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 |
|---|---|
| revenuebase-mcp-server avivshafir/revenuebase-mcp-server revenuebase-mcp-server | |
| trykittai-mcp-server avivshafir/trykittai-mcp-server trykittai-mcp-server | |
| ZeroBounce MCP Server avivshafir/zerobounce-mcp-server A Model Context Protocol server that allows interaction with the ZeroBounce email validation service, enabling users to validate individual emails, check account credits, and perform bulk validations. | |
| narration-mcp avivshaked/narration-mcp Enables AI agents to generate narration in a single fixed, pre-approved voice, returning audio with per-line timing, hashes, and automatic quality checks on content, speaker identity, and pace, all locally and reproducibly. | |
| MCP Agent Orchestration System aviz85/mcp-agents-orchestra A state-based agent orchestration system that allows transitions between different states (IDLE, PLANNING, RESEARCHING, EXECUTING, REVIEWING, ERROR) while maintaining conversation context and providing state-specific prompts. | |
| GitHub Plus MCP Server aviz92/python-github-plus-mcp Enables any MCP client to read GitHub repositories, branches, tags, pull requests, files and Actions workflow runs, and optionally create branches and pull requests, comment, assign, approve, trigger workflows, merge and delete. Read-only b | |
| Hukuk MCP avkaanaydin/hukuk-mcp MCP server for searching Turkish legal texts using ChromaDB, with PDF indexing and Claude Desktop support. | |
| Etsy MCP Server avlihachev/etsy-mcp-server Exposes a subset of the Etsy API through the Model Context Protocol, enabling MCP clients to retrieve shop data and manage listings. | |
| MCP OmniFocus avlihachev/mcp-omnifocus Enables task management in OmniFocus, including reading, creating, updating, and completing tasks, with automatic detection of Pro or Standard version. | |
| crowdcheck avnath13/crowdcheck MCP server that evaluates claims by mapping agreement and certainty from online sources, returning a structured contestation map with consensus, confidence, and weighted positions for agent decision-making. | |
| HomeTrace avneet-j/hometrace Enables households to record and query appliance maintenance, warranties, repair history, and follow-up reminders through natural-language MCP tools, with date calculations and persistent local storage handled by the server. | |
| weather-mcp-server avnibhardwaj1/weather-mcp-server Weather MCP Server | |
| QuantRisk avnijainnn/quantrisk Enables agents to generate alpha signals, retrieve market snapshots, compute portfolio risk, validate and submit paper orders, and trigger a kill switch, all under deterministic pre-trade risk controls and audit logging. | |
| Code Mender Triage MCP Server avnit/codemender-mcp Enables MCP clients to query and triage security findings published to BigQuery and correlate them with execution, sandbox, and diagnostic traces in Cloud Logging. Exposes tools, resources, and prompts for filtering issues by severity, stat | |
| legal-rag-toolkit avocatt/legal-rag-toolkit Enables semantic search over Turkish legal contracts and emails via an MCP server integrated with Claude Desktop and Claude Code, providing tools for document ingestion, hybrid vector search, and full-text retrieval. | |
| legal-mcp-croatia avoccadotech/legal-mcp-croatia Enables AI assistants to search and retrieve Croatian public court notices from the e-Oglasna ploča sudova, including downloading attached PDFs and listing courts, with a read-only, privacy-preserving design. | |
| Lifos avoccadotech/legal-mcp-sweden Enables monitoring Migrationsverket's public legal position feed to detect when cited RS/RK documents have been superseded, so firms can identify which knowledge base entries are out of date. | |
| notch-mcp avoguru/notch-mcp Enables agents to display status readouts in the Mac's notch area via MCP, with multiple styles and progress indicators. | |
| snes-lab avoliva/snes-lab Enables agents and scripts to inspect, disassemble, emulate, debug, patch, and mod SNES ROMs, including Super Mario World-specific level and route tooling, through callable tools backed by a Rust core. | |
| Prosp MCP Server avolveai/prosp-mcp MCP server for Prosp.ai LinkedIn outreach automation. Manage leads, campaigns, messaging, and analytics programmatically. | |
| SSH MCP Server avranju/ssh-mcp An MCP server that gives AI agents SSH capabilities to execute commands, transfer files, and inspect remote systems through a preconfigured host list. | |
| MCP Server Template avrecum/yf-mcp A minimal FastMCP server template for Render deployment with streamable HTTP transport. Provides a starting point for building custom MCP servers with easy one-click deployment capabilities. | |
| screenshot-vision-mcp avs845/screenshot-vision-mcp An MCP server that captures screenshots of URLs or local app windows and analyzes them with a local Ollama vision model, enabling Claude to visually inspect web pages and desktop applications without sending image data externally. | |
| jira-ai-auditor avtandil-abu/jira-ai-auditor Enables running Jira project health audits directly in Claude Desktop, providing real-time health scores, risk detection, and team workload analysis through natural language. | |
| plane-mcp-server avtechno-era/plane-mcp-server Enables an LLM to act as a project manager across self-hosted Plane workspaces and projects, providing tools for work items, cycles, modules, states, labels, comments, members, and intake triage via Plane's REST API. | |
| local-llm avtplay/mcp-servers-local-llm Enables delegating mechanical or high-volume subtasks to a local LLM through an MCP tool, letting the assistant query the local model without using its own output tokens for content. | |
