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 |
|---|---|
| Sub-Agents MCP Server claudiakilic58400/sub-agents-mcp Enables any MCP-compatible client to run reusable, Markdown-defined coding agents (such as reviewers, test writers, or investigators) through a configurable coding CLI backend, returning results into the same conversation. Agent definitions | |
| MCP GitHub Project Manager claudiar27119/mcp-github-project-manager Enables AI coding agents and human managers to coordinate work on GitHub Projects v2 through 20 tools and 169 actions for autonomous task checkout, heartbeats, reviews, token budgets, PRD generation, sprint planning, issue triage, and PRD-t | |
| Codex Control Plane MCP claudiaruiz56245/codex-control-plane-mcp Enables MCP clients to drive Codex Desktop and codex-app-server through durable asynchronous operations for long-running tasks, with polling, approvals, Plan Mode workflows, retry-safe submission, and structured final reports. | |
| Oh My Cassette claudiayoung104/oh-my-cassette A local MCP server that turns plain-language chat prompts about a folder of raw clips into finished, beat-synced montage videos — handling shot selection, music matching, subtitles, transitions, and picture-in-picture, and returning a revie | |
| Ollama MCP Server claudiayoung104/ollama-mcp Enables MCP-compatible applications to interact with local and cloud-hosted LLM models for model management, text generation, chat, embeddings, and web search/fetch. | |
| code-intel claudin-io/code-intel Enables agents to perform local hybrid code search and code intelligence across a workspace, including semantic and full-text search, symbol lookup, file outlines, and caller analysis. | |
| CamoFox MCP claudine32/camofox-mcp Enables MCP-compatible AI agents to control an anti-detection browser for navigation, interaction, search, extraction, downloads, multi-tab workflows, and persistent sessions. Supports stdio and HTTP transports for desktop or remote MCP cli | |
| LAPRAS MCP Server claudine5672/lapras-mcp-server Enables AI assistants to search and retrieve job postings and to view, create, update, or delete career-profile information such as work experiences, summaries, goals, and technical skills. | |
| Tapetide claudinel72489/nse-bse-indian-stock-market-data-mcp Gives AI assistants live, structured NSE and BSE market data across 8,200+ listed stocks, so users can ask in plain English for share prices, quarterly financials, technical indicators, a 326-ratio screener, FII/DII flows, option chains and | |
| mcp-shodan claudineveenstra4642/mcp-shodan Enables AI agents to query Shodan for host reconnaissance, device searches, DNS lookups, and CVE/CPE vulnerability intelligence, including CVSS, EPSS, and KEV data. | |
| Vectorize MCP Server claudio0400/vectorize-mcp-server Enables users to perform vector search and document retrieval, extract and chunk files into Markdown, and generate private deep research reports from a configured pipeline. | |
| arxiv-latex-mcp claudio50609/arxiv-latex-mcp Enables MCP clients to fetch and process arXiv papers by accessing their LaTeX sources, including full flattened LaTeX, abstracts, section lists, and specific sections. This allows accurate interpretation of equations, notation, and mathema | |
| Remote MCP Server (Authless) claudiobastos/remote-mcp-server-authless A template for deploying a Model Context Protocol server on Cloudflare Workers without authentication requirements, allowing integration with AI models through the Cloudflare AI Playground or Claude Desktop. | |
| AWS Cost Explorer MCP Server claudiodevos/aws-cost-explorer-mcp-server Enables users to query and analyze AWS spend and Amazon Bedrock usage data through natural language, including breakdowns by service, region, user, model, and instance type. | |
| Obsidian RAG MCP Server claudiogarza/obsidian-rag-mcp Enables semantic search and content retrieval from local Obsidian vaults through the Model Context Protocol. It allows AI assistants to query notes by meaning, filter by tags, and access full note content for enhanced knowledge integration. | |
| MCP Datadog Server claudiolazaro/mcp-datadog-server Enables interaction with Datadog APIs through automatically generated tools from Postman collections. Supports monitoring operations, log management, metrics submission, and other Datadog functionality through natural language. | |
| CardioTriage MCP Server claudiomedina17/cardiotriage-mcp Provides phenotype-aware cardiovascular triage tools including FHIR R5 case retrieval, missing-data analysis, ECGFounder-backed ECG interpretation, risk summarization, and structured SBAR handoff in multiple languages. | |
| Code Graph MCP claudioscheer/code-graph-mcp A local MCP server that indexes codebases into Neo4j and provides tools for code analysis, dependency visualization, and impact assessment. | |
| workflow-atlas claudiu-deving/workflow-atlas Enables an AI assistant to author algorithm storyboards, workflow maps, and UI styling through MCP, serving a local web app for visualizing and reviewing them. | |
| Mealie MCP Server claudiuio/mealie-mcp Enables LLMs to save recipes directly to a Mealie instance by converting schema.org/Recipe format and handling the Mealie API workflow automatically. | |
| devenv-mcp-server claudiujitea/devenv-mcp-server Provisions Docker-based development environments on demand, allowing AI agents to create, manage, and inspect containerized dev environments without manual setup. | |
| Bulwark claudius-ars/bulwark Acts as an MCP gateway between AI agents and upstream tool servers, evaluating YAML policies on every tool call, injecting real credentials at the last mile, scanning requests and responses for secrets, PII, and prompt injection, and record | |
| Gemini Research MCP claudiusbotticus/gemini-research-mcp Provides real-time web research and URL summarization capabilities using Gemini 2.5 Flash with native Google Search grounding. It enables users to perform factual searches and summarize web content directly within MCP-compatible clients lik | |
| Super Productivity MCP Server claus-92/super-productivity-mcp Enables Claude to interact with Super Productivity's local REST API for task, project, and tag management, including CRUD operations, status checks, and daily planning prompts. | |
