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 |
|---|---|
| tradingview-chart-mcp carlwagner260/tradingview-chart-mcp Enables users to fetch chart images for specified tickers and intervals, using browser pooling for concurrent performance. It also exposes performance statistics and supports natural-language prompts for common timeframe requests. | |
| borsdata-mcp-server carlwestman/borsdata-mcp-server MCP server that exposes the Borsdata financial data API as tools and resources for Claude, covering Nordic and Global stocks, financial reports, KPIs, stock prices, holdings, and calendars. | |
| pagerduty-mcp-community carlyou/pagerduty-mcp-community A community-maintained MCP server for interacting with PagerDuty accounts, enabling management of incidents, services, schedules, and event orchestrations through MCP-enabled clients. | |
| MCP Contract Auditor carlys17/mcp-contract-auditor Fetches verified EVM smart contract source code, scans for vulnerabilities, analyzes token holder distribution, and generates audit reports. | |
| company-mcp-server carmelocompiano/custom-mcp Enables AI assistants in Cursor and other MCP hosts to connect to a company REST API, handling token-based authentication, read-only lookups, and guarded job/package creation with optional shipping labels. | |
| GitLab MCP Server carmeloricarte/gitlab-mcp-server Enables AI assistants to interact with GitLab for managing projects, branches, issues, and merge requests. It provides tools for searching code and performing file operations like reading and writing directly within repositories. | |
| Jira MCP Server carmeloricarte/jira-mcp-server Enables AI assistants to interact with Jira Cloud issues, supporting create, read, update, delete, search, and transition operations via natural language. | |
| fancy-api carmelosantana/fancy-api MCP server that enables AI agents to read and write records in a live REST API generated from pasted data, with tools for listing, querying, inserting, updating, and deleting records. | |
| slop-guard carmen0482/slop-guard Enables agents to analyze inline text or files and return a 0–100 score for formulaic AI writing patterns, violation details, bands, counts, and improvement advice through MCP tools. | |
| jevcore-mcp carmen394/jevcore Exposes three stdio tools that return typed, calibrated judgments — yes/no, choice, and score — instead of prose, so MCP hosts can query a decision layer offline by default with any live egress reported on stderr. | |
| Taskade MCP Server carmen394/mcp Enables AI clients such as Claude, Cursor, VS Code, and Windsurf to list, create, update, and complete workspaces, projects, tasks, and AI agents through OAuth- or token-authenticated tools. It also ships an OpenAPI-to-MCP generator for bui | |
| knowledge-base-server carmen60488/knowledge-base-server Enables AI agents to capture, classify, promote, synthesize, and retrieve persistent knowledge from sources like Obsidian vaults, code, transcripts, and session logs, serving it through MCP tools and a REST API. Provides tiered, token-optim | |
| Juror Cloud MCP carmen8468/juror Inspects workspace-scoped review findings and hosted runs, and can prepare and, after explicit user confirmation, start or rerun an existing hosted review. It avoids exposing raw diffs, full reports, artifacts, screenshots, credentials, or | |
| Roundtable AI MCP Server carmen84914/roundtable Enables a primary AI assistant to delegate tasks in parallel to multiple specialized AI coding assistants, share project context, and synthesize their responses into a single result. | |
| Meta Ads MCP Server carmenahmed44493/meta-mcp Enables multi-tenant setup and management of Meta advertising accounts, campaigns, ad sets, creatives, audiences, reporting, and batch workflows through the Meta Marketing API, with OAuth and JWT-protected MCP access. | |
| Claude Telegram Supercharged carmenbarbosa64/claude-telegram-supercharged Enables running Claude Code around the clock through Telegram, with two-way voice notes, persistent memory and history across restarts, scheduled messages, calendar access, and a live view of every tool call while Claude works. It ships as | |
| Vectorize MCP Server carmenfisher0455/vectorize-mcp-server Enables advanced vector retrieval, document text extraction and chunking into Markdown, and private deep research through a configured pipeline. | |
| AKIMCP carmenlee4438/aki-mcp-sv Enables web-based AI assistants and local IDEs to securely operate a local machine through an OAuth-gated suite of 38 tools covering files, shell, search, Git, databases, browser automation, DevTools, background tasks, clipboard, localhost | |
| U.S. Census Bureau Data API MCP carmensahin/us-census-bureau-data-api-mcp Connects AI assistants with official Census Bureau data sources, letting them list datasets, resolve place names to FIPS codes, and pull aggregate statistics for states, counties, cities, and other geographies. Queries are served from the C | |
| mcp-ai-detection carminelau/mcp-ai-detection Enables multi-tier AI-detection screening on academic papers by extracting text from .tex and .docx files, splitting into standard sections, and running a pipeline of statistical and LLM-based analysis. | |
| Customer Service Data Analyst MCP Server carmithaas/customer-service-agent-carmit-haas Exposes five tools for querying and analyzing a customer-support dataset, including listing categories/intents, filtering, counting, and summarizing records. | |
| gatebound-support carnufex/gatebound-support Enables an ElevenLabs support agent to call support tools over MCP, including Discord ticket flows, post-call webhook handling, and knowledge-base syncing. | |
| Cinema4D MCP Server carol804/cinema4d-mcp Enables prompt-assisted 3D modeling, scene creation, and manipulation in Cinema 4D through Claude, with tools for objects, cameras, lights, materials, MoGraph, dynamics, and rendering. | |
| substack-mcp carol85009/python-substack Enables writing Substack posts in Markdown and safely creating, inspecting, scheduling, updating, exporting, publishing, and deleting drafts, with unsupported editor widgets preserved by default. It relies on the same environment variables | |
| MCP REST API Tester carolbailey053/mcp-rest-api Enables testing and interaction with REST API endpoints from MCP clients such as Claude and Cline, supporting multiple HTTP methods, authentication, custom headers, SSL verification control, and response-size limiting. | |
