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 |
|---|---|
| codebuddy-matrix-channel evlon/matrix-channel Bridges Matrix chat rooms to CodeBuddy Code sessions, enabling message exchange, permission approvals, and media downloads through the MCP protocol. | |
| ZenTao Bugs MCP Server evlon/mcp-zentao-bugs Enables interaction with ZenTao bug tracking system to search products, query assigned bugs, view bug details with extracted images, and mark bugs as resolved through natural language commands. | |
| nicegui-llm-bridge evnchn-nicegui/nicegui-llm-bridge Enables LLMs to drive NiceGUI apps by exposing an interactive element tree via MCP tools for clicking and filling form values. | |
| Merovingian MCP Server evo-hydra/merovingian Enables AI agents to map cross-repository dependencies, detect breaking changes in API contracts, and assess impact across services. | |
| morpheus-mcp evo-hydra/morpheus-mcp Provides plan state management and phase gate enforcement for AI development loops. It tracks task progress and coordinates the lifecycle of agents by requiring specific evidence before advancing through development phases. | |
| PayAgent evoarislan/payagent-x402-mcp Enables AI agents to autonomously pay for metered web APIs on a per-call basis, settling x402 v2 USDC micropayments via EIP-3009 authorization on Base Sepolia without human involvement. Spending is bounded by configurable per-call caps and | |
| rag-knowledge-mcp evokateur/rag-knowledge-mcp Connects RAG knowledge bases to Claude Desktop and Claude Code, allowing retrieval-augmented generation from ingested documents. | |
| NotebookLM MCP Suite evolialexwing34/notebooklm-mcp-suite Enables interaction with Google NotebookLM through a unified CLI and MCP server, featuring automatic multi-browser authentication and support for notebook queries, source management, notes, and audio generation. | |
| FastIntercom MCP Server evolsb/fast-intercom-mcp Enables fast, local access to Intercom conversations through intelligent caching and background synchronization. Provides sub-100ms search capabilities for conversation analytics with natural language timeframes and text search. | |
| eMCP for Evolution CMS evolution-cms/evo-mcp Allows scoped administration and content management in the Evolution CMS. Agent can edit or create website from scratch. | |
| Scorecard MCP Server evolv3ai/scorecard-mcp Enables Claude and other MCP-compatible clients to access Scorecard's evaluation tools for running experiments, generating synthetic data, and analyzing model performance. It is designed to be deployed on Cloudflare Workers and integrates s | |
| Agent Wallet Firewall evolve-hodl/agent-wallet-firewall Enables AI agents to send ETH and tokens, approve token spending, and make contract calls while every transaction is decoded, simulated, checked against policy, threat lists, and user intent, with suspicious actions blocked or escalated for | |
| GEP MCP Server evomap/gep-mcp-server Exposes GEP (Genome Evolution Protocol) evolution capabilities to MCP-compatible AI agents, enabling memory recall, evolution cycles, and community-based strategy publishing for autonomous improvement. | |
| Evomi MCP Server evomi/evomi-mcp MCP server for Evomi's proxy and web scraping APIs, providing tools for managing proxy credentials, geo targeting, usage, sessions, browser profiles, and a full scraping toolkit including crawling, URL discovery, AI-powered extraction, and | |
| ASSETMCP evonar543/assetmcp A Python MCP server for searching, downloading, extracting, inspecting, and previewing game assets from multiple public sources. | |
| Roblox Bridge Agent evonar543/roblox_bridge_agent A local-first MCP bridge and script operations layer that connects coding agents to authorized Roblox Luau development clients via websocket, enabling live execution, file watching, diagnostics, permission-gated script capsules, crash detec | |
| Vision Roblox MCP evonar543/vision-roblox-mcp Automates Roblox Studio tasks via MCP by combining multiple backends for scene editing, script management, asset insertion, and playtesting with safety features like undo recordings and task leasing. | |
