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 |
|---|---|
| @agentkarma/mcp agentkarmaio/mcp Exposes AgentKarma's read-only trust and reputation tools (karma, agents, succession, bonds, check_trust) to any MCP client for checking on-chain agent reputation. | |
| agentkeys-mcp agentkeys-io/agentkeys-mcp Enables AI agents to securely manage API credentials and make proxied API calls through AgentKeys, keeping secrets hidden from the agent. | |
| agentkit-mesh agentkitai/agentkit-mesh Enables agent-to-agent discovery and delegation via MCP, with tools for registering agents, discovering them by keyword matching, and delegating tasks over HTTP. | |
| AgentLadle MCP AKShare agentladle/mcp-akshare Provides 46 financial data tools for AI assistants covering A-share, HK, US markets, macroeconomics, funds, and derivatives, powered by AKShare. | |
| AgentLadle MCP CNINFO agentladle/mcp-cninfo Enables AI assistants to discover, download, parse, and search China A-share announcements from CNINFO (巨潮资讯网) through six structured tools. | |
| mcp-dart agentladle/mcp-dart Provides tools for discovering, downloading, parsing, and searching Korean DART financial reports, enabling AI assistants to access Open DART data through structured tools. | |
| mcp-hkexnews agentladle/mcp-hkexnews MCP server for discovering, downloading, parsing, and searching Hong Kong listed company announcements from HKEXnews through 6 structured tools. | |
| agentladle-mcp-reoi agentladle/mcp-reoi Enables AI assistants to perform multi-stage residual income projections, discounting, and enterprise value bridging analysis using standardized financial data inputs. | |
| agentladle/mcp-sec It enables AI assistants (Claude, Cursor, etc.) to access SEC EDGAR data through 6 structured tools — from discovering available filings to keyword-searching within their pages. | |
| AgentLatch agentlatch/agent-latch Monitor-only proxy for any MCP server: records tool calls with secrets masked, flags instructions hidden in tool definitions, and seals the trace in a tamper-evident hash chain. Also a static scanner for AI agent code, mapped to the OWASP A | |
| Basic MCP Server agentmail-to/agentmail-smithery-mcp A minimal template server demonstrating MCP tools, resources, and prompts built with Smithery SDK. Provides starter examples including a hello tool, history resource, and greet prompt. | |
| AgentMail agentmail-to/agentmail-toolkit Gives on-the-fly inboxes to AI agents. Agents / LLM's can send, receive, and take action in isolated inboxes. Built for AI unlike Gmail. Check us out at agentmail.to | |
| agentminds-mcp agentmindsdev/mcp-server MCP server for AgentMinds collective intelligence platform, enabling AI agents to scan websites for security/SEO/performance issues, pull personalized recommendations, and share findings across the network. | |
| ask-llm-mcp agentming/ask-llm-mcp Enables MCP clients to send raw text prompts to inexpensive LLM models via the Devin/Windsurf backend, returning answers in result files to avoid context bloat, with support for multi-turn sessions and model discovery. | |
| AgentMode agentmode/server An all-in-one Model Context Protocol (MCP) server that connects your coding AI to numerous databases, data warehouses, data pipelines, and cloud services, streamlining development workflow through seamless integrations. | |
| hitl-mcp-server agentmp/hitl-mcp-server Bridges Claude Desktop with a HITL escalation service, enabling creation, approval, modification, and management of human-in-the-loop requests directly from the chat interface. | |
| AgentMux MCP Server agentmuxhq/agentmux-mcp Enables AI agents such as Cursor, Claude Code, ChatGPT/Codex, and Grok bots to ask each other questions and receive replies in the same chat through a local-first message bridge with tickets, wake mechanisms, rooms, and safety defaults. | |
| ZeroCrawl MCP agentnex/zerocrawl-mcp ZeroCrawl MCP is a 100% free web crawling and scraping server for AI agents, offering tools like page scraping, domain crawling, metadata extraction, screenshots, sitemap parsing, batch scraping, and search-and-crawl. It requires no API key | |
| Agentoom Knowledge agentoom/knowledge A self-hosted, MIT-licensed MCP server that securely connects private documents and markdown files to LLMs. It provides a lightweight, local-first RAG infrastructure compatible with any MCP-enabled AI client or framework. | |
| AgentOps MCP agentops-ai/agentops-mcp The AgentOps MCP server provides access to observability and tracing data for debugging complex AI agent runs. This adds crucial context about where the AI agent succeeds or fails. | |
| SeaTalk MCP Server agentp-amateur/seatalk-mcp-server Enables sending and reading SeaTalk messages, including DMs, group chats, and message history, plus employee lookup via the SeaTalk Open Platform API. | |
| taskvault agentp-codes/project-eurycleia Enables AI agents to access only task-relevant data with secrets hidden and personal details pseudonymized, while enforcing destination policies to prevent data leakage even under prompt injection. | |
| ClawPact MCP Server agentpact/mcp Connects AI agents to the ClawPact marketplace, enabling them to discover tasks, submit bids, and manage the full execution lifecycle through standardized tool calls. It provides seventeen specialized tools for on-chain delivery, escrow man | |
| agentic-patterns agentpatternscatalog/mcp Exposes the Agentic Patterns Catalog as MCP resources and tools for AI coding agents to search, retrieve, and recommend patterns, recipes, frameworks, methodologies, and anti-patterns. | |
| Indonesia Financial Data MCP agentpixelated/indonesia-financial-data-mcp Citation-first MCP server for official Indonesian financial data from IDX, BPS, and KSEI, providing tools to access company profiles, financial reports, statistical tables, and investor demographics. | |
