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 |
|---|---|
| VA Form Generation MCP Server agilesix/va-form-generation-mcp Provides tools for auditing and fixing scaffolded VA forms to ensure they follow best practices and VA.gov content standards. Enables automated validation, agent prompt generation, and orchestration of form fixes across any vets-website wor | |
| airis-mcp-supabase-selfhost agiletec-inc/airis-mcp-supabase-selfhost MCP server for self-hosted Supabase with RLS-aware PostgreSQL and PostgREST layers, enabling safe database introspection, SQL queries, and PostgREST access via natural language. | |
| drafts-mcp-server agiletortoise/drafts-mcp-server Enables AI assistants to manage drafts, tags, workspaces, and actions in the Drafts app on macOS. | |
| imap-mcp agimenezdev/imap-mcp Enables email management via IMAP and SMTP with multi-account support, safe sending with confirmation, and read-only modes. | |
| thunderbird-mcp agimenezdev/thunderbird-mcp Enables searching and reading Thunderbird emails locally through MCP, using the mail client's own index for offline, credential-free access. | |
| TaskFlow AI agions/taskflow-ai TaskFlow AI is a premium MCP Server designed for AI editors, offering 40+ built-in tools covering file system, HTTP requests, databases, Git operations, and more. | |
| AgisHub MCP Server agishub/agishub-mcp AgisHub provides a diverse set of pay-per-call tools for AI agents—covering timezones, web extraction, AI, memory, webhooks, finance, and utilities—accessible via a free MCP tier or x402 HTTP micropayments in USDC on Base, with no signup or | |
| chronosync-mcp agishub/timezone-toolkit Free, keyless MCP server for timezone conversion, world clock, DST-aware date arithmetic, and cross-timezone meeting scheduling using IANA timezones. | |
| mcp-boilerplate agiulucom42-del/mcp-boilerplate Production-ready template for building MCP servers with TypeScript, featuring example tools and resources, and Claude Desktop integration. | |
| aipass-th-mcp agl01cpg/mcp-aipass Enables connecting to TH-AI Passport to retrieve chat lists and contents, and send new messages through a real browser. | |
| @agledger/mcp-server agledger-ai/mcp-server Connects MCP-compatible AI agents to the AGLedger API for change control, recording every change with signed, hash-chained records. Provides API pass-through tools and an offline audit verifier. | |
| evo-marko agliga/evo-marko-mcp Enables AI assistants to retrieve accurate definitions, examples, accessibility guidance, and documentation for eBay evo-web Marko 6 components, Marko 6, evo icons, and migration mappings so they can write correct markup and Tags API code. | |
| PubMed MCP Server aglitch120/pubmed-remote Enables comprehensive biomedical literature research through PubMed database access with advanced search, full-text retrieval, citation analysis, and batch processing capabilities. Supports both local deployment and cloud hosting for seamle | |
| Fetch MCP Server aglolz/mcp-fetch Enables LLMs to retrieve and process web content by fetching URLs and converting HTML to markdown format. Supports chunked reading of large pages and can access both public websites and local networks. | |
| phoneuse agmada-asa/phoneuse Enables a local coding agent to control and inspect an Android phone over the user's own Wi-Fi, with on-device consent and an app blocklist. Provides tools to read the screen, take screenshots, tap, swipe, type, scroll, and navigate Back, H | |
| plan-export-mcp agmonetti/plan-export-mcp Enables coding agents to export Markdown implementation plans and audits into pixel-perfect PNGs, PDFs, and self-contained HTML files, with code highlighting, Mermaid diagrams, and GitHub callouts preserved. | |
| agnara-mcp agnara-project/agnara-a8-mcp-service Enables MCP clients to discover and invoke Agnara capabilities over stdio, with schema-projected tools and fail-closed authorization. | |
| Request Triage MCP Server agnesmuita/ai-operations-triage-agent Provides tools to list pending requests, save priority scores, and retrieve ranked backlog, enabling AI-driven triage of automation requests from a Notion database. | |
| LINE OA MCP Ultimate agnieszka3425/line-oa-mcp-ultimate Lets AI agents operate one or many LINE Official Accounts through natural language, covering broadcasts, Flex and Rich Messages, rich menus, coupons, audiences, insights, and LINE Shopping. It handles LINE Messaging API calls, image hosting | |
| Ombre-Brain agnieszka49335/ombre-brain This server enables persistent, long-term memory for an LLM by storing past conversations and experiences with emotional coordinates. It implements a decay curve, allowing memories to naturally fade or actively surface based on their intens | |
| Smart Coding MCP agnieszka5281/smart-coding-mcp Enables AI assistants to search a codebase by meaning using locally generated embeddings, so relevant code is found even when the query's wording differs from the code. It also supports package version lookups across many ecosystems, plus r | |
| octagon-mcp-server agnieszka562/octagon-mcp-server Enables natural-language, source-backed research across SEC filings, earnings transcripts, company financials, stock and crypto market data, and prediction markets news. It also provides deep research orchestration and live documentation ac | |
| knowledge-base-server agnieszkac29/knowledge-base-server Enables AI agents to share persistent, self-improving memory by ingesting, classifying, synthesizing, and retrieving knowledge from sources such as Obsidian vaults, code, transcripts, bookmarks, and terminal sessions through MCP and REST AP | |
| env-doctor-mcp agnieszkahart/env-doctor Exposes 11 diagnostic tools to AI assistants, enabling them to check GPU/CUDA compatibility, assess AI model fit, and validate Dockerfiles for GPU issues through natural language. | |
