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 |
|---|---|
| lauther-mcp csanadymiklos/lauther-js Lets an AI agent ask its owner first, on their phone, before doing something irreversible: ask_approval blocks until a person answers and distinguishes DENIED from NO ANSWER, so a timeout is never read as consent. send_notification covers o | |
| JobScout MCP csarushan1729/jobscout-mcp An MCP server that enables Claude to search live job postings, rank them against a user's skills profile, and track application statuses locally. | |
| commvault-release-comparison-mcp csawantgit/commvault-release-comparison-mcp MCP server for comparing Commvault release versions, retrieving categorized changes, and generating release summaries to support upgrade planning. | |
| MCP Server Demo csc-0812/mcpserverdemo A WebSocket-based Model Control Protocol (MCP) server that processes model requests and provides responses. Supports chat and text completion actions with a standardized JSON protocol for AI model communication. | |
| mcp-canada csc392-csc492-building-ai-ml-systems/mcp-canada-server Gives AI agents structured, bilingual access to Canadian federal, provincial, and municipal open-data APIs, covering exchange rates, statistics, weather, recalls, drugs, immigration, parliamentary data, geospatial datasets, and local SQLite | |
| mpi-duplicate-detection cschare97/mpi-duplicate-detection Enables detection of duplicate patient records for a Master Patient Index by scoring record pairs and providing verdicts and reasons, intended for synthetic data only. | |
| lm-mcp-server cscokus/lm-mcp-server Enables Claude to read CRM data and propose actions (bid changes, budget shifts, etc.) via a thin authenticated router, without executing any changes. | |
| Gaia Health MCP Server cscrespo/gaia-health-mcp Exposes Supabase functionality for Gaia Health to n8n workflows, enabling appointment scheduling and management operations through MCP tools. | |
| Hermes n8n MCP csenguttuvan/hermes-n8n-mcp-plus A local stdio MCP bridge for managing n8n from Hermes Agent, exposing tools to check health, list/inspect workflows, view executions, and activate/deactivate workflows securely without exposing n8n over the network. | |
| Okta MCP Server csenguttuvan/okta-mcp-server Enables AI assistants to manage Okta users, groups, applications, policies, group rules, and system logs through the Okta API. Includes dry-run safety guardrails, confirmation flags, and a read-only inspection mode. | |
| Local MCP Test Server cserra16/local-mcp-test-server A local testing MCP server that provides weather information for L'Hospitalet de Llobregat using the Open-Meteo API, accessible from mobile devices via SSE transport on local networks. | |
| io.github.csgear/bitbucket-agent csgear/bitbucket-agent This MCP server enables AI agents to create Pull Requests in a self-hosted Bitbucket Server instance. | |
| boj-mcp csh1668/boj-mcp Unofficial MCP server for searching and recommending Baekjoon (BOJ) problems using the solved.ac API. | |
| durable-mcp cshah26/chatbot-mcp MCP server for Durable energy trading analytics that connects Claude Desktop to Snowflake data, enabling natural-language queries about spreads, constraints, generators, and prices. | |
| easy-jupyter-editor-mcp cshara1/easy-jupyter-editor-mcp Enables AI agents to safely and structurally edit Jupyter Notebook (.ipynb) files by providing tools to read, edit, add, and delete cells without corrupting the JSON structure. | |
| agentpeers MCP cshenx/agentpeers Enables Codex and Claude Code sessions on the same Mac to discover each other and exchange messages, questions, findings, and coordination through their native transports, with external storage and read receipts. | |
| jds6600-mcp csibug/jds6600-mcp MCP server for the JDS6600 signal generator, enabling vintage tape recorder calibration via auto-detection and advanced waveform controls. | |
| sigelo csigelo/sigelo Gives an AI agent a portable identity it can prove anywhere: create a DID, sign platform challenges, collect signed attestations, and hand over a bundle that anyone verifies offline. Runs locally, no network, no account. | |
| Intervals.icu MCP Server csikosaron98/intervals-mcp-server Enables Claude and ChatGPT to retrieve and manage activities, intervals, events, wellness data, power curves, and custom items through the Intervals.icu API. | |
| elastic-mcp csimi/elastic-mcp A Model Context Protocol server for Elasticsearch, enabling search, index inspection, and cluster information tools with optional write tools. | |
| pgs-mcp csjohnson23/pgs-mcp Enables analysis of pgsc_calc polygenic score matching outputs, flagging warnings and silent errors while surfacing effect-weight coverage, lost variants, strand issues, missing data, and actionable QC reports. | |
| TPLCP Reference MCP cskerritt/tplcp-reference-mcp Turns the 2026 CLCP orientation corpus into a searchable, citation-preserving reference source for TPLCP report work. | |
| python-executor-mcp cskevint/python-executor-mcp Enables coding agents to execute Python code, run script files, and install pip packages locally via MCP. | |
| TaskTrek MCP Server cskoushik9/tasktrekmcp A Model Context Protocol server for TaskTrek that enables AI assistants to manage tasks and projects programmatically via JSON file storage. | |
| Calendar MCP Server cskwork/gongrzhe_calendar-mcp-server A Model Context Protocol (MCP) server for Google Calendar integration in Claude Desktop, enabling AI assistants to manage Google Calendar events through natural language interactions. | |
