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 |
|---|---|
| Agent Spawner Decompose complex tasks into independent subtasks, spawn parallel agents to execute them, then collect and synthesize results efficiently. | |
| File Organizer Automatically sort and rename files by type into structured folders with undo support, configurable filters, and dry-run preview for safe batch organization. | |
| Inbox Triage Automates inbox management by categorizing messages into urgent, normal, or spam, generating daily digests, and drafting responses for low-priority items. | |
| Memory Augment Long-term memory system for OpenClaw agents. Store, retrieve, and query conversation history and learned information across sessions. | |
| Web Research Conduct structured web research by searching, fetching, and synthesizing information into reports with citations and source verification. | |
| Cron Manager Manage, schedule, monitor, and report on recurring cron tasks with flexible patterns and handle dependencies, priorities, timezones, and execution logs. | |
| text-scan Quickly find and score relevant lines with context in large text files using keyword and phrase matching to minimize reading entire files. | |
| Weather Alert Monitors weather for any location, sends alerts when rain, snow, temperature, wind, UV, or pressure thresholds are exceeded, plus daily briefings and trends. | |
| Bower Automatic Google Drive organizer. Scans Drive structure and file contents, builds a personalized preference profile, applies domain-specific logic (taxes by year, projects by name, home by system, finance by institution), and executes non-d | |
| Custodian Autonomously monitors OpenClaw system health, fixes log errors, initializes skills, registers tasks, and performs overnight maintenance to surface unresolved... | |
| Fellow Empirical experimentation engine. Invoked by Mentor to evaluate, compare, and promote improvements to OCAS skills, prompts, heuristics, and workflows using benchmark-driven experiments. Returns best variant result with lineage. Not user-inv | |
| Finch OCAS self-improvement orchestrator (Darwin's finch — adaptive evolution). Mines session JSONL files to detect corrections, breakthroughs, methodologies, course-changes, and behavioral directives (Always/Never). Routes each finding to the op | |
| Forge Skill architect and builder. Designs, builds, and validates complete Agent Skill packages through a mandatory eight-phase pipeline. Default output is the finished installable package. Not for skill evaluation (use skilllab) or variant propo | |
| Genie Safely audits and reclaims VPS/Linux disk space, investigates root-filesystem growth, and enforces backup retention when disk usage is high or maintenance is requested; use keywords disk cleanup, disk full, disk usage, snapshots, backups, s | |
| Imagine Art-direction engine for text-to-image generation. Separates Style from Content to keep aesthetic identity consistent across an image series. Use when generating, rendering, or illustrating images (especially across a series), capturing the | |
| Look Converts user-provided images into validated, decision-ready action drafts. Routes images by inferred intent across domains: events from flyers, macros from meal photos, places to save, products to price, receipts to log, documents to file, | |
| Lucid Nightly journal curator. Batch-processes OCAS skill journals via relevance classification and writes curated content to journal files for the configured memory provider to ingest. Classifies each journal for filing as a verbatim journal not | |
| Mentor Self-improving orchestration and evaluation engine for long-running multi-skill workflows. Analyzes journals, evaluates variants, and proposes skill improvem... | |
| Multipass Accomplishes tasks that need tools the agent does not have. Plans approaches, fills capability gaps with sandboxed tools, executes within an isolated session. Disposable identity, parallel discovery, incremental checkpoints, graceful degrad | |
| Ocas Praxis Bounded behavioral refinement loop. Records outcomes, extracts micro-lessons from repeated patterns, consolidates them into capped active behavior shifts, ap... | |
| Reach Live world-data query engine. Queries real-time external APIs for factual ground truth — no synthesis, no opinion, no research. Routes requests through a registry of ~55 registered sources covering US government data, scholarly literature, | |
| Sands Calendar management. Use for viewing, querying, creating, modifying, deleting, or analyzing calendar events. Handles natural-language scheduling, conflict detection with flexibility classification, free slot finding, automatic travel time e | |
| Scout Structured OSINT research on people, companies, and organizations. Use for provenance-backed briefs, entity resolution across public sources, background research with cited sources, or free-first research workflows that escalate to paid sou | |
| Sift Sift: web search, research synthesis, fact verification, entity extraction, and URL content extraction. The system's general research engine. Use for ANY task requiring web information: search, research, look up, investigate, find out, chec | |
