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 |
|---|---|
| workfront-fusion-mcp chaunceyplum/workfront-fusion-mcp Enables AI assistants to interact with Adobe Workfront and Workfront Fusion through scoped MCP tools, covering project management, user/resource administration, document handling, custom metadata, search, comments, planning, and Fusion scen | |
| mcp-shodan chavez18156/mcp-shodan Enables AI agents to query the Shodan API and Shodan CVEDB for internet-connected device reconnaissance, including open ports and banners, TLS certificates, DNS records, subdomains, and CVE/CPE vulnerability intelligence with CVSS, EPSS, an | |
| CVE-Search MCP Server chavez36040/cve-search_mcp Enables querying the CVE-Search API to retrieve vendors, products, product-specific vulnerabilities, specific CVE IDs, recently updated CVEs with CAPEC/CWE/CPE expansions, and database update information. It supports natural-language access | |
| vivado-mcp chavez58534/vivado-mcp Enables AI agents such as Claude Code, Cursor, and Codex to safely drive a locally installed Xilinx Vivado through 32 tools covering sessions, synthesis, implementation, timing, CDC, XDC, IP, waveforms, and device programming. Includes stru | |
| CAILculator MCP Server chavezailabs/cailculator-mcp MCP server for high-dimensional algebraic structure analysis, enabling AI agents to compute within sedenion and higher Cayley-Dickson algebras using formally verified transforms. | |
| KSJ MCP Server chavezailabs/ksj-mcp Converts handwritten journal photos into a searchable, AI-powered local knowledge base using Tesseract OCR. It enables users to query their notes, track insights, and export data through MCP-compatible AI assistants while maintaining comple | |
| ZDTP Chess chavezailabs/zdtp-chess Multi-dimensional chess analysis MCP server using Zero Divisor Transmission Protocol, evaluating positions across tactical, positional, and strategic layers with gateway convergence detection. | |
| Fimake chavisnguyen/fimake Enables AI agents to read, create, edit, and organize Figma documents directly through a local plugin bridge, without needing a Figma AI subscription. | |
| MCP Data Gateway chawengwit/mcp A unified data gateway MCP server that enables Claude to interact with multiple external REST and GraphQL APIs through OAuth 2.0 authentication. | |
| vscode-mcp-server chaworld/vscode-mcp-server A portable MCP server enabling AI assistants to operate VS Code, including file management, extension control, and workspace automation. | |
| MCP Playwright Weather Israel chayaetrog/mcpplaywrightweather Enables an LLM to retrieve Israeli weather forecasts by controlling a real Chromium browser to search and scrape a weather site. | |
| FS-MCP chayan-1906/fs-mcp Provides Claude with complete file system integration including directory management, file operations, Office document creation/editing, and advanced file tree visualization. | |
| GitHub MCP Server chayan-1906/github-mcp Enables AI agents to manage GitHub repositories, branches, issues, pull requests, releases, and actions through natural language. | |
| Google Workspace MCP Server chayan-1906/google-workspace-mcp The Ultimate MCP Server for Google Workspace Automation — Seamlessly integrate Google Drive, Sheets, and Docs with Claude AI and other AI agents through the Model Context Protocol (MCP). | |
| mcp-airflow-simple chayasin/mcp-airflow-simple Enables DAG management, monitoring, debugging, and connection testing for Apache Airflow through the MCP protocol. | |
| MCP Database Server chayasin/mcp-database Enables AI assistants to interact with PostgreSQL databases through query execution and schema inspection, supporting multiple schemas for customer data, document management, loan systems, and asset leasing. | |
| postgres chayasin/mcp-postgres-simple Enables querying and inspecting a PostgreSQL database, including executing SQL queries, listing schemas and tables, and describing table columns. | |
| mcp-server-duckdb chayes353/mcp-server-duckdb Enables executing SQL queries and inspecting or modifying DuckDB database schemas through MCP, with optional read-only mode and connection reuse for secure local analysis. | |
| oscine chazmaniandinkle/oscine An MCP server that exposes a synthesizer composer's command catalog as tools, enabling Claude to compose, sound-design, and mix in a live browser session. | |
| Video Downloader MCP Server chazmaniandinkle/video-downloader-mcp A Model Context Protocol server that transforms video downloading into a tool-based system for LLM orchestration, allowing users to download videos from 1000+ platforms with intelligent workflows and security features. | |
| space-stds chazzawarner/space-stds Local-first, read-only MCP server for retrieving and searching authorised CCSDS and ECSS standards, enabling citation-rich passage-level search and document access. | |
| notebook chchchadzilla/claude-notebook Enables Claude Code to list and read Gemini Notebooks through your own signed-in Chrome, in read-only mode. Client names on a local redaction list are replaced with labels on your machine before any text reaches Claude. | |
| chdb-mcp chdb-io/chdb-mcp An MCP server for chDB, the in-process SQL OLAP engine powered by ClickHouse. Lets agents query Parquet, CSV, JSON, and pandas DataFrames with one tool — no separate server, no Docker. | |
| Chatpack MCP chddaniel/chatpack Read-only MCP server for Chatpack documentation, framework setup guides, and React UI block source. Runs locally over stdio using npx -y @chatpack/mcp; no credentials or API keys required. | |
| ProjectM QA MCP chdnl0420-svg/unitymcp A Unity Editor command bridge that uses JSON files under .codex/unity-commands for request/response, enabling tools to check Unity status, execute editor commands, parse test results, and capture screenshots. | |
| Mail.ru MCP Starter chdp07egypt/mailru-mcp-starter Connects a personal Mail.ru mailbox to ChatGPT through Google OAuth and IMAP, enabling users to list folders, search and read messages without marking them read, move selected messages between folders, and send them to Trash. | |
