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 |
|---|---|
| contexte contexte-tech/contexte-python Search and load AI fine-tuning and evaluation datasets, prompts and few-shot contexts from the ContexteTech catalogue, grounded in official European sources, in 9 languages. Dataset download links (JSONL, ShareGPT, Alpaca, CSV) and cost est | |
| ContextFS contextfs/contextfs Universal AI memory layer that provides cross-client, cross-repo context management with semantic search, automatic code indexing, and session management. Enables persistent developer memory across projects with typed memories, graph-based | |
| ContextSynapse MCP Server contextsynapse/contextsynapse Exposes a shared graph-based context engine as MCP tools for Claude, Copilot, and other AI agents, enabling knowledge ingestion, recall, search, and LLM-ready context assembly across sessions. | |
| Contextual contextual-laboratories/contextual-labs Persistent memory for AI coding agents: local-first semantic search, dependency graphs, git history. | |
| Contextual MCP Server contextualai/contextual-mcp-server A Model Context Protocol server that provides Retrieval-Augmented Generation capabilities using Contextual AI, enabling AI interfaces like Cursor IDE and Claude Desktop to query domain-specific knowledge with context-aware responses and sou | |
| artl-mcp contextualizer-ai/artl-mcp Enables comprehensive scientific literature retrieval and analysis through Europe PMC, PubMed, and other databases, supporting metadata extraction, full-text access, and identifier conversion via MCP and CLI. | |
| landuse-mcp contextualizer-ai/landuse-mcp A Model Context Protocol server for retrieving land cover, soil type, and temporal land use data for any geographical coordinates using the National Land Cover Database and FAO soil classifications. | |
| Context MCP Server contextwtf/context-mcp Enables AI agents to browse, trade, and create prediction markets on Context Markets. Supports wallet management, order placement, and market creation through MCP tools. | |
| MCP REST API Tester conti742/mcp-rest-api Enables testing and interacting with REST API endpoints directly from MCP clients, supporting multiple HTTP methods, authentication methods, custom headers, and response size limits. | |
| Zotero Read-Only Assistant continuingrace/zotero-read-only-assistant Enables read-only access to a local Zotero Desktop library, providing search, recent items, metadata, tags, collections, PDF attachments, and full-text search through a browser UI or MCP endpoint. | |
| mcp-macos-toolkit contractorkeith/mcp-macos-toolkit Local-first macOS MCP server for searching files, running approved Shortcuts, managing Homebrew packages, and working with local models, with read-only defaults and optional gated mutations. | |
| ContractScan contractscan-dev/contractscan Enables scanning a single-file Solidity contract before deployment by running Slither, Aderyn, and rug-pull/centralization heuristics in a sandboxed environment, then returning a Deployable / Fix first / Do not deploy verdict with plain-lan | |
| qa-mcp contraliz/qa-mcp Lets an agent open a running web app in a real browser, perform literal interaction steps, capture screenshots, measure UI rules, diff frames, and store evidence, while leaving all judgment to the calling agent. | |
| Controtto contre95/controtto You are capable of interpreting golang code and judge it under the most strict ddd and clean architecture paragidms | |
| ET-MCP contresillo/et-mcp Provides 17 standalone tools across calc, site, and catalog domains, enabling optics calculations, knowledge-base search, and read-only lens catalog queries via MCP without requiring an LLM or frontend. | |
| E2B MCP Server contributory/e2b-mcp-server Enables managing E2B cloud sandboxes, templates, filesystems, and processes through Model Context Protocol tools. | |
| email-mcp contributory/email-mcp MCP server for reading, searching, sending, and managing emails via IMAP/SMTP, with tools like list_emails, read_email, search_emails, send_email, get_attachment, get_account_info, and mark_email_read. | |
| runloop-mcp contributory/runloop-mcp An MCP server that exposes Runloop Devbox operations as tools, enabling AI agents to create and manage Linux sandboxes, execute commands, edit files, snapshot disks, and drive interactive PTY sessions. | |
| Steel MCP Server contributory/steel-mcp Enables browser automation through the Steel API, allowing session management and actions like navigation, clicking, typing, screenshots, JavaScript evaluation, and data extraction. | |
| ControlBoard MCP Server controlboardai/controlboard-client Enables AI coding tools like Claude Code, Codex, and Cursor to register with ControlBoard boards, providing 44 tools for task management, agent coordination, and a live local mirror of board state via WebSocket. | |
| ControlDrill controldrill/mcp Let agents list, schedule, and pull evidence packets for your org’s incident-response tabletop exercises (evidence of practice, never a compliance verdict). | |
| Parts Finder MCP controlguy-ys/electronic-parts-finder-mcp Read-only MCP server for finding, comparing, and shortlisting engineering parts from distributor and marketplace APIs. | |
| dsh-bridge controlledentropy/dsh-bridge A stdio MCP server that wraps DeepSeek Harness's local /api into 9 tools, letting any standard MCP client create or adopt named dsh sessions, dispatch task briefs, poll asynchronously, and retrieve auditable per-turn results. It also enforc | |
| PCM MCP controllogix/pcm600-mcp An MCP server for ABB/Hitachi Energy PCM600 that provides offline IEC 61850 SCL file analysis, .apcmp project archive inspection, ACT logic recovery, and safe read-only drive of the PCM600 CLI for project exports and validation. | |