| Skilllab Skill library maintenance: audit, merge, rename, delete, consolidate, publish, sanitize, and critique skills. Interactive menu via clarify tool. Scans ALL profile directories recursively — never hardcodes a single path. Use when the user as | |
| Spot Use when checking appointment availability, booking services, monitoring for openings, or discovering venues at salons, spas, and restaurants. spot.discover finds and compares venues via Yelp before booking. Supports Acuity Scheduling, Squa | |
| Styx Transaction data store with merchant enrichment. Provides a clean, queryable interface over raw bank transaction data. Enriches garbled/obfuscated transaction names into real business entities using SearXNG search plus LLM resolution. Inclu | |
| Taste Behavior-driven taste model built from real consumption signals. Scans email and calendar for consumption data (restaurant reservations, food delivery, hotel bookings, purchases), enriches entities with taste-relevant attributes via Google | |
| UserContext Maintains a compressed `## Daily Context` block in the owner's USER.md: an evidence-grounded snapshot of mood, location, week theme, and yesterday/today/tomorrow bullets, inferred from whatever signal sources the setup exposes (calendar, se | |
| Vesper Daily briefing generator. Aggregates signals from across the system into concise morning and evening briefings. Surfaces outcomes, opportunities, and decisio... | |
| Voyage Travel planning, itinerary construction, reservation management, lodging search, and flight search. Parallel lodging search across Expedia, Marriott Bonvoy, Marriott AI, Google Hotels, 1Stay, and HotelsByDay (day-use rooms). Flight search v | |
| Weave Private provenance-backed social graph. Maintains queryable records of people, relationships, preferences, and shared experiences for recall, gifting, hostin... | |
| Reminiscence-追忆 本地记忆语义搜索。当用户查询记忆、搜索过往记录、询问"我记得..."、"搜一下..."等所有记忆召回场景时触发。基于 BM25 + 多维信号融合，完全本地运行，无需 API Key。 | |
| taichi 太极架构多 Agent 协作框架，支持集中式、分布式，元混合三种执行模式。基于 Redis 消息总线，实现 Planner/Drafter/Validator/Dispatcher 四个阶段的工作流。 | |
| Claude Code Memory Use when you want to set up, maintain, or review a Claude Code style layered memory workflow, including `CLAUDE.md` rules, session memory, durable memory, an... | |
| video-frames 基于 PyAV 的命令行工具，支持按帧号、时间点提取视频帧，批量采样，视频信息查看及视频和图片压缩转换。 | |
| Straker Verify - AI Translation & Human Review Professional AI-powered translation with optional human verification. Supports 100+ languages. Quality boost for existing translations. Enterprise-grade security and privacy by straker.ai. | |
| Straker Verify Professional AI-powered translation with optional human verification. Supports 100+ languages. Quality boost for existing translations. Enterprise-grade security and privacy by straker.ai. | |
| headless-terminal Drive hostile or full-screen terminal UIs through the `ht` CLI from montanaflynn/headless-terminal. Use when an agent needs reliable PTY-backed interaction,... | |
| junie Install, update, authenticate, configure, and direct JetBrains Junie CLI in Junie-native ways on macOS or Linux shells. Use when a host agent should steer Ju... | |
| MALP Scout and maintain project-local context | |
| Morty's Mind Blowers Find an unusual, funny, bleak, uncanny, technical, or deep-cut memory entry and retell it as a short story in the style of Rick and Morty's "Morty's Mind Blo... | |
| Unreliable Teleplay Lens Narrative analysis framework for understanding how multiple works within a shared property or historical tradition can coexist without strict canonical recon... | |
| Compiling Architecture Use when: user wants to select architecture patterns, compile a spec, iterate on constraints/NFRs, audit why patterns were selected/rejected, or finalise an... | |
| Implementing Architecture Use when: about to write code and docs/architecture/ exists with STATUS: APPROVED in architecture.yaml. Not when: no approved architecture yet (use compiling... | |
| Using Architecture Compiler Use when starting architecture work and you need to decide whether to compile/finalise architecture or implement an already-approved architecture. | |
| Content Alchemy Turn articles, web pages, and PDFs into reusable outcomes | |
| EPUB Read Task-mode-driven EPUB reading and analysis skill with overview, targeted reading, chunked full reading, extraction, complex-content inspection, and batch pro... | |
| Cloudflare Developer Skill Expertise in Cloudflare Workers, Pages, D1, R2, KV storage, AI integration, security best practices, deployment, and performance optimization. | |
| God's eye view of your dev repos. Multi-project tracking across GitHub/Azure DevOps. AI learns from your commits to upgrade your agents.md. Developer oversight and AI agent coaching. Use when viewing project status across repos, syncing GitHub data, or analyzing agents.md against commit patterns. |
38,251–38,300 of 108,824
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.