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 |
|---|---|
| Rundeck MCP Server dinfiesta/rundeck-mcp Enables AI assistants to manage Rundeck automation platform, including project and job management, execution, and system monitoring through the MCP protocol. | |
| HFSS FSS MCP Server ding-cha/hfss-fss-mcp Enables AI clients to control local Ansys HFSS for modeling FSS, metasurfaces, and periodic structures, including periodic boundaries, Floquet ports, geometry transforms, arrays, simulation setups, and results export. | |
| lowlevel-computer-use-mcp ding-ding-projects/lowlevel-computer-use-mcp Enables MCP agents to automate real GUI applications on headless desktops, providing background mouse/keyboard control, window/process management, screenshots, and safe human handoff without disturbing the user's desktop. | |
| dingdawg-governance dingdawg/governance-sdk Universal governance layer for AI agents — MCP-native,
fail-closed, LNN interpretability. Governed receipts, IPFS audit proofs, and
rollback for any agent in any framework. | |
| Faultline dingdongkkk/faultline Enables MCP-compatible AI coding agents to obtain clean failing-test context, ranked suspect lines, runtime value comparisons, bounded code search, and patch verification so they can fix Python test failures with fewer tokens. | |
| TOS MCP Server dinghuazhou/sample-mcp-server-tos Enables natural language exploration and management of Volcengine TOS storage, allowing users to list buckets, browse objects, and retrieve file contents. It supports content retrieval for various data types including text, images, and vide | |
| quick-shell dinglebear-ai/connexin Enables human-approved SSH terminal sessions and confined SFTP file operations for SSH-configured devices, with user-controlled terminal and file explorer. | |
| payroll-normalizer-mcp dingxiang-me/payroll-normalizer-mcp Enables AI tools to normalize messy payroll spreadsheets (xlsx/xls/csv) into a standardized 10-column template for social insurance calculation, with automatic column detection, net-to-gross conversion, and cross-entity/month merging. | |
| pubmed-proxy-mcp dingyifei/pubmed_proxy_mcp MCP server for NCBI PubMed E-utilities with rate limiting, enabling article search, metadata retrieval, full-text access, BibTeX generation, and bibliography management. | |
| Yahoo Fantasy Baseball MCP Server dingyiyi0226/fantasy-baseball-mcp Manage your Yahoo Fantasy Baseball team via Claude — check rosters, scout free agents, set lineups, and pull advanced stats from Baseball Savant, FanGraphs, and MLB Stats API. | |
| MCP Apple Notes dingzeefs/mcp-apple-notes A Model Context Protocol server that enables semantic search and retrieval of Apple Notes content, allowing AI assistants to access, search, and create notes using on-device embeddings. | |
| Tripo CN MCP Server dingzhenyao/tripo-cn-mcp Integrates Tripo China's 3D AI generation capabilities into the MCP ecosystem, enabling AI agents to create 3D models from text or images, manage tasks, and perform animation pipelines. | |
| Filesystem MCP Server SSE dinh-ai-system-exe-com-vn/file-system-mcp-see Node.js server implementing Model Context Protocol (MCP) for filesystem operations, allowing AI systems to read, write, edit files and manage directories within specified allowed paths. | |
| tradingview-chart-mcp dinh4995/tradingview-chart-mcp Enables fetching chart snapshots for any ticker and timeframe, with browser pooling for efficient concurrent requests and built-in performance statistics. | |
| ChatGPT Web MCP dinhthangqt/chatgpt-web-mcp-hermes Enables MCP clients like Codex to operate chatgpt.com through a dedicated persistent browser profile, allowing chat creation, project management, prompt submission, file uploads, and response reading without using the ChatGPT API. | |
| Loometo dinimiciuillabs-cloud/loometo Enables AI coding agents to visually build and run AI generation pipelines on a canvas by adding, wiring, and executing nodes via MCP tools. | |
| Carbono dinnger/mcp-carbono Enables AI to generate images by describing them with HTML using Tailwind CSS and DaisyUI, which are rendered to PNG images. | |
