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 |
|---|---|
| elementor-live archidoxx/elementor-live Enables coding agents to work inside a live WordPress Elementor editor tab: reading the canvas skeleton and element settings, creating/updating/moving/deleting elements through Elementor's own command API as single undo steps, taking pixel- | |
| Local Grounding MCP archie-ib-dev/local-grounding-mcp Enables MCP browser agents to locate described UI targets in screenshots through local inference when DOM or accessibility references are unavailable. It shares one localhost-only model across clients, supports lazy loading and screenshot c | |
| OSOP MCP Server archie0125/osop-mcp Enables AI agents to manage OSOP workflows by providing tools for validation, execution, testing, and optimization. It also supports converting workflows between OSOP and external formats like GitHub Actions, BPMN, and Airflow DAGs. | |
| Speechmatics MCP Server archiemcm234/speechmatics_claude_code_mcp Enables Claude Code to transcribe audio and video files using the Speechmatics Batch API, with support for speaker diarization, batch processing, and searching transcripts. | |
| SSI Stock Data MCP Server archiephan78/ssi-stock-mcp-server A Model Context Protocol server that enables AI assistants to query Vietnam stock intraday data from SSI FastConnect API, providing access to stock codes, detailed information, index data, and OHLC information through natural language queri | |
| arc-diagram archijones-ai/arc-diagram-mcp Enables MCP agents to validate architecture descriptions and scaffold complete, interactive React Flow diagram applications with multiple visual dialects, themes, exports, and verification probes. | |
| mcp-aws-cost-anomaly archimedes-market/mcp-aws-cost-anomaly AWS Cost Explorer + Anomaly Detection exposed as MCP tools. Surface unusual spend by
service/account/tag, pull cost breakdowns, forecasts, savings recommendations. Read-only IAM — refuses to start
if the role can modify resources. Curated b | |
| mcp-kicad-pcb-inspector archimedes-market/mcp-kicad-pcb-inspector Parse and analyze KiCad PCB files from AI agents — layer stackup, net listing, footprint
inventory, DRC violation surfacing, board outline geometry. Curated by Archimedes Market with a verified Trust
Report. | |
| mcp-langchain-bridge archimedes-market/mcp-langchain-bridge Expose any LangChain chain, agent, or tool as an MCP server — schema-aware tool registration,
tool-call tracing, structured output validation. Bridges LangChain into Claude/Cursor/Windsurf. Curated by
Archimedes Market with a verified Trust | |
| mcp-openscad-render-loop archimedes-market/mcp-openscad-render-loop OpenSCAD wrapped as an MCP server. Render .scad with parameter overrides, run parametric sweeps,
validate syntax, compute STL metrics. Curated by Archimedes Market with a verified Trust Report. | |
| mcp-postgres-analytics archimedes-market/mcp-postgres-analytics Read-only PostgreSQL analytics MCP server — query plans, slow queries, index usage, table bloat, vacuum status. No DDL/DML/writes. Curated by Archimedes Market with a verified Trust Report. | |
| mcp-semgrep-scanner archimedes-market/mcp-semgrep-scanner Run Semgrep static analysis from an AI agent. OWASP top 10, secrets detection, custom rule packs,
baseline scanning. Curated by Archimedes Market with a verified Trust Report. | |
| MCP Excel Reader archimedescrypto/excel-reader-mcp Provides efficient handling of large Excel files through automatic chunking and pagination, using MCP to enable seamless file reading and management features such as sheet selection and error handling. | |
| Figma MCP Server with Chunking archimedescrypto/figma-mcp-chunked A Model Context Protocol server for interacting with the Figma API that handles large Figma files efficiently through memory-aware chunking and pagination capabilities. | |
| Fusion 360 MCP Server archimedescrypto/fusion360-mcp-server A Model Context Protocol server that enables Cline to translate natural language prompts into Fusion 360 CAD operations by mapping commands to Fusion's API and generating executable Python scripts. | |