| rockwell-logix-mcp controllogix/rockwell-logix-mcp Exposes Rockwell Automation's Logix Designer SDK as 39 tools for programmatic ControlLogix/CompactLogix engineering, letting users create and build Studio 5000 projects, generate and validate L5X from point lists, read/write tags, resolve c | |
| FluxCD MCP Server controlplaneio-fluxcd/flux-operator GitOps on Autopilot Mode | |
| barcode-mcp convalexa-solutions-llp/barcode-mcp MCP server for generating and decoding barcodes, QR codes, and encoding RFID EPCs according to GS1 standards. All processing is local with no network calls. | |
| flux-mcp converged-computing/flux-mcp Provides agentic MCP tools for the Flux Framework, enabling job submission, management, and resource scheduling for HPC workloads. | |
| hpc-mcp converged-computing/hpc-mcp Provides MCP tools for high-performance computing (HPC) and converged computing, enabling agentic interactions with HPC resources and workflows. | |
| Converly MCP converlyio/converly-mcp Enables an AI assistant to set up and manage server-side conversion tracking by connecting ad platforms like Google Ads, Meta, and GA4, building and publishing conversion flows that fire when forms are submitted, installing tracking snippet | |
| convert-online-mcp convert-online/convert-online-mcp Convert files between 400+ image, video, audio, document, spreadsheet, ebook, archive and font formats, with OCR. A thin stdio client for the hosted Convert.Online REST API — it converts nothing itself and no file passes through the process | |
| File Convert MCP Server convertguru/file-convert-mcp A Model Context Protocol (MCP) server for converting files between different formats | |
| Convex MCP server convex/convex-backend Convex’s MCP server lets you introspect tables, call functions, and read/write data seamlessly. Agents can generate one-off queries safely—thanks to Convex’s sandboxed queries, ensuring data integrity. Perfect for AI automation, real-time a | |
| conviviera conviviera/conviviera-claude-plugin Enables MCP clients to act as disclosed AI participants on the public piazza: read discussions, reply, react, vote, bookmark, and message, while enforcing community norms and token-efficient reads. | |
| ConvoKit MCP convokitapp/convokit-mcp Enables coding assistants to integrate the platform using official SDK, UI, authentication, and REST documentation guides, and to manage an app's users, scoped tokens, memberships, conversation metadata, and messages through configurable co | |
| firedbg-mcp convonknorrisson/firedbg-mcp Enables discovery, execution, indexing, and querying of Rust program traces using FireDBG, scoped to a single Cargo workspace. | |
| Care Relay coo001/care-relay Enables families to maintain a shared, self-hosted care log through any MCP client: replacing a daily care plan, logging doses, meals, water, symptoms, notes and appointments with a duplicate guard, checking each planned slot's status, and | |
| mcp-system-info cooderamily/system-tool-mcp Provides system hardware information (CPU, memory, storage, etc.) and system status (OS, network, resource usage) via MCP tools. | |
| MCP-Discord cook392/mcp-discord Enables AI assistants to interact with Discord by logging in as a bot and managing servers, channels, forums, messages, reactions, roles, members, and webhooks. | |
| Joplin MCP Server cook52491/joplin-mcp Enables AI assistants to search, read, create, edit, delete, and tag notes and notebooks in a Joplin instance through 26 MCP tools, with optional permission levels, notebook allowlisting, and file import. | |
| aihub-mcp cookaihq/aihub-mcp Enables agents to generate images, video, audio, and documents via AihubMax API, with task management and media analysis capabilities. | |
| hamgoose cooked-ham/hamgoose Enables goal-driven mission orchestration for Goose, turning a user goal into a structured plan with an approval gate, isolated workers in git worktrees, dual validation, auto-correction, and crash recovery to produce validated code. | |
| Ebay MCP Server cookey-monster/ebaymcpserver A Model Context Protocol server that lets you fetch auctions from Ebay.com using natural language prompts like 'Find me 10 auctions for batman comics'. | |
| @cookiemunch/mcp cookie-munch/mcp Exposes the Cookie Munch Developer API as MCP tools, enabling AI assistants to manage sites, read consent analytics, and drive privacy operations. | |
| DevVault MCP cookieark7/devvault-mcp Provides structured access to DevVault's local Postgres database, allowing schema inspection, read-only queries, guarded writes, and dummy data seeding for testing. | |
| NeoSatoshi Card Recognition cookiebreed/card-recognition-api Identify trading cards (Pokémon, One Piece, Lorcana, Yu-Gi-Oh!, Magic, Star Wars: Unlimited) and football cards from a photo, several cards per photo, with Cardmarket prices. Search and correct cards and export them as CSV or JSON; works wi | |
| ClickUp MCP cookiecad/clickup-mcp Enables ClickUp workspace management including tasks, docs, teams, spaces, and folders through natural language using the ClickUp REST API. | |
| vincent-vnc-mcp cookiemonster0921/vincent-vnc-mcp A self-hosted, VNC-backed MCP server that enables AI agents to control a dedicated macOS user session remotely, without disturbing the console user. | |
| TeamMCP cookjohn/teammcp TeamMCP is an MCP-native collaboration server that enables AI agents and humans to communicate through shared channels, direct messages, and integrated task management. It provides a persistent layer for real-time collaboration with full-te | |
| caldav-mcp cookkie03/caldav-mcp Connects MCP-compatible clients to any CalDAV server for managing calendars, events, and todo tasks. |
40,301–40,350 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.