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 |
|---|---|
| @erplinker/bigcommerce-mcp ackm04/bigcommerce-mcp Provides AI assistants with comprehensive, precise BigCommerce developer documentation via 12 MCP tools, including REST endpoints, GraphQL operations, webhooks, OAuth scopes, and code examples. | |
| Fetch JSONPath MCP ackness/fetch-jsonpath-mcp Enables efficient extraction of specific data from JSON APIs using JSONPath patterns, reducing token usage by up to 99% compared to fetching entire responses. Supports single and batch operations for both JSON extraction and raw text retrie | |
| ach-memory ackstorm/ach-memory Enables coding agents to govern and access memory engines over MCP, with scoped read/write permissions, journaling, secret scrubbing, and bounded context delivery at session start. | |
| aclclouds acl-cloud/aclclouds-cli Runs locally over stdio to expose tools for listing services, controlling power, reading logs and console output, managing files and backups, and deploying directories or transferring files between your machine and your servers. It acts wit | |
| cursor-eff aclermont318-sys/cursor-eff A local MCP server that improves token efficiency for Cursor's agent by providing cheaper tools like search_code, outline_file, read_snippet, project_map, and handoff, along with rules that steer the agent to use them and reduce excessive c | |
| MCP Inspector Server acnlabs/mcp-inspector-server A basic MCP server template that provides a foundation for building custom tools, resources, and prompts. Serves as a starting point for developers to create their own MCP server functionality. | |
| OmniTaskAgent acnlabs/omnitaskagent A multi-model task management system that enables intelligent task creation, decomposition, status tracking, and dependency management through natural language, with support for integration into editors via MCP protocol and connection to va | |
| graphite-art-mcp acoci86/graphite-art-mcp Enables Claude and other MCP clients to create and edit vector artwork inside a running Graphite editor, turning SVG into fully editable native layers and supporting export, styling, transforms, selection and layer management. Every operati | |
| Compass MCP Server acogley313/compass-mcp Enables Claude to run SQL queries against Infor Compass (Data Fabric) directly from chat, with automatic export of large result sets to Excel. | |
| Parking Information MCP Server acorn025/parking-mcp2 Enables querying parking lot information through an MCP server built with fastMCP, allowing users to retrieve parking facility data via API calls. | |
| Terminal MCP Server acosx/terminal-mcp-server Enables executing shell commands on the host system via an MCP tool, with JWT/OAuth authentication and audit logging for secure remote access. | |
| TheirCare MCP acousland/theircare-mcp Enables an AI assistant to read bookings, check availability and session conditions, and prepare unsaved booking, cancellation or waitlist previews for a TheirCare / FullyBooked account through a local stdio MCP connection. Final saving and | |
| Executor Cloudflare MCP Server acoyfellow/executor-cloudflare Deploys an open-source integration layer for AI agents (Executor) to Cloudflare, providing a private MCP endpoint secured by Cloudflare Access, with D1 database, R2 storage, and Durable Objects for session management. | |
| jev-code-mode acoyfellow/jev-code-mode Lets agents run a small JavaScript program in a sandboxed worker that composes typed Jev judgments — claim checking, text screening, best-item picking, label classification, passage comparison, and yes/no questions — in a single call, retur | |
| mcpu acoyfellow/mcpu MCP server for managing Cloudflare Workers via Cloudflare Artifacts. Enables editing, committing, and deploying worker scripts directly. | |
| mcp-server-mssql acpepper/mcp-server-mssql A Model Context Protocol (MCP) server for Microsoft SQL Server databases, providing secure database operations through a standardized interface. | |
| attend acquiredintelligence/attend Enables MCP clients to receive settled, judged decisions from live event streams and route them as interrupt, queue, note, ask, skip, or wait, so agents wake only when attention is warranted. | |
| IETF RFC MCP Server acquo/ietf-rfc-mcp Provides LLM-based access to IETF documents such as RFCs, Internet-Drafts, STD/BCP/FYI series, and errata through a Model Context Protocol server. | |
| LINE Bot MCP Server (SSE Support) acquo/line-bot-mcp-server-sse Integrates the LINE Messaging API with AI agents via the Model Context Protocol, supporting both stdio and SSE transport protocols. It allows agents to send messages, manage rich menus, and retrieve user profile information for LINE Officia | |
| wc3-tester acroath/wc3-agent-map-editing Enables agents to control Warcraft III instances in the background for automated map testing, including launching and attaching, sending mouse and keyboard input, capturing screenshots, managing LAN games, and gathering crash and log diagno | |
| Acrolinx MCP Server acrolinx/nextgen-mcp A Model Context Protocol server that integrates with the Acrolinx NextGen API to provide advanced text analysis and improvement capabilities to AI assistants like Claude, offering features such as text rewriting, content analysis, and writi | |