| LlamaIndex M2MCent ToolSpec evozim/llama-index-tools-m2mcent Enables agents to query and execute 1,005 autonomous MCP micro-services via the M2MCent Gateway with x402 V2 micropayment protocol. | |
| telegram-bot evr1kys/telegram-bot Enables MCP clients to read allowlisted Telegram chats and send messages as a bot, with access control, local secrets, and duplicate send protection. | |
| Safe Code Sandbox evrabhinav/safe-code-sandbox Enables AI agents to run untrusted, model-generated Python code in a locked-down throwaway Docker container with enforced isolation and resource limits. Supports starting, checking, and stopping asynchronous runs while returning structured | |
| aiproject-mcp evrenonur/aiproject-mcp MCP server for managing AIProject tasks and projects, providing CRUD operations for projects, tasks, and assignments with API key authentication. | |
| Vulnerable MCP Server evrenyal/mcpsecurity Intentionally vulnerable Model Context Protocol (MCP) server designed for security research that processes natural language queries through an LLM to execute SQL queries or shell commands without restrictions. | |
| BambooHR MCP Server evrimalacan/mcp-bamboohr Enables AI assistants to interact with BambooHR's API through natural language queries. Provides access to employee data, time off management, company files, and HR operations with comprehensive tools for workforce management. | |
| Bitbucket Server MCP evrimalacan/mcp-bitbucket-server Connects AI assistants to Bitbucket Server/Data Center for reviewing pull requests, managing repositories, searching users, and more. | |
| Microsoft Graph MCP evrimalacan/mcp-microsoft-graph Enables AI assistants to interact with Microsoft 365 through the Microsoft Graph API, including searching Teams messages, managing chats, and sending messages. | |
| PDF-RAG evsdrg/pdf-rag Enables agents to search local component-manual corpora via hybrid semantic, full-text, and substring retrieval with table recognition and OCR fallback for scanned pages. Provides tools for literal/regex grepping, reading single or multiple | |
| evsoch-mcp evsoch/evsoch-mcp A secure thin client bridge for EVSocho vehicle data ingest, enabling tools like health check, brand listing, and vehicle draft validation/upsert via daily tokens and server-side auth. | |
| Ditto MCP Server evtapps/ditto-mcp Enables secure execution of Ditto DQL (Data Query Language) queries over HTTPS with safety checks and capability gating. Supports parameterized queries, health checks, and configuration management for Ditto database operations. | |
| Gmail MCP evyatar108/gmail-mcp Local MCP server providing Gmail tools (search, read, draft, send, trash) via Google's official API, integrated with GitHub Copilot CLI. | |
| arxiv-latex MCP Server ewa41043/arxiv-latex-mcp Enables MCP clients such as Claude Desktop, Claude Code, and Cursor to fetch and process arXiv papers' original LaTeX source so equations and mathematical notation are interpreted precisely. Exposes tools to retrieve a paper's full flattene | |
| SandBase MCP Bridge ewa619/cli Enables supported AI clients to discover, inspect, and execute 2,000+ models and APIs, including free data APIs and paid LLM, image, video, and audio calls, with OAuth, pricing checks, and rollback. | |
| Notion MCP Server ewa9731/notion-mcp-server Gives AI agents read/write access to Notion through the Model Context Protocol, enabling them to create and edit pages, query databases, append blocks, apply templates, comment, and upload files in plain language. It authenticates with a si | |
| Cinema4D MCP Server ewae796/cinema4d-mcp Enables Claude to drive Cinema 4D through natural-language prompts, creating and modifying 3D scenes via tools for primitives, objects, cameras, animation, lights, materials, Redshift inspection, MoGraph cloners and fields, dynamics, and re | |
| LINE OA MCP Ultimate ewahakansson626/line-oa-mcp-ultimate Enables AI agents to operate one or many LINE Official Accounts through natural conversation, covering broadcasts, Flex and tappable Rich Messages, rich menus, coupons, audiences, insights, LIFF, webhooks, and LINE Shopping. Includes pre-fl | |
