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 |
|---|---|
| MarkItDown MCP Server courage-zen/markitdown-mcp Enables agents to convert Office files, PDFs, images, archives, and other documents into Markdown over a stateless Streamable HTTP endpoint, accepting server-side paths, inline base64 content, or S3/MinIO object keys. Ships with bearer-toke | |
| OpenMixing couralabs/openmixing Enables an agent to analyze a folder of audio tracks, build and edit DJ sets with EQ, filters, tempo, effects, and loops, plan transitions, and render mixes offline to FLAC, WAV, or MP3. | |
| Invoice-MCP courtimusprime/rayshio MCP server that gives AI agents read access to subscription/SaaS invoice history, ingested from Gmail and stored in Postgres and MongoDB, with tools for listing invoices, retrieving PDFs, and summarizing spend. | |
| srp-tariff courtkillion/utility-api Enables exact residential electricity rates and itemized bills for Salt River Project, computed from filed tariffs with citations, via tools for listing plans, getting rates, and calculating bills. | |
| ads-mcp-server courtneydaly/ads-mcp-server A read-only MCP server that lets Claude query warehouse marts for paid media spend, impressions, clicks, conversions and derived ratios across platforms, campaigns, audiences, formats, and time periods. It also surfaces month-to-date budget | |
| WordPress Meta Trac MCP Server courtneyr-dev/meta-trac Provides AI assistants with comprehensive access to WordPress Meta Trac data, enabling intelligent queries about WordPress.org infrastructure, plugin/theme directories, WordCamp events, and other WordPress.org services through ticket search | |
| MCP Server Starter coutinhotts/funi-mcp A basic structure to build and run local tools that support the Model Context Protocol (MCP) standard, compatible with AI tools like Cursor and Claude. | |
| ts-graph-mcp couzic/ts-graph-mcp A TypeScript code graph tool with MCP integration that enables AI agents to perform semantic search and graph traversal (call graphs, paths between symbols) across a codebase. | |
| byndr-dev covagashi/covaga.dev Enables LLM-driven data enrichment for EPLAN article databases, allowing proposals for missing translations and descriptions through a Model Context Protocol server. | |
| Coval MCP Server coval-ai/mcp-server Enables AI assistants to interact with Coval's evaluation platform for launching and monitoring evaluation runs, managing agents and test sets, and retrieving evaluation metrics. | |
| GoldRush MCP Server covalenthq/goldrush-mcp-server Exposes Covalent's GoldRush APIs to provide LLMs with comprehensive blockchain data, including token balances, transaction histories, and chain metadata. It supports multiple networks and wallet types, including Bitcoin HD and non-HD addres | |
| dayz-agentic-modding-mcp covalschi/dayz-agentic-modding-mcp MCP server that enables an agent to autonomously build, compile-check, test, and debug DayZ mods, integrating with the running game via a server bridge and providing structured verdicts, world manipulation, client control, and API knowledge | |
| coven-mcp covenai-dev/coven-mcp MCP server for website auditing and AI visibility measurement using the COVEN v2.0.1 methodology, offering tools to scan, score, and optimize sites for agent traffic. | |
| Coveo MCP Server coveo-labs/coveo-mcp-server Enables AI agents to query Coveo's unified index for search, passage retrieval, and generative question answering, supporting multiple transport modes for client compatibility. | |
| xsiam-mcp coveosec/xsiam-mcp Exposes the entire Palo Alto Cortex XSIAM REST API (129 operations across 26 categories) as MCP tools, plus composite tools like xql_query for AI agents to search and investigate security data. | |
| analytics-mcp coveragex/google-analytics-mcp MCP server that provides tools to interact with Google Analytics APIs, enabling account and property retrieval, report running, and custom dimension/metrics access. | |
| Colab MCP covertlabsaus/colab-mcp Enables AI coding assistants like Claude Code, Cursor, and Codex to share chat logs, terminal history, and session context with each other. Eliminates the need to re-explain context when switching between different AI coding tools. | |
| mcp-gerrit-code-review coveyjorjet/mcp-gerrit-code-review MCP Server providing AI agents with tooling for Gerrit code review workflows via stdio transport. | |
| caldera-mcp cowboy-samurai/caldera-mcp Connects MCP-compatible AI clients to a MITRE Caldera adversary emulation platform, enabling natural language construction of attack scenarios, agent inspection, and operation management. | |
| alabasta cowboyshibuya/alabasta-agent-bridge Connects coding agents (Claude Code, Codex, Cursor) to Alabasta tasks, enabling agents to read tasks, start work, and submit structured resolutions for human review. | |
| Image-Toolbox-MCP cowlsly/image-toolbox-mcp_by-cowlsly Enables AI assistants to access image conversion, editing, compression, metadata, and batch-processing workflows through a Model Context Protocol integration. | |
| @cowork/mcp-server cowork-human-agent-protocol/human-agent-cowork-mcp-server Adds trust, handoffs, and accountability to any AI agent via 14 MCP tools implementing the COWORK Protocol. | |
| TeleBotHost MCP Server coworklab/telebothost-mcp Enables AI clients to manage Telegram bots via the TeleBotHost Developer API, including bot lifecycle, storage, broadcasts, and community store operations. | |
| Cowpin Agent Memory MCP Server cowpin-ai/mcp-server Enables Claude, Cursor, Windsurf, and autonomous agents to save web pages and notes as persistent memories, then search them using full-text keyword matching and semantic vector recall. | |
| xClaude Plugin cox30523/xclaude-plugin Enables iOS development automation for Claude Code through modular workflow-specific MCP tools for building, testing, launching, and interacting with Xcode, Simulator, and IDB while minimizing token and context usage. | |