| Kingdee MCP Server carold37/kingdeemcp Enables Claude, Cursor, Windsurf, Cline, and other MCP-compatible AI assistants to query and operate Kingdee Cloud Star ERP through natural language, covering procurement, sales, inventory, finance, production, costs, assets, auditing, work | |
| github-talent-mcp carolinacherry/github-talent-mcp MCP server that searches, scores, and ranks GitHub developers for technical recruiting. | |
| MCP Basics caroline-davis/mcp-basics A centralized Model Context Protocol server that provides common development tools (like formatting and translation) across all your Cline projects without needing to install them individually. | |
| CVE-Search MCP Server carolinebianchi85018/cve-search_mcp Enables querying a vulnerability database API to browse vendors and products, retrieve CVEs by ID, fetch the latest 30 CVEs with CAPEC/CWE/CPE expansions, and inspect database update status. | |
| arxiv-latex-mcp carolined4973/arxiv-latex-mcp Enables MCP clients such as Claude Desktop, Claude Code, and Cursor to fetch and process arXiv papers' LaTeX sources, allowing accurate interpretation of equations and mathematical expressions. Provides tools to retrieve full flattened LaTe | |
| locklens carolineegorov441/locklens Enables auditing npm, Yarn, and pnpm lockfiles from local project directories or remote Git repositories for dependency vulnerabilities, with configurable severity thresholds, dev-dependency skipping, and text or JSON reporting. | |
| Mental Health MCP carolinefebraga/mental_health_mcp This MCP server provides emotional support through a rule-based system that analyzes user messages for emotional patterns and returns structured responses with self-care suggestions. It acts as a conversational assistant with ethical limita | |
| wanderlog-mcp carolinehill01/wanderlog-mcp Enables Claude or any MCP-compatible agent to view, build, and edit Wanderlog trip itineraries through conversation — adding places, notes, hotels, transit, car rentals, checklists, budgets, and custom sections. | |
| EasyMCP carolinelefebvre08/easy-mcp Enables TypeScript developers to build Model Context Protocol servers by defining tools, prompts, resources, resource templates, and roots with minimal boilerplate, using either an Express-like API or experimental decorators. | |
| jmcomic-ai carolines72/jmcomic-ai Enables AI agents to search, browse, download, post-process, and manage comic albums, comments, favorites, rankings, and account sessions through standardized MCP tools and resources. | |
| Food Core MCP caroliny1031/food-core Independent MCP server for tracking food inventory, estimating best-before dates, managing consumption, and returning expiry reminders to MCP clients. | |
| midea-mcp caroliny1031/midea-mcp Local MCP server for controlling Midea air conditioners via LAN or cloud, providing tools for device management and state control. | |
| Android Source Explorer MCP Server carolreddy97299/android-source-explorer-mcp Provides on-demand, precise access to actual AOSP and AndroidX source code, enabling AI tools to inspect framework internals, search classes and methods, view hierarchies, and resolve cross-file definitions and references. | |
| ClauseWise carolyn-beep/clausewise Enables employees and independent contractors to submit contracts such as NDAs, offer letters, severance and invention-assignment agreements and get plain-language explanations of the clauses that deserve attention. Each flagged clause is c | |
| ReActMCP Web Search carolyn12767/reactmcp Enables AI assistants to run basic and advanced web searches through the Exa API, with filtering by domains, required text, and dates, and returns real-time Markdown-formatted results including titles, URLs, publication dates, and content s | |
| Zotero MCP carolyn72604/zotero-mcp Enables AI assistants to search a Zotero library, retrieve complete item metadata, and read the full text of attached documents such as PDFs through MCP tools. It works against either the local Zotero API or the Zotero Web API. | |
| Webflow MCP Server carolynhassan87032/mcp-server Enables AI agents to interact with the Webflow Data API, so users can manage sites, CMS content, and Designer components through natural language. Runs remotely over OAuth or locally with an API token, bridging the Webflow Designer with MCP | |
| Project OS for Codex carolynlarsson/project-os-for-codex Enables Codex and other MCP clients to read kickoff cards, acceptance criteria, Git evidence, and next steps, then append validated, audited progress events for resumable project handoffs. | |
| tradingview-chart-mcp carolynn597/tradingview-chart-mcp Enables users to fetch TradingView chart images for specified tickers and intervals, using browser pooling for faster concurrent performance and session-based authentication. | |
| Image Context Runtime for Codex carolyno4878/codex-image-context-runtime Enables context-bounded image generation and inspection through durable local jobs, returning only bounded text handoffs, hashes, relative references, and Job IDs while keeping provider media bytes off the public MCP boundary. | |
| AutoCAD MCP Pro carolynshimizu/autocad-mcp Enables AI agents to create, inspect, and validate production-grade CAD drawings through one typed contract, driving either a live AutoCAD session over COM or a headless DXF engine on any platform. Covers ISO-compliant mechanical, architect | |
| BigQuery Validator caron14/mcp-bigquery Enables validation and dry-run analysis of BigQuery SQL queries without execution. Provides cost estimates, schema previews, and syntax validation for BigQuery queries. | |
| mcp-bigquery-dryrun caron14/mcp-bigquery-dryrun Validates BigQuery SQL syntax and performs dry-run analysis without executing queries, providing cost estimates, referenced tables, and schema previews. | |
| mcp-duckvault caron14/mcp-duckvault Provides a RAG system for your Obsidian Vault using DuckDB and vector search, enabling semantic search and note retrieval through AI agents. | |
| codebase-wiki carreira-cloud/codebase-wiki Enables AI agents to index, search, and retrieve architectural documentation and store self-learning notes from codebases. |
36,951–37,000 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.