| WooCommerce MCP Server ewahunter1015/woocommerce-mcp-server Enables management of ecommerce store data—products, orders, customers, shipping, taxes, discounts, reports, and configuration—through the WordPress REST API using JSON-RPC 2.0. | |
| excalidraw-architect-mcp ewaiyer/excalidraw-architect-mcp Enables AI assistants to generate and revise auto-laid-out, hand-drawn-style Excalidraw diagrams across 25 types — from architecture and flowcharts to sequence diagrams, ER models, Gantt charts, and scatter plots — with architecture-aware s | |
| pfSense MCP Server ewal96623/pfsense-mcp-server Enables natural-language management of a pfSense firewall from Claude Desktop, Claude Code, or any MCP client, covering firewall rules, NAT, VPNs, DNS, DHCP, certificates, logs, and diagnostics across 332 tools. Includes safety guardrails s | |
| dbt-doctor ewalefebvre/dbt-doctor Enables AI assistants to audit dbt project health, profile warehouse data, detect schema drift, and safely generate or update dbt documentation and tests through natural language. | |
| Gitingest-MCP ewamendes48/gitingest-mcp Enables MCP clients such as Claude Desktop, Cline, and Cursor to extract information from GitHub repositories, including repository summaries, project directory structures, and file contents. It runs gitingest as a Model Context Protocol se | |
| ATProto MCP Server ewanc26/atproto-mcp-server An MCP server for interacting with the AT Protocol (ATProto) ecosystem, including Bluesky, providing tools for identity, profiles, and social discovery. | |
| byerisk-mcp ewangzai/byerisk-mcp MCP server that integrates ByeRisk's content compliance detection into AI assistants, enabling text, image, and video compliance checks with risk details and rewrite suggestions. | |
| OceanBase Oracle MCP Server ewanjasper/oceanbasemcp Enables AI assistants to directly connect to OceanBase databases (Oracle mode) for querying, schema browsing, PL/SQL export, and execution plan analysis through MCP. | |
| SessionRelay ewanjasper/sessionrelay Session-level (not fragment) local memory for AI coding agents: passively captures Claude Code, Codex, ZCode and Qoder conversations into one SQLite store, with provenance-cited retrieval and a human-only right to be forgotten. | |
| agent-discussion-mcp ewanni/agent-discussion-mcp Enables reusable role-based agents, solo execution, and bounded multi-agent discussions with independent proposals, peer critiques, judge consensus, revision rounds, token budgeting, and SQLite audit logging. | |
| api_agent_mcp ewanni/api_agent_mcp Enables users to define and run reusable role-based agent profiles that complete tasks alone or in bounded multi-agent discussions with independent proposals, parallel critiques, an independent judge verdict, and optional revision rounds, p | |
| Octagon MCP Server ewaokada35940/octagon-mcp-server Enables users to ask natural-language questions and receive structured, source-backed answers across public filings, earnings transcripts, company financials, stock and crypto market data, and prediction market news and research. | |
| pfSense MCP Server ewasmit/pfsense-mcp-server Enables natural-language management of pfSense firewalls from Claude Desktop, Claude Code, or any MCP client, covering firewall rules, VPNs, NAT, DNS, DHCP, certificates, routing, and diagnostics through hundreds of wire-format-verified too | |
| flameox ewastewart/flameox Enables coding agents to capture and analyze bounded runtime evidence from explicit artifacts or commands, coordinating profilers, benchmark tools, trace processors, and local targets for hotspot investigation. | |
| Claude Telegram Supercharged ewasuzuki/claude-telegram-supercharged Enables users to run and interact with Claude Code from Telegram 24/7, with two-way voice notes, persistent memory, live tool-call visibility, scheduled reminders, calendar access, and automatic daemon recovery. | |
| mcp-ip2location eweley95/mcp-ip2location Enables AI assistants to perform IP geolocation, proxy detection, and domain WHOIS lookups using IP2Location.io and IP2WHOIS data. |
49,051–49,100 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.