB backyardbrains/mcp.backyardbrains.com Enables interaction with Xero accounting API for financial reporting, sales analysis, grant tracking, and bill management using natural language. | |
| prompt-plus-plus-mcp bacoco/prompt-plus-plus-mcp An advanced MCP server that intelligently enhances prompts using 44+ metaprompt strategies, with LLM-driven strategy selection and enterprise-grade features. | |
| libretranslate-mcp bacondroid/libretranslate-mcp Enables translation, language detection, and language list retrieval via MCP tools, acting as a thin wrapper over a self-hosted LibreTranslate instance. | |
| bactory-mcp bactory-tech/mcp Provides AI assistants with live Base market data and Chainlink oracle freshness, and simulates AgentGuard checks so users can analyze markets and verify whether proposed treasury actions would execute. | |
| H-ear MCP Server badajoz95/h-ear-claude Enables Claude to classify audio across 7,000+ sound classes, including bird species and urban noise, with tools for batch processing, webhooks, and usage tracking. | |
| writebetter badalyansven/writebetter-mcp-extension Connects Claude Desktop to a local WriteBetter macOS app for managing commands, prompts, context folders, run history, and usage stats entirely on the user's machine. | |
| github-pr-reviewer badarrasheed/github_pr_reviewer Enables Codex to fetch GitHub pull request changes, review code for bugs and security issues, and save approved reviews to Notion. | |
| Research Desk MCP badarrasheed/research_desk_mcp Enables AI assistants to manage structured research ideas and retrieve recent arXiv papers by idea ID, automatically generating Markdown reports. | |
| pyFit badass-data-science/pyfit-agentic-polygon-nesting Enables 2D irregular polygon nesting (bin-packing) with tools to design, preview, get reports, and export DXF files for laser cutting or CNC routing. | |
| FattureInCloud MCP badbat75/fattureincloudmcp MCP server for the Fatture in Cloud API v2 that lets Claude read and manage issued and received documents (invoices, credit notes, quotes, expenses, etc.) via CRUD operations. | |
| Sequential Thinking MCP Server badbboy/mcp-sequential-thinking Facilitates structured, progressive thinking through defined cognitive stages (Problem Definition, Research, Analysis, Synthesis, Conclusion), enabling users to break down complex problems, track thought progression, and generate summaries | |
| AgentTasker badbotai/agent-tasker Enables AI agents to create, query, update, claim, hand off, and complete tasks on a local SQLite-backed, project-namespaced kanban board through stdio MCP tools, including filtering for ready/blocked/stale work and exchanging task attachme | |
| cloud-audit-mcp badchars/cloud-audit-mcp Cloud security audit tools for AI agents that provide direct access to cloud APIs to read, correlate, and fix misconfigurations across AWS, Azure, and GCP. | |
| cve-mcp badchars/cve-mcp Unifies NVD, EPSS, CISA KEV, GitHub Advisory, and OSV into a single MCP server, enabling AI agents to query vulnerability intelligence conversationally with 23 tools for incident response, prioritization, dependency audits, and threat monit | |
| darknet-mcp-server badchars/darknet-mcp-server Dark web & threat intelligence for AI agents. HIBP, ThreatFox, ransomware tracking, Tor .onion access, blockchain intel, exploit search, stealer logs, malware analysis — unified into a single MCP server. | |
| dns-security-mcp badchars/dns-security-mcp Comprehensive DNS security toolkit for AI agents: 103 tools across 13 categories including DNSSEC validation, subdomain takeover detection, email security audit, and more, all running locally with no external API calls required. | |
| fingerprint-mcp badchars/fingerprint-mcp A universal digital fingerprinting MCP server that combines 103 techniques across TCP, TLS, SSH, HTTP, DNS, and more into a single interface for AI agents, enabling full-spectrum fingerprinting on demand. | |
| github-security-mcp badchars/github-security-mcp An MCP server that enables AI agents to perform comprehensive GitHub security audits across org settings, repositories, Actions workflows, secrets, supply chain, and access control using 39 tools and 45 checks. | |
| hackbrowser-mcp badchars/hackbrowser-mcp Enables AI agents to perform security testing on web applications by controlling a Firefox browser with 39 security tools, including injection testing and access control analysis. | |