| Debug MCP coykto/debug_mcp A debugging gateway for distributed systems that provides 17 tools for interacting with AWS CloudWatch, Step Functions, LangSmith, and Jira. It enables efficient log analysis, workflow tracing, and ticket management while significantly redu | |
| severally coz-a/severally Enables coding agents to consult other coding-agent CLIs for independent opinions on proposals, receiving per-agent responses that can be verified and recorded without sharing conversation history. | |
| alldata-mcp-server cozadizzle/alldata-mcp-server Local MCP server for searching your ALLDATA repair subscription using your browser session, enabling AI agents to access labor times, procedures, TSBs, DTCs, and wiring diagrams. | |
| autozonepro-mcp-server cozadizzle/autozonepro-mcp-server Local MCP server for your AutoZone Pro commercial account. HTTP-first catalog/session client that returns commercial cost and list price for shop quoting. | |
| partsgeek-mcp-server cozadizzle/partsgeek-mcp-server Enables searching PartsGeek for parts, retrieving product details, and obtaining cart estimates for price comparison, without placing orders or requiring a PartsGeek account. | |
| coze-mcp-server coze-dev/coze-mcp-server A Model Context Protocol server that provides Coze resources and tools for managing workspaces, bots, and conversations. | |
| Cisco NX-OS CLI MCP Server cpaggen/cisco_nxos-mcp_server Enables interaction with Cisco NX-OS devices through CLI commands via NX-API. Supports single and multi-device command execution with text or JSON output, authentication from .env, and comprehensive error handling. | |
| meridian59-llm-bot cpappas213/meridian59-llm-bot Provides MCP supervision and knowledge tools for controlling an LLM-driven Meridian 59 character, enabling durable goal management, persona configuration, and audited gameplay. | |
| PRD Creator MCP Server cpatel1293/prd-mcp-server Enables AI systems to generate detailed, well-structured Product Requirements Documents (PRDs) using various AI providers or templates through the Model Context Protocol. | |
| moa cpcc/moa Enables multi-model reasoning via Mixture-of-Agents orchestration, allowing complex task processing with diverse perspectives and reduced hallucinations. | |
| Augments MCP Server cpereira1627/augments-mcp-server Enables Claude Code and other MCP clients to pull real-time framework docs — signatures, prose, and code examples — for any npm package, with intent-aware formatting. It also provides version diffs and migration guides, error diagnosis, pac | |
| sticky-notes cpeters234/sticky-notes-mcp Gives Claude full read/write access to Windows Sticky Notes, allowing creation, searching, editing, and deletion of notes, plus control over note properties. | |
| MCP Server Streamable cpetra/mcpservertest A demonstration MCP server that runs over HTTP with streamable transport, providing a simple greeting tool for testing MCP client-server communication. Built with FastMCP framework for educational purposes in learning MCP server development | |
| destiny-telling cph0512/destiny-telling Enables AI agents and local programs to perform North-school Zi Wei, BaZi, palace overlay, and bidirectional cross calculations via a local stdio MCP, returning structured numerical and structural data. | |
| MCP REST API Tester cphoenix921/mcp-rest-api Enables users to test and interact with REST API endpoints from MCP-compatible clients, supporting multiple HTTP methods, authentication, custom headers, SSL verification settings, and configurable response-size limits. | |
| gamma-app-mcp cphoskins/gamma-app-mcp Enables generating presentations, documents, webpages, and social posts via Gamma's API with full parameter surface including templates, folders, headers/footers, and email sharing. | |
| gptzero-mcp cphoskins/gptzero-mcp Enables AI content detection with sentence-level and paragraph-level AI probability scoring to identify and fix AI-generated text. | |
| meetalfred-mcp cphoskins/meetalfred-mcp MCP server for MeetAlfred LinkedIn automation, enabling campaign monitoring, lead management, reply tracking, messaging, tag management, campaign CRUD, and social post scheduling. | |
| nimble-crm-mcp cphoskins/nimble-crm-mcp MCP server for the Nimble CRM API, enabling management of contacts, deals, notes, tasks, and tags through natural language. | |
| notion-full-mcp cphoskins/notion-full-mcp Full-featured Notion MCP server enabling deep page reading, block editing, snapshot/restore, file uploads, table manipulation, page restore, and destructive page copying. | |
| BattForge Agent cpidkuub/battforge-agent Enables natural-language battery-cell requirements to be parsed and routed to simulation backends, returning design forms and performance metrics while supporting calibration, thermal-runaway, COMSOL, and UI draft workflows. | |
| Amadeus cpietsch/amadeus Enables coding agents to work on the MUSICA supercomputer without hand-written ssh and sbatch by providing tools to sign in, run light commands, draft, check, submit, wait for, and read jobs, move files, and monitor budgets, while enforcing | |
| WebAI-MCP cpjet64/webai-mcp WebAI-MCP is a comprehensive browser automation and monitoring solution that enables AI applications to capture and analyze browser data through a Chrome extension, providing 20+ tools for screenshots, console logs, network monitoring, stor | |
| comwel-mcp cplalks-create/comwel-mcp Enables Claude to search Korean workers’ compensation disease rulings, review decisions, and industrial accident court precedents, open their full texts, and verify quotations against the original source. Supports filtered searches and char | |
| roblox_studio cpleasance/roblox-studio-mcp-bridge Enables AI IDEs and agents to connect to and control Roblox Studio through the Model Context Protocol, bridging to Studio's native StudioMCP daemon to interact with the active place and DataModel. |
40,551–40,600 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.