| Mail.ru MCP starter chdp07egypt/mailru-mcp-starter-free Connects a single Mail.ru mailbox to ChatGPT through Google OAuth and IMAP, enabling folder listing, email search, non-destructive reading, moving messages, and moving selected messages to the trash. | |
| doc-cheap cheap-doc/ocr-mcp Reads passports, ID cards and driver's licences from a photo or scan and returns the printed fields and MRZ as structured JSON. One credit ($0.01) per recognised document; nothing is charged when no document is found. | |
| CheapestInference cheapestinference/mcp CheapestInference — unlimited flat-rate API for frontier open-source LLMs | |
| receiptconverter-mcp cheatbased/receiptconverter-mcp MCP server for ReceiptConverter that allows AI assistants to parse any receipt or invoice image/PDF into structured JSON with a single tool call. | |
| Codex Folders cheaux/codex-folders Enables users to organize Codex CLI conversations into folders, start and move chats within projects, and share project-specific instructions, briefs, and searchable local memory across related chats. | |
| Codex Remote cheaux/codex-remote Enables users to pair the official ChatGPT mobile app with a local Codex CLI session, check connectivity, list or revoke paired devices, and enable or disable remote access through terminal or conversational commands. | |
| UI Screenshot Comparison MCP chechle39/my-mcp-server Enables automated visual testing by comparing screenshots against baseline images using OpenAI to verify UI consistency. It generates detailed performance reports in both terminal and Excel formats based on provided user stories and accepta | |
| mcp-server-check check-technologies/mcp-server-check An MCP server that wraps the Check Payroll API, providing 263 tools for managing companies, employees, contractors, payrolls, tax configuration, and more. | |
| onshape-cad MCP server checkmate321/onshape-mcp Enables Claude to create and modify real, editable Onshape CAD models through the Onshape REST API, covering parametric sketches, solid features, configurations, assemblies with mates and motion tests, interference checks, FeatureScript cus | |
| cad-3d-builder checksim/agentic-cad-mcp Enables AI coding agents to turn natural-language descriptions and dimensional sketches into validated, watertight 3D-printable STL files by compiling build123d scripts, inspecting meshes, and rendering deterministic multiview previews. | |
| oneapi-agent checocadena/oneapi-agent-toolkit Enables coding agents to migrate, compile, scan helpers, verify behavior, and benchmark oneAPI/SYCL ports through structured, evidence-first tool results. | |
| ClearPass Sidekick MCP Server cheddarking/clearpass-sidekick-mcp Enables natural-language management of Aruba ClearPass configuration and API operations through an MCP client, exposing hundreds of ClearPass operations via progressive discovery, OAuth2/API-token authentication, and stdio transport. | |
| vpn-mcp cheeeee/vpn-mcp Enables AI coding assistants to access the internet through VPN exit nodes to bypass geo-restrictions and avoid rate limits. It allows users to route HTTP requests through various global regions and manage VPN connections directly within MC | |
| NetMCP cheenu1092-oss/netmcp Open-source MCP servers that give AI agents structured access to networking standards, device databases, and security data. | |
| Statuspage MCP Server cheenu1092-oss/statuspage-mcp-server Enables management of Atlassian Statuspage incidents, components, and subscribers through natural language. | |
| cheerio-mcp-bridges cheeriocorner/cheerio-mcp-bridges A suite of four MCP bridges that enable orchestrator agents to drive local installed CLI coding assistants (Pi, Agy, Codex, Copilot) with secure, sandboxed prompts and session continuity. | |
| MCP_HCL cheese-sansan/mcp_hcl Enables users to inspect existing H3C Cloud Lab .net projects and generate independent staged copies with added devices or links through any stdio MCP client; the returned project file can then be opened in HCL to validate the staged topolo | |
| OpenConnector cheese-zj/openconnector Provides a single local MCP endpoint that connects Gmail, GitHub, Slack, Notion, and Linear once, with multiple accounts per service, so any AI agent can use per-agent tokens, policies, and optional result filtering without re-authenticatin | |
| browser-mcp cheesecrust/browser-mcp Enables AI agents such as Claude Code, Claude Desktop, and Cursor to control a real browser through Playwright, including navigation, accessibility snapshots, clicking, typing, screenshots, JavaScript execution, tab management, and dialog h | |
| Confluence MCP Server cheesecrust/confluence-mcp Enables page search and retrieval from Confluence using the Model Context Protocol. It allows users to search documents via CQL and fetch page content as text for use within Claude. | |
| Aerospace MCP cheesejaguar/aerospace-mcp Enables flight planning and aviation operations through intelligent airport resolution, great-circle route calculation, and aircraft performance estimation. Supports 28,000+ airports worldwide and 190+ aircraft types for comprehensive fligh | |
| tradefloor-structure cheetah-trade/tradefloor-mcp Enables AI assistants to analyze smart-money market structure—trend, character shifts (ChoCh/BOS), liquidity sweeps, fair value gaps, order blocks, and pullback zones—from Hyperliquid or user-supplied candles. | |
| forency-mcp cheevahagadog/forency Enables AI agents to investigate any website's technology stack, identifying CMS, ecommerce platforms, JavaScript frameworks, analytics, CRM, marketing automation, payments, chat, CDN, and hosting. | |
| cadgang cheewee2000/cadgang Block-based implicit modeling CAD with a REST API, WebSocket updates, and an MCP server that enables Claude Code to build models, inspect geometry, render previews, and export STLs. |
38,101–38,150 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.