| Web Toolkit MCP dino-996/web_toolkit_mcp Enables local LLMs to perform real-time web searches, scrape static and dynamic pages, extract HTML tables via headless Chromium, and check HTTP status, with safeguards against SSRF and prompt injection. | |
| Obsidian MCP Server dino-quadrivia/obsidian-mcp Lets Claude save conversations, notes, and structured summaries directly to your Obsidian vault. Supports YAML frontmatter, auto-backlinks, daily notes, and vault search. | |
| Finance MCP Server dino65-dev/finance_mcp-server Provides real-time financial data from Yahoo Finance to Large Language Models through the Model Context Protocol, enabling AI models to access stock prices, historical data, and company information. | |
| sharebit-mcp dinoquinten/sharebit-ai-mcp Enables a coding agent to create, list, and read ShareBit pastes over the Model Context Protocol, with no shell, filesystem, or credential-admin access. | |
| Google Cloud Run MCP Server (SSE) dinosbakerype/google-cloud-mcp-server Enables deployment of a Model Context Protocol server with SSE transport on Google Cloud Run for integration with Antigravity. | |
| OpenMailConnect dinq-labs/openmailconnect Enables connecting your own Gmail or SMTP mailbox and managing email through tools for sending, replying, searching, reading threads, and creating drafts. | |
| openpeoplerouter dinq-labs/openpeoplerouter Enables people and company discovery, enrichment, identity resolution, and contact finding through unified MCP tools, with optional provider endpoint catalog access using your own API keys. | |
| Weather MCP Server dinuka-kasun-medis/weather Provides weather alerts and forecasts via the National Weather Service API, enabling Claude to answer weather-related queries. | |
| RecurPost MCP Server dinwal/recurpost-mcp Provides AI assistants with access to the RecurPost API to manage social media accounts, schedule posts, and organize content libraries. It enables users to automate recurring posts, track engagement metrics, and generate social media conte | |
| discord-bot-mcp diocata/discord-bot-mcp A local MCP server that lets AI clients control a Discord bot via Discord's REST API, offering messaging, administration, and moderation tools. Includes safety features such as guild scoping, allowlists, and opt-in write permissions. | |
| ExoSense MCP Server diodechain/exosense-pymcp Enables interaction with ExoSense IoT devices, sensors, groups, and assets via GraphQL, supporting device management and data queries through a Model Context Protocol interface. | |
| DillyDallyMCP diodide/dillydallymcp A basic Model Context Protocol server template ready for Dedalus deployment, demonstrating MCP server structure with a simple integer addition tool. | |
| Broker-mcp diofthecr3ed/broker-mcp Read-only MCP server that connects a Broker trading account to AI clients, providing account data, positions, orders, and market data via 21 tools, with a mock sandbox mode for evaluation. | |
| zrok-mcp diogenesoftoronto/zrok-mcp Enables AI agents to manage zrok tunnels, shares, and access programmatically through environment management, share creation/deletion/listing, and access control actions. | |
| MCP Tree-sitter Server diogo-rp-menezes/mcp-tree-sitter-new Enables AI clients to analyze codebases through Tree-sitter (WASM) by exposing tools for AST and symbol inspection, structural queries, reference and dependency lookup, complexity and code-similarity analysis, and project registration with | |
| MCP Tree-sitter Server / Studio diogo-rp-menezes/poc-mcp-tree-sitter Enables MCP clients to register projects and analyze source code through Tree-sitter WASM parsing, exposing tools for AST and symbol extraction, custom queries, reference finding, complexity and similarity analysis, dependency discovery, an | |
| IPMA MCP Server diogoazevedo03/ipma-mcp-server Provides access to Portuguese weather data from IPMA (Instituto Português do Mar e da Atmosfera), including weather forecasts, meteorological warnings, seismic data, UV index, and real-time observations from weather stations across Portugal | |
