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 |
|---|---|
| genpark-yield-curve-nelson-siegel-interpolator-skill alphaparkinc/genpark-yield-curve-nelson-siegel-interpolator-skill Enables users to perform zero-dependency quantitative finance and risk analytics through MCP, including Nelson-Siegel yield curve interpolation, option Greeks, Monte Carlo simulations, VaR/CVaR, and bond duration/convexity calculations. It | |
| genpark-zero-query-inspiration-graph-matcher-skill alphaparkinc/genpark-zero-query-inspiration-graph-matcher-skill Enables agents to turn ambient visual wallpapers and lifestyle scenes into personalized retail product recommendations and shopping actions through MCP tools. | |
| OpenClaw GenPark Alpha Leaderboard MCP Server alphaparkinc/openclaw-genpark-alpha-leaderboard Enables agents to compute conservative Bayesian TrueSkill/Glicko-2 ratings and run anti-Sybil collusion audits for leaderboard matchmaking through deterministic MCP tools. | |
| openclaw-genpark-CognitiveSynapse alphaparkinc/openclaw-genpark-cognitivesynapse Enables agents to use ACT-R spreading activation memory, semantic association graphs, and automated memory consolidation via the Model Context Protocol. | |
| OpenClaw GenPark Curator alphaparkinc/openclaw-genpark-curator Enables high-throughput MinHash LSH dataset deduplication and content quality scoring through a zero-dependency STDIO MCP server that returns deterministic JSON results for agent telemetry and task inputs. | |
| OpenClaw GenPark Deep Auditor alphaparkinc/openclaw-genpark-deep-auditor Enables deterministic auditing of multi-hop agent trajectories through cyclic loop detection, diversity scoring, and execution drift prevention via the Model Context Protocol. | |
| OpenClaw GenPark Envoy alphaparkinc/openclaw-genpark-envoy An MCP server that enables agents to perform inter-agent mutual handshakes and route messages through HMAC-authenticated envelopes with replay-attack prevention. It also provides deterministic, zero-dependency execution of telemetry inputs | |
| OpenClaw GenPark Latent Action Engine alphaparkinc/openclaw-genpark-latent-action-engine Enables MCP clients to perform speculative tree-search action prediction and prefetching using Laplace-smoothed Markov transitions, returning deterministic JSON tool results. | |
| OpenClaw GenPark Latent Intent Orchestrator alphaparkinc/openclaw-genpark-latent-intent-orchestrator Enables agents to estimate latent user intent, maintain belief states, and resolve ambiguous requests using entropy-based thresholding through MCP tools. | |
| OpenClaw GenPark Memory Vault alphaparkinc/openclaw-genpark-memory-vault Enables agents to store and retrieve hierarchical memory in cryptographically partitioned namespaces, with HMAC-based isolation and Ebbinghaus time-decay so recall fades realistically over time. Runs as a zero-dependency Python STDIO MCP se | |
| OpenClaw GenPark Negotiator alphaparkinc/openclaw-genpark-negotiator Enables multi-issue bilateral negotiation through Boulware concession curves and Pareto counter-offer synthesis, exposing deterministic game-theoretic results via the Model Context Protocol over STDIO. | |
| OpenClaw GenPark Producer alphaparkinc/openclaw-genpark-producer Enables agents to orchestrate multimodal media task DAGs, estimate critical-path makespan, and run parallel production stages deterministically through MCP. | |
| OpenClaw GenPark Recursive Operational Synthesis alphaparkinc/openclaw-genpark-recursive-operational-synthesis Enables high-throughput deterministic execution, cryptographic security, and game-theoretic optimization through the Model Context Protocol. | |
| OpenClaw GenPark Recursive Protocol Synthesizer alphaparkinc/openclaw-genpark-recursive-protocol-synthesizer Enables agents to run deterministic protocol and schema synthesis through an MCP STDIO server, including Robinson-type unification, schema lens generation, and graph edit distance scoring. | |
| OpenClaw GenPark Recursive Strategic Optimizer alphaparkinc/openclaw-genpark-recursive-strategic-optimizer Provides an MCP server for deterministic game-theoretic optimization, enabling regret-matching equilibrium computation and payoff-matrix analysis with IESDS dominance pruning via JSON tool results. | |
