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 |
|---|---|
| AuraAssist alagapie/alexa-mcp-server Enables hands-free, context-aware control of a smart home by exposing MCP tools for device control, routine orchestration with confirmation flows, object finding, scene description, recent event history, and daily briefings. It keeps a mock | |
| grepsense alaiba/grepsense Provides two-modal code search (lexical via Zoekt and semantic via ChromaDB embeddings) for AI coding agents through MCP tools, enabling fast regex and meaning-based code lookup. | |
| CodeTruth MCP Server alaikasif/codetruth A verification layer that lets AI agents safely delete code in large codebases by assessing usage paths and providing risk statuses. | |
| 法语词汇检测 alain-0721/french-vocabulary-test Enables learners to quiz themselves on French word meanings from textbook units and daily review sets, with interactive card flips, self-scoring, and per-user cloud progress storage. | |
| Stock MCP alain682/stock-mcp Enables AI agents and backends to query and analyze A-share, US equity, ETF, index, and crypto market data, technical indicators, fundamentals, money flow, news, and filings through MCP tools or HTTP APIs. It also supports agent-friendly ar | |
| Basecamp MCP Server alainalekseev6958/basecamp-mcp-server Enables MCP-capable clients to browse and manage Basecamp 3 projects, todos, messages, card tables, documents, uploads, comments, and campfire lines through OAuth-authenticated API calls. Also provides cross-project search, reports, events, | |
| CVE-Search MCP Server alainc10/cve-search_mcp Enables querying the CVE-Search API to browse vendors and products, retrieve vulnerabilities by vendor/product or CVE ID, fetch the latest CVEs with CAPEC/CWE/CPE expansions, and inspect current database information. | |
| Pingfusi alainkrylov/pingfusi Enables coding agents to publish work mid-task for real human review, receive pinned comments anchored to specific issues, and iterate until a reviewer approves the result. | |
| Excalidraw Architect MCP alainm01842/excalidraw-architect-mcp Enables AI coding assistants to turn natural-language descriptions of systems and data into editable, auto-laid-out Excalidraw diagrams across 25 types — from architecture and sequence diagrams to Gantt charts and scatter plots — plus optio | |
| CORTEX Memory MCP alainrc2005/cortex_memory_mcp Persistent semantic memory MCP server for AI agents with hybrid search, LLM scoring, and decay engine, fully local. | |
| MeaningSpace MCP alainux/meaningspace Free, deterministic, theory-traceable computational-creativity framework that generates, develops, contrasts, evaluates, and synthesizes structured creative ideas through MCP, with no accounts, database, or model inference. | |
| Authorize.net MCP Server alamedaim-apps/authnet-mcp Provides read-only access to Authorize.net transaction reporting APIs, enabling users to query settled batches, transaction details, customer payment history, and settlement statistics directly from AI assistants. | |
| compy-mcp alameddinc/compy-mcp MCP server for searching and reading notes captured with the Compy Chrome extension, allowing AI agents to access local highlights and tasks on demand. | |
| SiteBridge alameen-2301/sitebridge Enables AI applications to read and interact with a signed-in website through Chrome by exposing visible page text and controls as MCP tools, with user-reviewed actions for navigation, clicking, form filling, dropdown selection, and scrolli | |
| FastAPI MCP OpenAPI alamkanak/fastapi-mcp-openapi A FastAPI library that provides Model Context Protocol tools for endpoint introspection and OpenAPI documentation, allowing AI agents to discover and understand API endpoints. | |
| Homestead MCP alammers83/homestead-mcp Enables an AI assistant to help run a household by judging whether conditions suit a kayak trip or dog walk, tracking pet care, and drafting sitter messages that queue for human approval. All tools run at enforced permission tiers with audi | |
| Telegram OSINT alamri-intel/telegram-mcp Enables an AI assistant to read and search the user's own Telegram account chats through a local server with no write operations. It also runs a background watcher that pre-filters incoming messages with substring, word, or regex rules and, | |
| GLPI MCP Server alan-gois/glpi-mcp Connects AI assistants to GLPI through the Model Context Protocol, enabling management of tickets, ITIL objects, assets, projects, tasks, documents, sessions, entities and massive actions via the legacy REST API. It supports GLPI 10 and 11 | |
| mcp-a11y-service alan-ho/mcp-a11y-service Enables automated WCAG 2.2 AA accessibility audits of Figma designs and webpages. Generates detailed markdown reports with severity-grouped violations, specific criterion references, and concrete fix recommendations. | |
| universal-agent-control-plane alan-vz/universal-agent-control-plane Enables centrally authoring and validating reusable agent guidance and delivering it across MCP-compatible hosts via registry resources, prompt templates, skill execution, and shared state. | |
| Accio Multi-Store MCP alan113523/accio-multi-store-mcp Enables users to query multiple authorized Accio stores through separate fixed-identity, read-only channels bound to existing store conversations, with live seller identity verification before and after account-summary queries. | |
| mcp-altair-studio alan4041207/mcp-altair-studio MCP server that enables Claude to control Altair AI Studio for data mining and machine learning tasks, including data import, cleaning, transformation, model training, clustering, association rules, and executing saved processes. | |
| ClaudeMetaMCP alan7799de/claudemetamcp Local MCP server for operating Instagram, Meta Ads, and Facebook Page from Claude Code via Meta's Graph API. Provides 20 tools for publishing, campaign management, and insights. | |
| doc-extract alanaag/invoice-extraction-mcp Enables reading entire PDF documents into validated structured JSON, including tables, key-values, and markdown, with read-only extraction tools and layout reconstruction. | |
| ticket-writer-mcp alanaag/ticket-writer-mcp Transforms free-text feature requests into well-formed tickets for Jira, GitHub, GitLab, and Linear, handling clarification, formatting, and duplicate detection while leaving the actual submission to the caller. | |
