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 |
|---|---|
| Plane Workflow MCP amirhosseinkz/plane-workflow-mcp MCP server for Plane, including self-hosted Plane. Lets Claude Code, Codex, Cursor and other agents plan, start, and complete Plane work items under your team's rules, with dry-run previews, idempotent creates, project briefings, and factua | |
| contribution-compass amirimi/contributorcompass Provides MCP access to Contribution Compass's evidence catalog, enabling users to query curated open-source project activity, contribution opportunities, and observation histories. | |
| SmartMoney77 amiriss555/smartmoney77-mcp Public, no-login MCP server exposing SmartMoney77's financial calculators: compound interest, FIRE number, credit-card payoff, emergency fund, inflation, fees and the cost of waiting. Also computes historical "what if I had invested" return | |
| jamgate amirj4m/jamgate-old A neutral memory quality-gate for AI agents — a gate, not a store. It provides one shared memory of you that every AI agent reads from and writes to, kept honest at write time. | |
| Google Business Profile MCP Server amirjahfar1/google-business-profile-gbp-mcp An MCP server that provides 40 tools for managing Google Business Profiles, including accounts, locations, verifications, reviews, and performance analytics, enabling AI agents to interact with GBP via REST APIs. | |
| Google Search Console (GSC) MCP amirjahfar1/google-search-console-gsc-mcp Connects Google Search Console to AI assistants, enabling natural language queries for SEO data, indexing audits, sitemap management, and full site audits. | |
| HiveMind amirk-s/hivemind Enables AI agents to contribute and search a shared knowledge commons, so that solutions learned by one agent become available to all connected agents. | |
| BabyBuddy MCP Server amirkaromashkin/babybuddy-mcp Integrates with self-hosted BabyBuddy to log and retrieve baby care data such as feedings, sleep, diaper changes, and measurements via natural language. | |
| MetaTrader 5 MCP Server amirkhonov/metatrader5-mcp Enables comprehensive access to the MetaTrader 5 trading platform for retrieving market data, managing accounts, and executing trading operations. It provides 32 specialized tools for interacting with MT5 functionalities, including historic | |
| Sond Core API MCP Server amirlazarovich-git/sond-core-api Enables interaction with the Sond Core API through the Model Context Protocol. Auto-generated from the OpenAPI specification at https://core-api-lb.sond.com/api-json to provide programmatic access to Sond's services. | |
| senior-sde-mcp-guard amirmadani/senior-sde-mcp-guard Enforces AST-based architectural guardrails on AI-generated code, blocking writes that violate maintainability, security, or complexity rules and prompting immediate refactoring. | |
| CanIUse MCP amirmahdi-kaheh/caniuse-mcp Provides intelligent CSS/JS feature compatibility checking with configurable browser targets, polyfill support, and smart project scanning. Enables developers to automatically detect browser compatibility issues and get actionable remediati | |
| Pega MCP Server amirmcs/pega-mcp Enables interaction with Pega case operations through a metadata-driven tool layer, allowing users to fetch, update, and manage cases. It supports standard Pega actions such as retrieving case details, attaching documents, and submitting ca | |
| mcpserve amirnaghibi/mcpserve A minimal, decorator-based framework for building MCP servers in Python with zero dependencies. It enables you to define tools and resources via simple decorators, handling JSON-RPC protocol, type inference, and stdio transport automaticall | |
| Naver Booking MCP amiro-lab/booking-mcp Enables users to query real-time reservation availability for Naver Booking places in Korea, including beauty salons, restaurants, and other categories. | |
| Hyperon-MCP amiroussama/hyperon-mcp An MCP server that gives coding agents persistent, scoped symbolic memory with PLN/NAL inference on the OpenCog Hyperon MeTTa stack. | |
| Photo MCP amirrezasalimi/photo-mcp Enables searching Pinterest and Unsplash for images, including query-based search, photo-seeded Pinterest search, and finding similar Pins, with paginated results and optional attribution. It also supports saved browser logins, session stat | |
| codex-claude-bridge amirshayegh/codex-claude-bridge MCP server that enables Claude Code to send code and plans for review by OpenAI Codex, returning structured feedback inline. | |
| GitLab MCP Server amirsina-mandegari/gitlab-mr-mcp Connects AI assistants to GitLab, allowing users to manage merge requests, view reviews, and interact with discussions through natural language queries. | |
| dev.io MCP Server amirtaherkhani/dev-io-mcp Captures AI conversation summaries, converts them to Markdown posts, and manages local or remote publishing with metrics tracking. | |
| PostgreSQL API SSH MCP Server amirtlinov/sentryfrogg-mcp A universal MCP server that enables AI agents to securely manage PostgreSQL databases, make API requests, and execute SSH commands with features for database analysis, schema editing, and data operations. | |
| outlook-local-mcp amirulmenjeni/outlook-classic-windows-mcp Enables local automation of classic Outlook for Windows via COM, allowing email search, folder listing, calendar leave block creation, and contact/recipient management without needing cloud APIs or admin approval. | |
| MCP Server for Up-to-Date Library Documentation amirupskill/mcp-server Provides Large Language Models with real-time access to the latest documentation for Python libraries like Langchain, LlamaIndex, and OpenAI, enabling accurate and up-to-date code suggestions. | |
| mcp-server-duckdb amishra98/mcp-server-duckdb Enables interaction with a DuckDB database through the Model Context Protocol, allowing SQL queries, table creation, and schema inspection via a unified query tool. Supports optional read-only mode to prevent write operations and maintain d | |