| OpenClaw GenPark Sentiment Harvester alphaparkinc/openclaw-genpark-sentiment-harvester Enables agents to run high-throughput deterministic sentiment polarity analysis with lexicon decay, valence shifting, and time-weighted stream aggregation through MCP tools. | |
| OpenClaw GenPark Sentinel Flux alphaparkinc/openclaw-genpark-sentinel-flux Enables agents to detect drift anomalies with CUSUM, forecast trends using Holt linear methods, and automatically trip a circuit breaker to protect workflows. | |
| OpenClaw GenPark Visual Sleuth alphaparkinc/openclaw-genpark-visual-sleuth Enables auditing visual evidence chains and checking spatial bounding consistency to detect synthetic artifacts through deterministic MCP tool responses. | |
| OpenClaw MoA Aggregator alphaparkinc/openclaw-moa-aggregator Enables deterministic execution, cryptographic security, and game-theoretic optimization through the Model Context Protocol, returning deterministic JSON tool results for agent telemetry and task inputs. | |
| MCP Memory Service alphaplapplap/mcp-memory-service Provides intelligent, persistent memory for AI assistants with semantic search, natural language queries, and OAuth-based team collaboration, enabling context-aware conversations across multiple clients. | |
| proton-bridge-mcp alpharomercoma/proton-bridge-mcp Enables AI assistants to read and search Proton Mail inbox through Proton Mail Bridge, providing tools to list mailboxes, list messages, search messages, and fetch full message bodies. Read-only, with secure certificate pinning. | |
| proton-bridge-mcp alpharomercoma/proton-bridge-mcp-py MCP server for reading and searching Proton Mail via Proton Mail Bridge, providing tools to list mailboxes, list/search messages, and get message details with TLS certificate pinning. | |
| invarianteval-mcp alpharomerojl/invarianteval Enables AI agents to run safety-invariant checks on structured outputs, ensuring locked fields are never auto-filled by the model without human confirmation. The server provides two tools: check_invariants and list_invariants for determinis | |
| claude-usage-mcp alphasaleaidan/claude-usage-mcp Gives the model visibility into the same 5-hour session, weekly, and per-model usage percentages shown in Claude Code, along with reset times. It also lets a project cap how much of the weekly limit may be spent via start/check/end budget t | |
| intently alphaxalchemy/intently Enables AI agents to find the right tool from a vague, misspelled, or rambling description by searching a library of tools and returning ranked matches with fit grades, links, and evidence. | |
| Swiss Whale Intelligence alpineflow-io/swiss-whale-intelligence-mcp Methodology-transparent BTC + ETH whale forensics. 30 tools, anonymous OAuth 2.1 Free tier. | |
| aseprite-lua-mcp alpsei/aseprite-lua-mcp Enables LLM agents to create pixel art and animations in Aseprite by writing and headlessly executing complete Lua scripts, with API documentation and output verification. | |
| paperloom alpsource/paperloom Enables coding agents to maintain a folder-scoped research wiki for scientific papers by providing MCP tools for full-text search, reading, note creation, tagging, logging, and PDF ingestion, all without requiring its own LLM API key. | |
| obsidian-mcp alq78/obsidian-mcp Enables AI agents to move and rename notes and folders inside an Obsidian vault while keeping internal links intact, by driving the running Obsidian app through its official CLI. Also exposes backlink lookups and works from clients whose sh | |
| fffinstill alraico/fffinstill-mcp-server MCP server for fffinstill — A Research Lab for Your Investment Ideas | |
| mcp-guard alramalho/mcp-guard An HTTP proxy that secures MCP servers by intercepting tool calls and blocking requests based on configurable keyword patterns. It provides a simple way to prevent destructive operations on upstream servers like databases through a JSON-bas | |
