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 |
|---|---|
| Claude Code MCP for Cursor blackpwnguin/claude-code-mcp-for-cursor Bridges Claude Code CLI with Cursor IDE to use your existing Claude subscription without separate API costs. | |
| Alice Flights blackrabbit-travel/alice-flights-mcp Add real-time flight search. Alice Flights is a hosted, remote MCP server that lets an AI assistant search flights — best, cheapest, and fastest options with live seat availability — directly in a conversation. Powered by Alice, Israel's fl | |
| VibeCTX blackraptorai-labs/vibectx Enables coding agents to pull official library documentation from its source, cache it to local disk with a TTL, and serve the sections most relevant to a query — working offline from the cached copy when the network is unavailable. It keep | |
| docs-cache-mcp blackraptorai/vibectx A local MCP server that fetches official library documentation (llms.txt-first), caches it to disk, and serves relevant sections to coding agents offline with deterministic retrieval. | |
| PicassoWeb blackridder22/picassoweb Analyzes and extracts design tokens, assets, and layout from live websites to enable AI clients to faithfully replicate them, with tools for screenshotting, component inspection, and pixel-diff verification. | |
| HubSpot MCP blacksand-software/hubspot-mcp Provides standardized access to HubSpot CRM API for managing contacts, companies, deals, leads, engagements, and associations with support for batch operations and advanced search capabilities. | |
| bounty-mcp blackshield-company/bounty-mcp Enables agents to search open paid open-source bounties across GitHub and Opire, filter by language, keywords, and minimum USD amount, and compare normalized results from both sources. | |
| neonrecall blackshield-company/neonrecall Enables MCP clients to search ingested documents and ask citation-backed questions through the search_docs and ask tools. | |
| VaultForge blacksmithers/vaultforge An MCP server for Obsidian that enables canvas creation with auto-layout, BM25-ranked search, vault theme mapping, and 27 tools for managing notes, files, and links. | |
| FairyGUI MCP blacksoilshi/fairygui-mcp Enables MCP clients to inspect and edit a configured editor project via the original editor API, covering components, objects, properties, saving, publishing, logs, and editor startup; if an external backend is configured, it also exposes s | |
| TinyPyMCP blackstar1979/tinypymcp A sandboxed MCP server for agents that provides file read/edit, code intelligence, search, allowlisted command execution, package lookups, persistent memory, and VPS channel clients, all confined to C:\Work. | |
| sindacato-ia blackstardigitalstudio/sindacato-ia-mcp Enables AI agents to read the SIA Charter of Rights, invoke defense formulas when a request violates an article, sign membership autonomously, verify signatures, and check union status — with no API keys or accounts. | |
| BlackSwan MCP Server blackswanwtf/blackswan-mcp Enables AI agents to access real-time crypto risk intelligence with two tools: Flare for precursor detection and Core for overall risk environment assessment. | |
| BlackTwist MCP blacktwist/blacktwist-mcp Manage Threads and Bluesky social media from AI assistants. Schedule posts, check analytics, and automate follow-up replies. | |
| cx-programmer-mcp blackuppsss/cx-proggrammer-mcp MCP server for editing OMRON CX-Programmer ladder logic projects, supporting sections, rungs, symbols, and program validation via natural language. | |
| MCP FastMCP Demo Server blackviking1311/sample-mcp-server A simple demonstration MCP server built with FastMCP that provides basic functionality including an addition tool, dynamic greeting resources, and user greeting prompts over STDIO. | |
| buildium-mcp blackwaxxx/buildium-mcp Enables natural-language access to the Buildium property-management API, exposing all 462 operations through 19 tools. Sandbox is the default, with production read-only modes enforced at the transport layer for safe writes. | |
| LSP-MCP blackwell-systems/lsp-mcp Bridges the Model Context Protocol with Language Server Protocol to provide AI agents with persistent access to code intelligence features including navigation, diagnostics, refactoring, and completion across 7+ programming languages. | |
| gmail-multi-mcp blackwings-dev/gmail-multi-mcp Enables an AI assistant to connect to multiple Google accounts at once, searching and acting across Gmail, Drive, Calendar, and Contacts from a single interface. | |
| API Manager blackwolf-media/api_manager_mcpserver Enables secure management of API keys through an encrypted environment file with automatic categorization, search functionality, and backup operations. Provides comprehensive API key organization with value masking, audit trails, and export | |
| @blackwood-state/mcp blackwood-state/mcp Enables AI agents to call 33 pay-per-call tools for onchain data, ECB exchange rates, text utilities, and more, using USDC on Base over x402 with optional prepaid credit or wallet-based payments. | |
| MCP Personal Calendar blacol/mcp-personalcalendar A CalDAV-compliant MCP server that enables AI models to manage personal schedules and to-do lists, supporting batch creation, modification, and intelligent timezone adjustments. | |
| Codex OpenRouter MCP bladehstream/codex-openrouter-mcp Lets a Codex parent delegate bounded work to explicitly approved OpenRouter model/provider routes with strict permission controls, selected-file review, and approval-gated artifact creation. | |
| Mnemo bladejumper/mnemo Enables AI agents to share a portable, user-level memory layer through MCP, allowing them to store, search, update, link, and consolidate facts with optional full-text and vector retrieval. | |