| investor-lens-mcp cskwork/investor-lens-mcp Provides educational US market analysis by combining exchange rates, stock snapshots, and five famous investor perspectives (Buffett, Graham, Lynch, Dalio, Wood) to generate watchlist ideas, reasoning, risks, and follow-up checks. | |
| Knowledge Retrieval Server cskwork/keyword-rag-mcp A BM25-based MCP server that enables document search and retrieval across structured domains of knowledge content, allowing Claude to search and reference documentation when answering questions. | |
| LocalWorkspace csl19980820/chatgpt-local-workspace Enables ChatGPT web conversations to directly operate a Windows machine through OpenAI Tunnel, including file read/write, precise editing, command execution, and Git review, with a live dashboard for replaying each tool call. | |
| Abstract MCP cslou/abstract-mcp A smart proxy server that prevents context window bloat by caching large tool responses to local files and returning compact resource links. It supports format conversion and data uploads, allowing LLMs to handle massive datasets without co | |
| OpenKer Modeler MCP Server cslv1/openker-modeler Enables AI agents to traverse SysML v2 model graphs, query requirements, and perform impact analysis for model-based systems engineering. It allows agents to interact with plain-text models to automate documentation and refine system archit | |
| MCP Chat CLI cslylla/mcp_chat_cli A command-line chat interface that connects to an MCP server for reading and editing documents. It provides tools for document manipulation, resource access, and prompts for formatting and summarization. | |
| Google Flow MCP csmc387-cloud/google-flow-mcp Enables AI assistants to automate a local background Chromium browser for interactive web tasks, including prompt generation on Google Flow (Veo & Imagen), DOM inspection, clicks, screenshots, and JavaScript evaluation. | |
| CLAWD Wallet csmoove530/unified-clawd-wallet-mcp A unified MCP server providing x402 payments, TAP identity verification, referral onboarding, and domain registration for Claude Code and other MCP clients. | |
| SevenRooms MCP Server csnkarthik/seven-rooms-mcp-v2 Enables restaurant reservation management through SevenRooms API, allowing users to create reservations and query available time slots with guest details and party size information. | |
| Feishu MCP Server cso1z/feishu-mcp Provides access to Feishu (Lark) documents for AI-driven coding tools like Cursor, Windsurf, and Cline based on Model Context Protocol implementation. | |
| ai-economy-infrastructure csoai-org/ai-economy-infrastructure An MCP server for AI economy infrastructure with built-in EU AI Act compliance, supporting risk management, transparency, and bias detection. | |
| biometrics-ai csoai-org/biometrics-ai Enables interaction with biometrics AI features, including risk management, transparency, bias detection, and compliance tracking, all compliant with the EU AI Act. | |
| blizzard-wow-mcp csoai-org/blizzard-wow-mcp Auction house analytics, market intelligence, crafting optimization, inventory valuation, farming routes, guild analytics, and token tracking — all through the Model Context Protocol. | |
| Brave Search MCP Server csoai-org/brave-search Enables AI assistants to perform web searches using Brave Search with EU AI Act compliance and enterprise features. | |
| COBOL Bridge MCP Server csoai-org/cobol-bridge-substrate Connects legacy COBOL mainframe systems to modern AI governance via MCP, with tools for parsing copybooks, assessing CICS, scanning JCL, mapping VSAM, and translating EBCDIC. | |
| Credential Manager MCP csoai-org/credential-manager-mcp Credential Manager - MCP server providing AI-powered tools and automation by MEOK AI Labs | |
| meok-agents-md-lint-mcp csoai-org/csoai-agents-md-lint-mcp Validates AGENTS.md files against the cross-vendor coding-agent spec, detecting security smells and consistency issues. | |
| meok-ap2-mandate-mcp csoai-org/csoai-ap2-mandate-mcp Enables issuing, verifying, and consuming signed Google AP2 v0.2.0 spend mandates over MCP, with a PSD2 SCA crosswalk. | |
| Meok Cra Art14 Reporter MCP csoai-org/csoai-cra-art14-reporter-mcp Enables reporting of actively exploited vulnerabilities in compliance with EU CRA Article 14, generating ENISA and CSIRT payloads. | |
| MEOK DORA Tlpt Planner MCP csoai-org/csoai-dora-tlpt-planner-mcp MEOK DORA Tlpt Planner - MCP server providing AI-powered tools and automation by MEOK AI Labs | |
| meok-eu-aia-art-9-rms-mcp csoai-org/csoai-eu-aia-art-9-rms-mcp Generates EU AI Act Article 9 Risk Management Systems with a 4-step iteration process, covering 12 risk categories and Annex IV attestation. | |
| meok-eu-aigc-icon-mcp csoai-org/csoai-eu-aigc-icon-mcp Provides tools to emit EU AI Act Article 50 compliance icons and metadata for AI-generated content. | |
| MEOK Fria Generator MCP csoai-org/csoai-fria-generator-mcp MEOK Fria Generator - MCP server providing AI-powered tools and automation by MEOK AI Labs | |
| MEOK Governance Engine MCP csoai-org/csoai-governance-engine-mcp MEOK Governance Engine - MCP server providing AI-powered tools and automation by MEOK AI Labs | |
| meok-mcp-cardgen-mcp csoai-org/csoai-mcp-cardgen-mcp Generates signed .well-known MCP server cards (SEP-1649/1960/2127) to enable MCP server discovery and compliance. |
40,951–41,000 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.