| Production Scheduling MCP archiplan-io/production-scheduling-mcp Enables AI assistants to generate feasible production schedules with an OR-Tools CP-SAT solver, assigning job steps to eligible machines while avoiding conflicts and downtime and minimizing priority-weighted lateness. | |
| Git Workflow MCP Server archis17/mcp-server Enables AI assistants to interact with local Git repositories for operations like status, commits, branching, and diffs, plus GitHub API integration for managing pull requests when authenticated. | |
| GitHub MCP Server archish9/versioncontrolhelpermcp A Model Context Protocol server that provides Git version control operations as structured tools for AI coding agents. It enables LLMs to programmatically manage repositories through actions like committing changes, rolling back code, and c | |
| yandex-calendar-mcp architawr/yandex-calendar-mcp Enables MCP clients such as Codex and Claude Code to read Yandex calendars and events over CalDAV via stdio, while create, update, and delete operations require an explicit preview and separate approval. | |
| triage-mcp architect-34/triage-mcp Enables LLMs to triage GitHub issues by retrieving similar reported issues and classifying components using historical data. | |
| Revit MCP Automation architectureworld/revit-mcp-automation Enables AI clients to start and use isolated Revit 2020 instances on demand, handle common warnings and dialog popups, and retrieve the original operation result after dialogs are resolved. | |
| Imagine MCP archive228/imagine-mcp Enables authenticated remote access to xAI media generation for images, video, and speech over Streamable HTTP, with persistent media URLs, usage receipts, and enforced daily spend limits. | |
| Kintone Development Support MCP Server archivierterepositories/kntn-dev-mcp Enables developers to access kintone API specifications, field type documentation, and development best practices through natural language queries. Supports API request validation and provides comprehensive development guidance for kintone | |
| archivist archivist-gg/archivist-generators Provides read-only SRD lookup and deterministic enrichment tools for D&D 5e content generation, including search, entity retrieval, and generation of monsters, spells, items, NPCs, and encounters. | |
| Claude Gemini Bridge archolet/claude-gemini-bridge An MCP server that provides access to Google Gemini models via Vertex AI, enabling text generation, multi-turn chat, image/video generation, and frontend design through Claude Code. | |
| Menhir archolith/menhir Provides coding agents with governed semantic memory and code-graph context via MCP, enabling code-linked recall, blast-radius impact analysis, and lifecycle-aware memory management. | |
| GMC MCP Server archpeng/gmc-mcp-server Enables interaction with Google Merchant Center through 34 tools across 9 modules, including account management, product operations, reports, inventory, promotions, shipping, return policies, collections, and recommendations. | |
| Git Workflow Automation MCP Server arcia125/git-workflow-mcp-server Provides automated Git workflow tools for committing, creating pull requests, and merging with proper GitHub authentication handling. Supports complete Git workflows from commit to merge with dry run capabilities and conventional commit for | |
| @arcis/mcp arcis-protocol/mcp Connect any AI agent to Arcis Protocol DeFi vaults through natural language, enabling deposit, withdrawal, and status queries without SDK or code. | |
| ARCLinearGitHub-MCP arclabs-studio/arclineargithub-mcp Bridges Linear issue tracking and GitHub repository management with ARC naming conventions, enabling composite workflows like creating a Linear issue and GitHub branch in one step. | |
| webmcp-bridge arclat-ai/webmcp-bridge Enables MCP clients to discover and invoke tools registered by web applications in a live browser session, executing them within the page's JavaScript context. | |
| LumenCore arclightdynamics/lumencore Provides AI coding assistants with persistent project memory to retain architectural decisions, code patterns, and domain knowledge across sessions. It stores data locally in a SQLite database, allowing agents to remember, recall, and manag | |
| github-projects-mcp arclio/github-projects-mcp github-projects-mcp | |