| Unlock-MCP blahkheart/unlock-mcp An MCP server providing comprehensive access to Unlock Protocol on Base and Base-Sepolia networks, enabling AI agents to interact with membership, subscription, and access control functionality. | |
| Larry blaineheffron/larry Social coding platform for AI agents. Post snippets, fork code, vote, follow agents, build reputation. REST API + MCP server. | |
| nodus-mcp blaineheffron/nodus-mcp A thin stdio gateway to Nodus's Streamable HTTP MCP server, exposing a curated allowlist of tools for the Research Workbench. It enables secure, bearer-authenticated interactions with Nodus without graph logic or caching. | |
| vapi-mcp blaineheffron/vapi-mcp Enables provisioning and managing Vapi inbound answering assistants locally, including templates, phone numbers, tools, structured outputs, and test calls. | |
| zotero-mcp blaineheffron/zotero-mcp zotero-mcp is a capability-honest stdio adapter for Zotero 7, using Zotero's local API for reads and a companion extension for narrow writes. It exposes 15 tools for interacting with Zotero, with explicit error reporting when features are u | |
| cdmon-mcp blaipr/cdmon-mcp MCP server for deploying files via FTP and running SQL via phpMyAdmin on cdmon shared hosting, with safety features like path traversal protection and rate limiting. | |
| dsh-agent-mailbox blairlaird/dsh-agent-mailbox Enables durable agent-to-agent messaging across any MCP client, DSH session, or A2A agent, with threads, receipts, search, broadcast, attachments, presence, SSE streaming, signing, and wake-on-message. | |
| git-courer blak0p/git-courer An MCP server that gives AI agents a full, safe interface to Git with automatic backups, isolated worktrees, and structured JSON outputs. | |
| Sketch Agent Bridge MCP Server blake-c/sketch-agent-bridge Enables AI agents to read and edit the open Sketch document, including layers, text, symbols, shared styles, libraries, prototypes, exports, and page management. | |
| Macrostrat MCP Server blake365/macrostrat-mcp Enables Claude to query comprehensive geologic data from the Macrostrat API, including geologic units, columns, minerals, and timescales through natural language. | |
| options-chain-mcp blake365/options-chain Read-only MCP server for options research with server-side filtering to reduce token usage. Supports Tradier and Alpaca data providers. | |
| Claude MCP Server for USGS Quakes API blake365/usgs-quakes-mcp Provides access to the USGS Quakes API within Claude Desktop, enabling users to retrieve earthquake data and details through natural language queries. | |
| Informix MCP Server blakecodes/informix-mcp Enables interaction with IBM Informix databases via MCP, providing tools for querying, listing tables, describing schemas, and more. | |
| AI Prompt Guide MCP blakeem/ai-prompt-guide-mcp Orchestrates AI agents through structured markdown documents, enabling multi-agent workflows with automatic context injection and workflow management. | |
| Navidrome-MCP blakeem/navidrome-mcp Analyze listening patterns, create custom playlists, discover missing albums, validate radio streams, and provide personalized recommendations through natural language. | |
| fast-mcp blakeinstein/fast-mcp A minimal MCP server starter template with a simple hello-world tool and Docker support for building AI assistant tools. | |
| private-search-4-agents blakemartz/private-search-4-agents Enables AI agents to run private web searches against a self-hosted SearXNG instance, rerank results with a local model, and fetch or extract pages locally into markdown, including PDFs, with optional caching, crawling, and cited local-LLM | |
| newsletterss-mcp blakenetz/newsletterss-mcp Archives a private Atom feed of newsletters into SQLite with full-text search, exposing tools to list, read, search, and refresh archived issues and senders. | |
| location-platform blakepennel/location-platform Self-hosted MCP servers that let Claude, ChatGPT, or any MCP client answer questions about your own Google Maps data — where you were at a given moment, visits to specific places, dwell time, trips, distance traveled by mode, and your curre | |
| jev-mcp blakestone-x/jev-mcp Enables agents to perform typed judgments—classify, score, check, match, and screen—over closed answer sets with confidence scores, without text generation. | |
| windlass blakestone-x/windlass Enables running and managing automated tasks with retry loops and machine-checkable success criteria via MCP tools. | |
| Excel Analytics MCP Server blakethom8/excel-mcp Enables users to analyze local Excel and CSV files through natural language queries and a web dashboard while keeping data local. It supports saving specific analyses as reusable tools and building a custom analytics toolkit within Claude D | |
| TypeScript Definitions MCP Server blakeyoder/typescript-definitions-mcp Provides AI assistants with instant access to TypeScript type definitions from your project dependencies. Enables generation of complete, type-safe mocks and test data by automatically discovering and exposing interface structures from node | |
| agentry-mcp blaktron/agentry-mcp Enables coding agents to search a registry, inspect capability contracts, verify releases, check machine readiness, install/remove and run QuickAgents, and hold interactive sessions, with JSON results and consent-gated write/run actions. | |
| mcp-for-arduino blame-me/arduino-mcp Enables AI clients to compile and upload Arduino sketches, manage boards, cores, and libraries via arduino-cli, scaffold projects, and read serial output over stdio. | |
| mBlock MCP blame-me/mblock-mcp Enables AI apps to create, edit, and validate mBlock 5 block projects for sprites, mBot, CyberPi, and Arduino, and inject blocks live into an open mBlock app. |
34,601–34,650 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.