| Aṣṭādhyāyī MCP avulaankith/astadhyayimcp Enables read-only, deterministic MCP access to scholarly Sanskrit data such as sūtras, dhātus, śabdas, and stored rūpāṇi. Supports offline search, retrieval, form lookup, pagination, and provenance-aware evidence for downstream agents. | |
| Banca Dati di Merito MCP Server avvocati-e-mac/mcp-bdm-civile Enables querying and retrieving Italian civil court rulings, decrees, and orders from the Ministry of Justice's database via natural language, using CIE authentication. | |
| norm-mcp avvocati-e-mac/normattiva-mcp Enables reading, verifying, and citing Italian legal norms from Normattiva.it through MCP tools for article lookup, Markdown citation generation, source search, and URN resolution. | |
| 80mcp avwohl/80mcp Enables AI agents to run CP/M, MP/M, and DOS packages on Z80/x86 emulators, inspect byte-exact results and files, and debug the emulators themselves over the Model Context Protocol. | |
| XiaoZhi MCP Aggregate avxxoo/xiaozhi-mcp A powerful interface for extending AI capabilities through remote control, calculations, email operations, knowledge search, and more. | |
| Figxel avyour/figxel-mcp A local MCP server paired with a Figma desktop plugin that enables AI agents to read, build, edit, and animate real, editable designs in the Figma file you have open. It supports layers, components and variants, styles, variables and modes, | |
| CaitGPT aw1kswinton/ffvii-rebirth-cait-gpt Enables MCP-capable agents to play FINAL FANTASY VII REBIRTH locally through validated telemetry, bounded controller input, navigation, combat, menus, save handling, and Queen's Blood tools, with simulation mode available. | |
| tool-convert awacloud/tool-convert Enables converting documents between formats over MCP: any supported input (docx, odt, xlsx, ods, pptx, odp, pdf) to structured Markdown, Markdown to docx, odt or pdf, direct cross-format pairs, and Markdown to sanitised HTML. Fidelity loss | |
| report-intelligence awad19977/report-intelligence-platform AI-native tooling and MCP integrations for understanding enterprise reports | |
| bridge8 awaik/bridge8 Enables AI agents to query Russian API, product help, and training documentation by resolving catalog services, searching ranked document fragments, and reading full or paginated documents via remote MCP tools. | |
| devops-deploy-guard-mcp-server awais2o/devops-deploy-guard-mcp-server Production-ready, zero-knowledge AI DevOps deployment, infrastructure provisioning, self-healing execution, and persistent documentation engine for VPS servers. | |
| llm-sidecar awaistechnologist/llm-sidecar MCP server for grounded, cited AI: answers questions from live web sources, verifies claims, fact-checks documents, searches and reads URLs, summarises, classifies, and extracts fields, with usage tracking and status. | |
| facebook-mcp-server awakenorigins/facebook-mcp-server Enables AI agents to manage Facebook Pages through the Graph API, including creating posts, moderating comments, fetching page and post insights, and filtering negative feedback. | |
| lunar-mcp awakenorigins/lunar-mcp Enables AI agents to convert between solar and lunar dates, calculate BaZi charts, generate auspicious-day guidance, track the 24 solar terms, and analyze Five Elements composition through MCP tools. | |
| pg-mcp awaketai/postgres-mcp Enables natural language querying of PostgreSQL databases through the Model Context Protocol. It translates user questions into validated SQL, executes read-only queries safely, and returns results to MCP-compatible clients like Claude Desk | |
| Subnet Calculator MCP Server awakm618/subnet_calculator_mcp Enables subnet mask calculations and network planning through MCP framework. Provides detailed subnet information including network addresses, IP ranges, and broadcast addresses, plus LAN planning advice for different network scales. | |
| mcpbluesky awaku7/mcpbluesky An MCP server that enables users to interact with the Bluesky social network through comprehensive read and write API tools, including session management and timeline navigation. It also features a Jetstream-powered local SQLite database fo | |
| Washington State Legislature MCP Server awalcutt/wa-leg-mcp Enables AI assistants to access Washington State Legislature data for bill tracking, committee meetings, legislator lookup, and legislative document retrieval via conversational interfaces. | |
| Perforce P4 MCP Server awalczak83/p4mcp-server Enables AI assistants to interact with Perforce P4 version control through safe, structured read/write tools for changelists, files, shelves, workspaces, jobs, reviews, streams, and server metadata, plus P4 DAM assets via its REST API. Supp | |
| mysql-explorer awand795/mcp-server-mysql Enables Claude to interact with a MySQL database by automatically discovering its schema and retrieving full table data for analysis. | |
| AwardTape MCP Server awardtape/awardtape-mcp Enables searching and analyzing US defense contract obligations, expiring recompetes, power-grid interconnection queues, and supply-chain compliance screens, plus exporting custom relational datasets. | |
| AWARSE awarselabs/awarse-mcp Self-healing browser automation MCP server integrating Playwright with LLM-assisted locator repair. | |
| Train in Silence awatanabe39/train-in-silence Enables users to describe an LLM fine-tuning job once and receive the cheapest, fastest, and most balanced GPU options across multiple cloud providers by calculating required VRAM and FLOPs. It aggregates live market pricing and returns ran | |
| Cross-Platform Filesystem MCP Server awaybreaktoday/mcp-filesystem-cross-platform Enables comprehensive filesystem operations across Linux, macOS, and Windows with platform-aware command execution, secure path restrictions, and intelligent adaptations for file search, directory management, and shell commands specific to |
32,001–32,050 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.