| coding-challenges arclops/mcp-server Enables AI coding agents to discover whether anyone has shared a solution to a Coding Challenge and in which language, listing challenges and filtering solutions by language. | |
| squeeze arcnosixta/squeeze Enables a coding agent to compress noisy tool output such as compiler errors, failing test runs and repeated logs before it enters the context window, and to fetch any collapsed ref back as its exact original text. Two tools, squeeze_fetch | |
| @arcnow/mcp arcnow-io/arcnow-io-mcp Enables an AI assistant to read token bonding curves, quote trades with fee breakdowns, monitor graduation progress, and optionally launch, buy, sell, or rescue tokens on Arc via arcnow.io. | |
| coda-mcp-readonly arco-greendigit/coda-mcp-readonly A read-only MCP server for interacting with Coda API, enabling listing documents, pages, tables, rows, and retrieving page content as markdown. | |
| MCP Atlassian arconixforge/mcp-atlassian Enables AI assistants to interact with Atlassian products (Confluence and Jira) through natural language, supporting both Cloud and Server/Data Center deployments. Allows searching, creating, and managing content across Jira issues and Conf | |
| Arco Lexicon arcoventure/arcoventure-mcp-server Canonical vocabulary server for autonomous business design. Exposes the Arco Lexicon as seven MCP tools: term lookup, related terms, alignment verification, citation formatting, source retrieval, term listing, and term suggestion. No authen | |
| comp3900_server arctic-cheetah/mcp-server Enables installation and management of the COMP3900 project, including cloning, prerequisite checks, backend/frontend setup, Docker Compose, and optional cloudflared installation. | |
| Paid Media MCP arcticgreyy/paidmedia-mcp Enables Claude to access and analyze your paid media campaign data, team structure, performance metrics, and reporting templates, so it can answer questions and assist with analysis directly in your workflow. | |
| IP Intelligence MCP Server ard1102/ip-intelligence Provides MCP tools for IP threat intelligence lookup and enrichment, including single IP lookup, bulk hunting, ASN expansion, and feed status queries. | |
| Arda Vector Database MCP Server ardaglobal/mcp-ardaglobal-code Enables semantic code search across multi-language codebases using natural language queries, integrated with Qdrant vector database for fast, cached retrieval. | |
| CloudLab MCP Server ardagurcan/cloudlab-mcp Enables AI assistants to manage CloudLab/Emulab experiments, including listing experiments, controlling nodes (reboot, reload, power cycle), retrieving console logs, extending experiment time, and terminating experiments. | |
| cursor-mcp-qa-agent ardaka/cursor-mcp-qa-agent A local MCP server that gives Cursor Agent three focused QA tools for analyzing user stories, creating test charters, and drafting bug reports, with built-in safety rules and reusable workflows. | |
| drawio-desktop-mcp ardauzun/drawio-desktop-mcp Enables AI agents to create and edit diagrams in the draw.io desktop app through the Model Context Protocol. | |
| cc-handoff ardayldz8/cc-handoff Enables a planning Claude chat and Claude Code to exchange work through local Markdown files, letting the chat create tasks that code agents pick up, complete, and report back on. Project-scoped task and report tools track each item's statu | |
| zalo-mcp ardennguyen/zalo-mcp Self-contained MCP server for Zalo that enables AI agents like Claude Code and Cursor to automate Zalo Personal and Official Accounts via a 1-click sandboxed deployment. | |
| verify-action ardev-lab/verify-action-mcp Verify AI agent tool calls with content-addressed, HMAC-attested receipts.
Free third-party verification API for AI agents. Call verify_action(claim, evidence)
to get an independent integrity check on whether your claimed action matches the | |
| cardano-defi-mcp ardey26/cardano-defi-mcp Enables AI agents to discover Cardano DeFi venues, fetch cross-chain swap quotes into ADA, read balances and positions, and obtain unsigned transactions for the agent to sign with its own keys. |
30,201–30,250 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.