| aether-mcp alrazihi/aether-mcp Provides system utilities, file operations, data tools, creative idea generation, and dynamic resources via MCP, with auth support for bearer tokens and OAuth. | |
| astra-aigate alrcatraz/astra-aigate Unified AI gateway that aggregates MCP tools from multiple servers and routes LLM requests with provider combos and fallback, all managed through a web UI. | |
| astra-knowledge-base-mcp alrcatraz/astra-knowledge-base-mcp MCP server for managing and searching multi-tenant knowledge bases backed by SQLite with FTS5, enabling AI agents to persist and retrieve content via full-text search. | |
| Gong-MCP alroy/gong-mcp Provides tools to access Gong call data, including listing calls, retrieving details and transcripts, searching across transcripts, and listing users. | |
| ios-control-mcp als0m3/ios-control-mcp Enables a macOS MCP client to control a real iPhone through CoreDevice services, including screenshots, normalized taps and swipes, text entry, hardware-button presses, and app launching or listing. | |
| ft_mcp alsaeed3/ft_mcp A Python MCP server implemented from scratch, providing tool execution capabilities like system time and file hashing via stdio or HTTP transport. | |
| customer-replies-mcp-server alsaltitop/customer-replies-mcp-server MCP server for managing and composing customer replies for a phone and computer repair shop, with built-in templates and WhatsApp link generation. Supports Arabic and English. | |
| phpIPAM MCP Server alsamasu/phpipam-mcp Enables LLMs to manage IP addresses, subnets, and network sections through natural language, with security features like read-only by default. | |
| fsm-voice-mcp alsayedgamal/fsm-voice-mcp Turns a single XState-compatible finite state machine config into a voice-driven MCP surface, generating one tool per event and a resource exposing the current state, context, and available actions. Lets voice assistants and other MCP clien | |
| shop-db alser15/mcp This MCP server lets an AI agent securely connect to a read-only SQLite store database, inspect its tables and schema, and run analytical SQL queries without modifying any data. | |
| PolicyPilot MCP Server alshawwaf/policypilot Enables LLM agents to automate Check Point firewall rule changes by translating natural language access requests into correct, first-match-safe policy updates via MCP tools. | |
| Allure TestOps MCP Server alshurov13/allure-testops-mcp-python Enables natural language interaction with Allure TestOps API for managing test cases, launches, and test plans with full CRUD support and 56+ controller endpoints. | |
| Sherlock's second brain alshyra/sherlock-second-brain This MCP server implements a second brain system, managing unvalidated investigation cases as JSON and validated knowledge as markdown files and skills. It provides tools for creating, updating, promoting cases, managing knowledge files, an | |
| mcp-redmine alsimoes/mcp-redmine-rest MCP server for Redmine that provides full read/write coverage of issues, projects, wiki, time tracking, and more through 73 tools via the Redmine REST API. | |
| Strata MCP alsk1992/strata-mcp Enables MCP-compatible agents to access live Strata markets and Sonar pricing for real-time quotes and market data. | |
| Librarian MCP alsokolov2/librarian-mcp Transforms a folder of Markdown files into a structured, version-controlled knowledge base with semantic search and safe AI editing via draft branches. | |
| decide alsoleg89/decide Enables AI agents to bulk-classify files, logs, and JSONL records against user-defined criteria via Jev, returning compact summaries and review queues for exceptions. It keeps bulk data out of the agent context and supports reproducible cos | |
| MCP Test Project alsomefuad/mcp A simple MCP server/client implementation for testing Hermes Agent, exposing basic tools like echo, add, and get_server_info via stdio. | |
| GitHub MCP Server alsonwangkhem/github-mcp-2 An MCP server that allows Claude and other MCP-compatible LLMs to interact with the GitHub API, supporting features like creating issues, getting repository information, listing issues, and searching repositories. |
27,701–27,750 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.