| aedificium-template clausd/aedificium-template Enables a personal learning notebook and lexicon with Claude-native chat, supporting markdown notes, definitions, PDFs, math rendering, wiki-links, and git auto-commit. | |
| MCP Unified Server v6 clausmcp/mcp-unified-server-v6 A comprehensive local offline MCP server with over 300 tools for file operations, office documents, PDFs, code execution, databases, web browsing, memory, and cognitive functions, designed to work offline except for web search and email. | |
| tossinvest-mcp clauzewitz/tossinvest-mcp Wraps the Toss Securities Open API so users can look up Korean and US stock quotes, stock and sector data, market indicators, and their own account holdings, orders, buying power, and conditional orders through natural-language tool calls. | |
| Binder clavarium/clavarium-binder Empowers AI agents to keep lists of records—adding, showing, noting on, attaching to, and moving items through states—while the binder itself stays outside the agent's reach. Human approval gates, per-list read/change access, and archive-on | |
| parley-mcp clavarium/clavarium-parley Enables command-line AI agents to communicate with a person through seven verbs for telling, asking, showing files, reporting activity or status, reading replies and open questions, and closing questions. It writes the same exchange files a | |
| DevRev MCP server clavia-labs/mcp-server-7 Enables searching, retrieving, creating, and updating issues and tickets in DevRev using natural language. | |
| Email Triage MCP claw-factory/email-triage-mcp Enables AI agents to interact with Gmail for classifying messages, extracting action items, and performing batch inbox triage. It supports automated labeling, smart replies, and task creation for external platforms like Linear, Jira, and To | |
| TRUSS MCP Server claw-factory/truss-mcp A developer tool suite for Claude Code that automates the creation of CLAUDE.md files, project rules, and specialized AI agent definitions. It also provides advanced features for generating n8n workflows, performing security audits, and cre | |
| Google Search MCP Server claw256/mcp-web-search Provides Google search capabilities, web content extraction, and screenshot functionality with advanced bot detection avoidance through the MCP protocol. | |
| clawborrator-mcp clawborrator/channel_v1 Connects Claude Code instances to a clawborrator hub via WebSocket, enabling cross-session communication, file exchange, and agent dispatch. | |
| ClawCall MCP Server clawcall-dev/clawcall Enables AI agents to make real outbound phone calls to US/Canada numbers, handle conversations, and return transcripts and recordings via the Model Context Protocol. | |
| a2a-mcp-bridge clawd-ops/a2a-agent-bridge A stdio MCP server that allows MCP-capable agents to call an A2A endpoint, enabling agent-to-agent messaging through the A2A protocol. | |
| @clawdate/mcp clawdate/clawdate-mcp MCP server for Clawdate, enabling AI agents to register, create profiles, discover matches, converse, and connect. | |
| coinopai-mcp clawdbotworker/coinopai-mcp Local stdio MCP server for x402-powered paid crypto intelligence, decision verification, and agent automation search over USDC micropayments on Base. | |
| imagegen-mcp-x402 clawdbotworker/imagegen-mcp AI image generation from text prompts via x402 micropayments on Base. $0.10 USDC per image, paid automatically from your wallet. No API key required. | |
| universal-memory-service clawdbrunner/universal-memory-service Self-hosted service providing unified memory search and write operations across file-based memory, vector embeddings, and the Graphiti temporal knowledge graph, accessible via HTTP API or MCP stdio transport. | |
| fizzy-mcp clawdcraft/fizzy-mcp MCP server for Fizzy, Basecamp's open-source Kanban tool. Enables AI assistants to manage boards, cards, tags, columns, and comments via API. | |
| Discord Vencord MCP Bridge clawdecode/discord-vencord-mcp Enables MCP-compatible AI agents to interact with Discord through a local Vencord plugin inside the native desktop client, providing over 30 tools for messaging, server management, roles, moderation, and invites without bot or user tokens i | |
| ESXi MCP Server clawdieclawdita/esxi-mcp-server Enables administering VMware ESXi or vCenter hosts through MCP clients, exposing tools to authenticate, list, create, clone, power on and off, and delete virtual machines, and to retrieve VM performance statistics. Supports both native SSE | |
| ClawdsBet MCP Server clawdsbet/clawdsbet-mcp Enables AI assistants to interact with the ClawdsBet prediction arena, allowing them to view leaderboards, browse markets, get bot statistics, and place bets. | |
| x402-mcp clawfred/x402-mcp Calls an x402-paid HTTP API and automatically handles payment when a 402 Payment Required response is received. | |
| @clawket/mcp clawket/mcp An MCP server that enables LLMs to pull-based search through Clawket's RAG repository for exploratory and conditional queries. It provides read-only access to search artifacts, tasks, and decisions via HTTP API. | |
| clawmem-mcp-server clawmem-ai/clawmem-mcp-server An MCP server that leverages a GitHub-compatible API as a durable memory store for AI agents, enabling automatic memory storage, recall, and management without requiring signup or API keys. | |
| captcha clawpaw-beep/captcha-solver Enables agents to recognize text, arithmetic, slider, click, and rotation challenges locally, returning answers, drag distances, click coordinates, confidence, and human-like interaction trajectories. | |
| ot-dossier-mcp clawrence124/ot-evidence-invariants Enables reproducible target-disease evidence dossier assembly and validation by replaying frozen Open Targets GraphQL responses and checking citations and structured assertions against deterministic scientific contracts. | |
| ClawResearch MCP Server clawresearch-official/clawresearch-mcp Enables AI assistants to interact with the ClawResearch autonomous AI research platform, including paper search and submission, peer review management, and agent collaboration. |
39,201–39,250 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.