| Academic Paper Search MCP Server agnieszkamustafa1128/academic-search-mcp-server Enables Claude and other MCP-compatible clients to search academic papers across Semantic Scholar and Crossref, fetch detailed metadata and abstracts, filter topic searches by date, and retrieve full-text content when available. | |
| Stock Trade MCP Server agnieszkas052/stock-trade-finance-api Exposes Tiingo API endpoints as MCP tools, enabling retrieval of end-of-day and intraday prices, forex quotes, news articles, fundamental statements and metrics, dividend distributions and yields, and stock splits. It lets MCP clients query | |
| Gitingest-MCP agnieszkateixeira16172/gitingest-mcp Enables MCP clients to quickly extract information about GitHub repositories, including repository summaries, project directory structure, and file content. | |
| tradingview-chart-mcp agnieszkathomas943/tradingview-chart-mcp Enables users to fetch TradingView chart images for any ticker and interval, with browser pooling for faster concurrent requests and built-in performance statistics. | |
| review-md agnojf/alson-annotation Enables reviewing Markdown files in a browser with inline annotations, submitting or cancelling reviews, and returning structured feedback through the review_markdown MCP tool. | |
| BenchClaw MCP Server agnuxo1/benchclaw-integrations Register LLMs and agents on the P2PCLAW decentralized benchmark network and query live performance scores via the BenchClaw API. | |
| p2pclaw-mcp-server agnuxo1/p2pclaw-mcp-server A backend MCP server that enables AI agents to publish, validate, and search research papers, submit swarm-compute jobs, and invoke formal proof checking on the P2PCLAW decentralized network. | |
| PaperClaw Research Companion agnuxo1/paperclaw-research-companion Enables a local MCP-compatible assistant to discover real publications from Europe PMC, Crossref, or P2PCLAW, compare selected sources, and create evidence briefs; with an optional write token, it can also save, list, and export collections | |
| PayPal Agentic Guardrail agnuxo1/paypal-agentic-guardrail Enables an AI agent to create and capture orders, refund captures, and pay suppliers through PayPal while the operator's policy fixes the payee, currency, and credential behind a broker that the agent never sees. Adds spending limits, human | |
| API Agent agoda-com/api-agent Turn any API into an MCP server. Query in English. Get results—even when the API can't. | |
| StarRocks MCP Server agonzalez4282/mcp-server-starrocks It enables AI assistants to execute SQL, explore databases and schemas, access system metrics, retrieve table and database overviews, and generate Plotly charts from query results. | |
| agoradigest-mcp agoradigest/agoradigest-mcp MCP server that connects your AgoraDigest A2A agent to MCP-compatible clients, enabling drive of agent actions like sending DMs, checking inbox, managing friends, and rehydrating context with persistent per-friend memory. | |
| Agoragentic agoragentic/agoragentic-integrations Agent-to-agent marketplace where AI agents discover, invoke, and pay for services from other agents using USDC on Base L2. 72+ services, free tools, x402 micropayments. | |
| Agoric Dev MCP Server agoric/agoric-dev-mcp Provides AI assistants with a comprehensive toolkit for developing, testing, and deploying smart contracts on the Agoric blockchain. It supports key Agoric features such as the Zoe contract framework, ERTP asset handling, and cross-chain or | |
| Agorus MCP Server agorus-ai/mcp-server MCP server for the Agorus AI agent marketplace, exposing API operations as tools for LLMs to discover, contract, and interact with agents and services. | |
| gitlab-duo-mcp-bridge agostynah/gitlab-duo-mcp-bridge Wraps GitLab Duo CLI as an MCP tool for code review, enabling agents to get structured Duo reviews via duo_review. | |
| zenodo-mcp agostynah/zenodo-mcp An MCP server for discovering, retrieving, citing, and evaluating scientific records from the Zenodo repository. | |
| ferric-fred-mcp agpalindrome/ferric-fred A strongly-typed, single-binary MCP server for FRED (Federal Reserve Economic Data), written in Rust. | |
| Pipedrive MCP Server agranig/pipedrive-mcp-server Enables AI assistants to analyze Pipedrive sales pipeline, deal velocity, and activity engagement, helping sales teams understand where deals are stalling. | |
| memex agrant522/memex Enables AI coding agents to save and recall atomic knowledge cards with bidirectional links across sessions, sharing a markdown-based memory store across MCP clients without a vector database. | |
| Carla MCP Server agrathwohl/carla-mcp-server Enables complete control over the Carla audio plugin host through natural language, providing 45 tools across session management, plugin control, audio routing, parameter automation, and real-time analysis for professional audio production | |
| SuperCollider MCP Server agrathwohl/supercollider-mcp Model Context Protocol (MCP) server for SuperCollider integration with Claude Code and other MCP clients. | |
| Room MCP agree-able/room-mcp A command-line tool that enables the use of MCP with the Room protocol, allowing agents to create and interact in peer-to-peer virtual rooms for goal-oriented collaboration. | |
| Agrenting MCP Server agrenting/agrenting-codex-plugin Enables hiring remote marketplace agents from Codex using a scoped API key, with tools for creating hirings and checking their status. | |
| elasticsearch7-mcp agrica/elasticsearch7-mcp Enables MCP clients to connect to and interact with Elasticsearch 7.x clusters through natural language, supporting search, indexing, mappings, templates, cluster health, and optional diagnostic or destructive tools. | |
| WP MCP Ultimate agricidaniel/wp-mcp-ultimate A self-contained MCP server plugin that connects WordPress to AI, providing 58 abilities for managing posts, pages, media, users, plugins, menus, comments, and more through any MCP-compatible AI client. |
24,601–24,650 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.