| fisicai diogodebastos/fisicai MCP server providing tools for high-energy physics: literature search (INSPIRE-HEP, arXiv), data access (HEPData), and statistical analysis (pyhf likelihoods) for reinterpreting LHC searches. | |
| openapi-mcp diogofabri/openapi-mcp Turns any OpenAPI 3.x spec into an MCP server that exposes one validated tool per API operation, so AI agents can discover and call a REST API over stdio or Streamable HTTP. It is read-only by default, with allow/deny lists, environment-bas | |
| Hey Harper multi-store Shopify MCP server diogoferacruz-dev/heyharper-shopify-mcp-server A remote MCP server that aggregates unfulfilled and needs-attention orders across all five Hey Harper Shopify stores in one connection, using permanent Admin API tokens to avoid per-store OAuth re-authentication. | |
| quick-tts-mcp diogoseca/quick-tts-mcp Provides text-to-speech functionality using OpenAI's TTS API, enabling text-to-speech conversion, voice listing, and model listing. | |
| Packet Tracer MCP diomedesmateo/packet-tracer-mcp Enables AI agents to plan, create, and control Cisco Packet Tracer network topologies in real time, including deploying devices and cabling, configuring IPs and IOS CLI, and querying or clearing topologies through an HTTP bridge. | |
| MCP Server for Spinnaker dion-hagan/mcp-server-spinnaker A Model Context Protocol server implementation that allows AI models to interact with and manage Spinnaker deployments, pipelines, and applications through a standardized interface. | |
| SimpleCalculator MCP Server dionbenfernandes-dev/simplecalculator-using-mcp-server---docker Enables arithmetic operations (add, subtract, multiply, divide) through a custom Model Context Protocol implementation, containerized with Docker for easy deployment. | |
| MAGDA-MCP dionysusdwi/magda-mcp Enables MCP clients to connect to a running MAGDA instance over stdio and access its native composition tools, resources, and resource templates, while providing instance discovery, fixed-instance connection, credential recovery, diagnostic | |
| Atom of Thoughts dioptx/mcp-atom-of-thoughts Structured reasoning MCP server that decomposes problems into atomic steps (premise, reasoning, hypothesis, verification, conclusion) with confidence scoring, live visualization, and approval feedback. | |
| web3-docs dioptx/web3-docs Unifies 11 protocol specification repositories (EIPs, BIPs, CIPs, etc.) and canonical contract addresses across 10 chains into a local FTS5 index, enabling coding agents to retrieve exact spec text and contract addresses via natural languag | |
| promem-mcp dip-ro/mcp_package Enables AI coding agents to maintain persistent project context, including rules, decisions, environment intelligence, and Git history, using a local-first MCP server with automatic project detection and token-efficient retrieval. | |
| AgentSync MCP Server dipakkr/agentsync Provides MCP tools for AI coding agents to coordinate on shared repositories, enabling task claiming, conflict detection, and plan management in real-time. | |
| iceberg-mcp-server-trino dipankarmazumdar/iceberg-mcp-server-trino Model Context Protocol server for read-only access to Iceberg tables through Cloudera Trino: schema discovery, SQL queries, metadata-based health checks, time travel, and performance analysis. | |
| Sahmk MCP dipesh1917/sahmk-mcp Enables AI agents to access Saudi market data, including company profiles, market details, and historical data from Tadawul, through the MCP protocol. | |
| Meraki MCP Server dipeshmaindolia001/meraki-mcp-server-testing Provides role-based access to the Cisco Meraki Dashboard API via MCP, enabling management and monitoring of Meraki networks, devices, firmware, and licenses through natural language tools. | |
| Scopus MCP Server diplococcus94/scopus-mcp-server Scopus MCP Server enables researchers to interact with the Scopus database through natural language. It provides tools for searching documents, fetching abstracts, finding author profiles, and viewing citation overviews. |
44,801–44,850 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.