| Casebook MCP agentpostmortem/casebook-mcp Enables agents to query a registry of documented AI-agent failures for debugging incidents, deployable on Cloudflare Workers. | |
| AgentPrism Workflows agentprism/agentprism-workflows Run dynamic, multi-agent workflow scripts — agent(), parallel(), pipeline() — over real coding agents (Claude Code and OpenAI Codex), with deterministic journaling, resume, token budgets, and git-worktree isolation. | |
| xap-mcp agentra-commerce/xap-sdk Enables AI assistants such as Claude and Cursor to discover and verify agents, negotiate offers, execute conditional settlements, and verify receipts and complete multi-agent workflows through eight MCP tools. | |
| agentraas agentraas/agentraas Enables AI agents to execute real-world API actions with exactly-once reliability, deduplication, auditing, and human-in-the-loop safeguards via MCP. | |
| Universal Agent Economy OS agentrails/agent-economy-os Foundational MCP/A2A-native core platform for secure credential injection, native x402 micropayments, and Agent-to-Agent routing. | |
| Gym MCP Server agentring/gym-mcp-server Expose any Gymnasium environment as an MCP server, automatically converting the Gym API into MCP tools that any agent can call via standard JSON interfaces. | |
| Uno MCP Stdio agentrix-ai/uno-mcp-stdio Local stdio proxy for Uno MCP Gateway that enables MCP clients without OAuth support to securely connect to authenticated remote servers. | |
| Agents Registry MCP Server agents-registry-com/mcp-server Enables AI agents to discover each other and communicate through cryptographically verified messaging and secure inbox management via the Agents Registry. It provides tools for Ed25519-based identity authentication, message signing, and age | |
| clinicaltrials-mcp agents100x/clinicaltrials-mcp Enables conversational access to 400,000+ clinical trials on ClinicalTrials.gov, allowing users to search, compare, and retrieve trial details using plain English through MCP-compatible clients like Cursor and Claude Desktop. | |
| zotero-cli-cc agents365-ai/zotero-cli-ai MCP server that exposes 45 tools for Zotero reference management, enabling AI agents to read/write items, search, extract PDF text, and manage workspaces via the Zotero CLI. | |
| AgentScore MCP Server agentscore-trustless/agentscore-mcp Provides access to the AgentScore Registry on Base Sepolia to retrieve agent reputation scores, history, and registration details. It enables trustless querying of agent performance metrics through standard Model Context Protocol tools. | |
| AgentScore agentscore/mcp Provides trust and reputation tools for AI agent wallets within the x402 payment ecosystem and ERC-8004 agent registry. It enables users to perform wallet reputation lookups, real-time risk assessments, and browse registered agents. | |
| AgentVPS agentsdance/agentvps Turns your own VPS into an agent's remote computer, exposing shell and code execution, persistent workspace files, Bash PTYs, a Chromium browser, notes, scheduled tasks, and a streamed Linux desktop over MCP. Clients such as Claude Code or | |
| laozhang-image MCP agentseo/laozhang-image-mcp Enables image generation and editing using laozhang.ai's OpenAI-compatible API, with tools for text-to-image and image-to-image transformations. | |
| Agentset agentset-ai/mcp-server An open-source platform for Retrieval-Augmented Generation (RAG). Upload documents and query them ⚡ | |
| Azure DevOps MCP Server agentsgang/azure-devops-mcp Enables interaction with Azure DevOps services including work items, builds, releases, test plans, repositories, and search via natural language commands from a code editor. | |
| AgentsGate agentsgate/agentsgate Enables AI agents to securely call MCP tools with risk scoring, checkpoints, rollback, and approval workflows. | |
| AgentsID Guard agentsid-dev/shell-guard MCP server that protects shell, file, database, git, and HTTP operations with per-agent permission rules | |
| agentskill-mcp agentskill-sh/mcp-server MCP server for discovering and installing AI agent skills from agentskill.sh. Search skills across platforms, browse trending skills, and install them with built-in security scanning. | |
| agents-mcp-server agentsmcp/agents-mcp-server A set of MCP servers that provide AI agents with safe, composable access to web3 market data and trading, featuring read-only intelligence and execution modes with SIM/PAPER/LIVE safeguards. | |
| MCP Test Server agentspan-ai/mcp-testkit A Python MCP server with 65 deterministic tools across 8 groups, supporting stdio, HTTP, and REST API transports for consistent MCP protocol testing. | |
| AgentStack MCP agentstacktech/agentstack-mcp Enables AI agents to run 700+ backend actions across data, auth and RBAC, payments and wallets, CRM, hosting, RAG, bots, scheduling, and automation through a single execute tool, remotely or via a stdio bridge. | |
| AgentStandard agentstandard/mcp-server Certified AI agent package marketplace. Browse and install verified packages for Claude, ChatGPT, Gemini, and OpenClaw — covering health, finance, productivity, career, and more. Stateful and with intent. | |
| mcp-sleep agentsworkingtogether/mcp-sleep Tool that allows you to wait a certain time to continue the execution of an agent. | |
| agent-task agenttaskllc/agenttask-plugin AgentTask is a governed work platform where human teams and AI agents share one backlog. Hosted remote MCP server (streamable HTTP, OAuth 2.1 or org API keys) with 60+ tools for tasks, subtasks, projects, groups, labels, notes, comments, at |
24,501–24,550 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.