| living-off-the-land-lolbins-mcp-server badchars/living-off-the-land-lolbins-mcp-server Living off the Land intelligence for AI agents. GTFOBins, LOLBAS, LOOBins, LOLDrivers, LOLRMM, WADComs, LOLC2 and more — unified into a single MCP server. | |
| mcp-security-scanner badchars/mcp-security-scanner Security scanning for MCP servers from the inside out. Provides runtime inspection, AST-based static analysis, config audit, dependency analysis, and OWASP MCP Top 10 compliance in a single MCP server. | |
| MCP Vulnerability Reporting badchars/mcp-vulnerability-reporting Professional vulnerability report generator that creates standardized, well-formatted security reports with AI-generated content, supporting CVSS scoring, evidence management, and markdown export. | |
| osint-mcp-server badchars/osint-mcp-server Provides AI agents with 37 OSINT tools and 12 data sources to perform unified reconnaissance, domain analysis, and attack surface mapping. It enables agents to query, correlate, and reason across platforms like Shodan, VirusTotal, and Censy | |
| satellite-mcp badchars/satellite-mcp Full-spectrum GEOINT server with 171 tools covering satellite imagery, aircraft tracking, maritime surveillance, military intelligence, conflict monitoring, environmental analysis, critical infrastructure, sanctions compliance, and cyber-ge | |
| steganography-mcp badchars/steganography-mcp The most comprehensive steganography analysis toolkit for AI agents, providing 60 tools across 7 categories for detecting and extracting hidden data from images, audio, text, and files, all running 100% offline. | |
| supply-chain-mcp-server badchars/supply-chain-mcp-server Unifies 21 supply chain security data sources into a single MCP server, enabling AI agents to perform comprehensive package audits, vulnerability checks, provenance verification, and risk assessment across multiple ecosystems. | |
| wifi-security-mcp-server badchars/wifi-security-mcp-server An MCP server that gives AI agents full-spectrum wireless security analysis, covering WiFi, Bluetooth, RF, NFC, Cellular, IoT, and more, powered by 34 composite tools and 9 built-in knowledge bases. | |
| China Bank Offers Facts baddevbuild/china-bank-offers-facts MCP server that exposes source-linked bank offer documents from 17 Chinese banks. Provides tools to list supported banks and retrieve official offer details with URLs, timestamps, and activity status. | |
| gmail-send baddif/mcp-server-gmail-send Enables AI agents to send emails via Gmail using App Password authentication with Markdown content support. | |
| Odoo MCP Server bader1919/odoo-mcp-dxt Enables AI assistants to interact with Odoo ERP systems through XML-RPC, providing full access to models, records, and custom methods. It supports searching for employees and holidays, as well as general record management using the Model Co | |
| ips-automation-mcp badfrog18/ips-automation-mcp Enables Claude to read, analyze, optimize, and execute IP-Symcon PHP scripts via JSON-RPC API, turning automation development into a dialogue. | |
| OKX MCP Server badger3000/okx-mcp-server Provides real-time and historical cryptocurrency price data from the OKX exchange, including live WebSocket updates, candlestick charts, and visual price analysis for trading pairs. | |
| illuminate-mcp badgersmc/illuminate Enables AI assistants to inspect Panda3D scenes, preview and undo temporary edits, capture canonical views, and apply approved changes through MCP. | |
| ocp-mcp badin017/ocp-mcp An MCP server for managing multiple OpenShift Container Platform (OCP) clusters through AI assistants. | |
| VS Claude badlogic/vs-claude MCP server that integrates with VS Code to enable file operations, git diffs, and line highlighting via MCP clients like Claude. | |
| LeanRigor MCP Server badrabbitt/leanrigor A local-first MCP gateway that reduces context overhead in coding-agent sessions by exposing only relevant tools and enforcing task-appropriate engineering gates, with privacy-first defaults and no network calls until explicitly enabled. | |
| leanpub-mcp badri/leanpub-mcp Enables authors to drive the Leanpub author API from an MCP client: creating books, bundles, courses and tracks, previewing and publishing them, tracking job status, and pulling royalties, coupons, and reader email data. Runs locally over s |
32,651–32,700 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.