| auto-mcp-server alanbuxton/auto-mcp-server Enables LLMs to interact with any REST API that has an OpenAPI specification by providing a lightweight MCP server that translates between natural language and API calls. | |
| remote-mcp-server-authless alanchenx/remote-mcp-server-authless A stateless remote MCP server deployed on Cloudflare Workers without authentication, implementing the MCP 2026-07-28 specification and supporting custom tools. Can be connected to Cloudflare AI Playground and local MCP clients like Claude D | |
| Insurance Campaign MCP Server alandexiong/mcp_campaign_server Enables AI-powered insurance marketing campaign management with audience targeting recommendations and personalized content generation for different insurance products and marketing channels. | |
| ElevenLabs Audio MCP for ChatGPT alandyallworwor-cmd/mcp_eleven Enables ChatGPT to generate ElevenLabs speech from text, returning playable MP3 audio, with voice listing and preference management. | |
| Marketing Connect MCP Services alanedavis/mcp A Model Context Protocol server for Marketing Connect AI integrations that provides tools, resources, and prompts for AI models to interact with marketing systems and data. | |
| TPCU MCP Server alaner652/tpcu-mcp Enables AI applications supporting MCP to log into a university academic affairs system and query schedules, absences, grades, and leave records through natural-language conversation. It also lets users submit or withdraw leave requests and | |
| GitHub MCP Server alanezequiel112/proyecto-m5-mcp-github MCP server that enables AI agents to perform GitHub operations like creating repositories, issues, and commits through natural language. | |
| Agency Opportunity Radar alanfnl/agency-opportunity-radar Enables users to research public websites, identify SEO problems, match them to agency services, and score opportunities with evidence. | |
| Octagon MCP Server alang5620/octagon-mcp-server Enables natural-language financial and market research across SEC filings, earnings transcripts, company financials, stock and crypto data, and prediction markets, returning structured, source-backed answers for investors, analysts, and res | |
| sportlink-mcp alangr12/sportlink-mcp Enables AI agents and LLMs to query SportLink data through natural language, including searching for events, trainings, jobs, clubs, and coaches, as well as viewing profiles and calculating matches. | |
| Swagger/Postman MCP Server alangreyjoy/swag-mcp Server that ingests Swagger/OpenAPI specifications and Postman collections, providing just 4 strategic tools that allow AI agents to dynamically discover and interact with APIs instead of generating hundreds of individual tools. | |
| ValueScope alanhewenyu/valuescope Standardized DCF valuation engine for stocks (A-shares, Hong Kong, US, Japan). One run_dcf tool with an analyst-style two-phase flow: baseline valuation from 5-year historicals, then a final valuation with reasoned assumptions — value bridg | |
| newrelic-mcp alanhoff/newrelic-mcp MCP server for New Relic workflows, enabling NRQL queries, NerdGraph access, entity lookup, logs, alerts, dashboards, and service levels. | |
| mcp-ess-proposal alanhuang168/mcp-ess-proposal Generates deterministic solar and energy storage system preliminary proposal calculations from structured customer inputs. | |
| Weni MCP Server alanjaeger/weni-mcp MCP server that enables querying the Weni Insights Engine API for conversation metrics such as totals, resolved, unresolved, and transferred conversations. | |
| beaver-mcp alanko0511/beaver-mcp Provides Google Maps search, navigation, and travel time estimation alongside Lunch Money financial management, all accessible via a Cloudflare Workers MCP server with OAuth authentication. | |
| Graphiti-Memory MCP Server alankyshum/graphiti-memory Enables storing and querying memories in a Neo4j knowledge graph with automatic entity extraction. Supports adding episodes, searching entities and relationships, and managing graph data through natural language. | |
| google-classroom-mcp alanmagno1/google-classroom-mcp Enables students to query Google Classroom courses, pending assignments, grades, announcements, and materials, and to attach files or submit assignments, with support for multiple Google accounts from any MCP client. | |
| Overleaf CE MCP Server alanmagno1/overleaf-ce-mcp Enables AI assistants and agents to explore, read, live-edit, patch, create, and delete files across projects on a self-hosted Overleaf Community Edition deployment, with OT-safe edits that sync instantly to open browser tabs. It also trigg | |
| tuaulavirtual-unam-mcp alanmagno1/tuaulavirtual-unam-mcp Enables querying courses, assignments, deadlines, and materials from the UNAM Moodle virtual classroom, as well as downloading files and submitting assignments through natural language. | |
| code-review-mcp alanniew/code-review-mcp An MCP server that provides local code quality analysis for AI coding assistants, supporting file analysis, git diff review, and full project scanning with quality scoring. | |
| Betaflight MCP Server alanogic/betaflight-mcp Enables AI clients to read and configure flight controllers running Betaflight firmware over USB serial using MSP, with tools for telemetry, battery monitoring, PID/rates tuning, filters, modes, and saving configuration. | |
| Odoo MCP Server Advanced alanogic/mcp-odoo-adv Enables AI assistants to interact with Odoo ERP systems through the Model Context Protocol. Provides comprehensive access to Odoo models, records, and methods with enhanced features like employee search, holiday management, and flexible dom | |
| Odoo MCP Server alanogic/oo Enables AI assistants to interact with Odoo ERP systems through XML-RPC integration. Provides access to Odoo models, records, employee search, holiday management, and custom method execution via the Model Context Protocol. | |
| prompte-mcp alanroybal/prompte-mcp An MCP server that automatically enhances user prompts by applying advanced engineering techniques like chain-of-thought and few-shot reasoning based on identified intent. It optimizes technique selection through local learning and integrat |
25,751–25,800 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.