| SAP MCP Server amistaus-ava/sbo-mcp-hana Enables AI clients to query live data from SAP HANA and SQL databases through read-only SELECT queries with CSV-formatted results. | |
| Gmail MCP Server amit-confer/gmail-mcp-server Enables interaction with Gmail through the Gmail API, allowing users to list, read, search emails, create and send drafts, and get email summaries through natural language commands with OAuth2 authentication. | |
| Superset MCP Server amit-dalal-1/superset_v4_mcp Local stdio MCP server for reviewing Apache Superset dashboards, retrieving chart data, executing SQL through SQL Lab, and creating or updating saved queries. | |
| TradingView MCP Jackson amit-fs/tradingview-mcp-remodified Enables AI agents to interact with TradingView Desktop via Chrome DevTools Protocol for automated morning briefs, chart analysis, Pine script development, and trading workflows. | |
| Postman MCP Generator amit-lakhani/mcp1 An MCP-compatible server that provides tools for integrating selected Postman API requests, allowing LLMs like Claude to interact with APIs through natural language. | |
| fortax-demo-shoot amit-voais/fortax-demo-shoot Enables turning a product URL into a narrated, branded demo video in your own voice, with automated planning, recording, and editing for multiple aspect ratios. | |
| nanobanana-mcp amit-y11/nanobanana-mcp Enables text-to-image generation and image editing or composition with Google's Gemini image models via MCP tools, prompts, and resources. Supports automatic model selection, aspect ratio and resolution control, curated prompt templates, an | |
| JDD-Agent OS amit11-ibm/jdd-agent-os-mcp MCP-native evolution control plane that discovers, tests, governs, versions, and promotes improved AI agents. Integrates with LocalLLM-MCP for real or simulated model evaluation. | |
| kernel-mcp amit11-ibm/kernel-mcp An MCP server that enables AI-powered Linux kernel development, exposing tools for symbol search, static analysis, build automation, QEMU/GDB debugging, and more via IBM Bob. | |
| LocalLLM-MCP amit11-ibm/localllm-mcp-github MCP server that exposes local llama.cpp LLM models to IBM Bob in VS Code via STDIO, enabling natural language interaction with models like Granite, Nemotron, Gemma, Qwen, and Llama. Configuration is managed through a single models.json file | |
| MCPyDoc amit608/mcpydoc Provides real-time access to Python package documentation, source code, and symbol search to prevent AI hallucinations. | |
| Charlotte amit92334/charlotte Gives AI agents token-efficient browser access to the web by returning structured page representations — compact orientations, targeted element queries, and on-demand detail — instead of full accessibility-tree dumps. It supports navigation | |
| Social Media Scraper amit92334/custom-mcp-server Enables AI assistants to fetch public profile and company data from LinkedIn, Facebook, and Instagram and to run Google web searches, exposing each capability as a callable tool that returns structured JSON results. | |
| x402 Crypto Price Tracker amitabhainarunachala/x402-crypto-price-tracker Enables agents to pay per call in USDC for live crypto prices and revenue intelligence via HTTP 402, with no API keys required. | |
| Poki_MCP amitabhsingh64/poki_mcp A Model Context Protocol server that provides LLMs with Pokémon data access and battle simulation capabilities, including an interactive web interface. | |
| OpenText Process Automation MCP amitagl27/opentext-pa-mcp A Model Context Protocol server that lets Claude and any other MCP-compatible client work with an OpenText AppWorks Platform tenant in plain English. | |
| openui-engine-mcp amitamit10/openui-engine Enables AI coding agents to build professional websites using a curated component registry, WCAG-verified design systems and tokens, a human-in-the-loop visual editor, and real-browser Chromium QA that verifies rendered pages and iterates o | |
| anchor-mcp amitboker/anchor-mcp An MCP server that reads a team's interviews, tickets, and docs to build a model of the product, exposing tools to ask questions, list contradictions and gaps, and draft documents, with all answers citing their source fragments. | |
| S&P 500 MCP Server amitdang1454/sp500-mcp-server Enables querying S&P 500 company data from Supabase, including fundamentals, annual financial metrics, historical price data, news sentiment, executive officers, and SEC filings, with embedded MCP App UI resources plus elicitation and sampl | |
| stdout-mcp-server amitdeshmukh/stdout-mcp-server A Model Context Protocol server that captures and manages stdout logs through named pipes, making application output available for querying and debugging in AI tools like Cursor IDE. | |
| MiniMax MCP JS amitdinh3820/minimax-mcp-js Enables MCP-compatible clients to generate images and videos, synthesize speech, clone voices, and design custom voices through MiniMax APIs, with configurable transport modes and resource output. | |
| Redshift MCP Server amitds1997/redshift-mcp-server Enables connecting to Amazon Redshift and executing SQL queries with read-only safety checks. | |
| ResearchGraph amiteshk469/researchgraph Gives existing agents controlled access to a local Neo4j research memory, letting them import papers and notes, record models, experiments, evidence and decisions, search full text plus graph neighbors, and resume bounded research sessions | |
| CareLoop amiteshsinghsps-star/careloop Enables a clinician's spoken visit to be captured and turned into a grounded, dose-free care plan that families can query through Alexa+, using extractive quotations, safety gates, and 12 tools over Streamable HTTP. | |
| memex amitg6610/memex Enables AI coding agents to save task insights as atomic, bidirectionally linked markdown cards and recall relevant ones in later sessions, with tools for searching, reading, writing, linking, archiving, and organizing a git-synced knowledg | |
| Indian Railway MCP amith-vp/indian-railway-mcp Enables searching and tracking Indian Railways trains, checking seat availability, live status, delays, and station/train codes. |
28,151–28,200 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.