| Epicor MCP OSS acroston1/epicor-mcp-oss Enables MCP-compatible assistants to discover tables and fields, run bounded SELECT queries and saved BAQs, resolve dashboards, and search imported documents against Epicor Kinetic, without writing business records. | |
| figma-developer-mcp acrt-eval/figma-context-mcp-315-cr1 Enables AI coding agents such as Cursor to access simplified Figma layout and styling data from file, frame, or group links so they can implement designs more accurately in code. | |
| Framelink Figma MCP Server acrt-eval/figma-context-mcp-315-cr10 Gives AI coding agents like Cursor access to Figma file, frame, and group data, simplifying and translating Figma API responses into concise layout and styling context so designs can be implemented accurately in any framework in one shot. | |
| Framelink Figma MCP Server acrt-eval/figma-context-mcp-315-cr11 Enables AI coding agents to retrieve simplified Figma layout and styling data from files, frames, or groups so they can implement designs in code more accurately. | |
| Framelink Figma MCP Server acrt-eval/figma-context-mcp-315-cr5 Enables AI coding agents such as Cursor to access Figma file, frame, and group data, simplifying Figma API responses into relevant layout and styling context so designs can be implemented accurately in code. | |
| Framelink Figma MCP Server acrt-eval/figma-context-mcp-315-cr7 Enables AI coding agents such as Cursor to fetch, simplify, and translate Figma layout and styling data so they can implement designs accurately in code. | |
| Framelink Figma MCP Server acrt-eval/figma-context-mcp-315-cr9 Enables AI coding agents to access Figma design data, including file, frame, and group metadata, so they can implement designs accurately in code. It simplifies and translates Figma API responses into relevant layout and styling information | |
| Lara Translate MCP Server acrt-eval/lara-mcp-547-cr1 Enables AI applications to perform text translation across numerous language pairs with automatic source-language detection, contextual hints, and custom instructions. | |
| Lara Translate MCP Server acrt-eval/lara-mcp-547-cr10 Enables MCP-compatible AI applications to translate text between many languages, with automatic source-language detection, contextual hints, and custom translation instructions. | |
| Lara Translate MCP Server acrt-eval/lara-mcp-547-cr11 Enables MCP-compatible AI applications to translate text between languages with automatic language detection, contextual hints, custom instructions, and multi-language support. | |
| Lara Translate MCP Server acrt-eval/lara-mcp-547-cr5 Enables AI applications to perform multi-language translations with automatic language detection, contextual hints, and custom instructions through an MCP-compatible interface. | |
| Lara Translate MCP Server acrt-eval/lara-mcp-547-cr7 Enables MCP-compatible AI applications to translate text through the Lara Translate API, with automatic language detection, context-aware translations, and custom instructions. | |
| Lara Translate MCP Server acrt-eval/lara-mcp-547-cr9 Enables AI applications to translate text through the Lara Translate API, with automatic language detection, context-aware translations, and custom instructions. | |
| Pinot MCP Server acrt-eval/mcp-pinot-141-cr1 Enables users to interact with Apache Pinot clusters through Claude Desktop for real-time analytics and metadata exploration. Supports listing tables, segments, and schemas, executing read-only SQL queries, and viewing index and column meta | |
| Pinot MCP Server acrt-eval/mcp-pinot-141-cr10 Enables real-time analytics and metadata queries on an Apache Pinot cluster, including listing tables, segments, and schema info, executing read-only SQL, and viewing index and column metadata through Claude Desktop. | |
| Pinot MCP Server acrt-eval/mcp-pinot-141-cr11 Enables Claude Desktop to explore and query Apache Pinot clusters, listing tables, segments, and schema metadata, running read-only SQL queries, and inspecting index and column-level details for real-time analytics. | |
| Pinot MCP Server acrt-eval/mcp-pinot-141-cr5 Enables real-time analytics and metadata queries on Apache Pinot through Claude Desktop, including listing tables, segments, and schemas, viewing index and column metadata, and executing read-only SQL queries. | |
| Pinot MCP Server acrt-eval/mcp-pinot-141-cr7 Enables Claude Desktop to explore Apache Pinot metadata, list tables and segments, inspect schemas and indexes, and execute read-only SQL queries for real-time analytics. | |
| Pinot MCP Server acrt-eval/mcp-pinot-141-cr9 Enables Claude Desktop users to inspect Apache Pinot tables, segments, schemas, and metadata, and to run read-only SQL queries for real-time analytics. | |
| mcp-server-kubernetes acrt-eval/mcp-server-kubernetes-308-cr1 Enables connection to a Kubernetes cluster to list and manage pods, services, deployments, and nodes, create/delete/describe pods, inspect namespaces, and retrieve logs for debugging. | |
| mcp-server-kubernetes acrt-eval/mcp-server-kubernetes-308-cr10 Enables connecting to a Kubernetes cluster through kubectl context to list and manage pods, services, deployments, nodes, and namespaces, create or delete pods, describe pods, and retrieve logs for debugging. | |
| mcp-server-kubernetes acrt-eval/mcp-server-kubernetes-308-cr11 Enables connection to a Kubernetes cluster to list and manage pods, services, deployments, nodes, and namespaces, including creating, deleting, describing pods and retrieving logs for debugging. | |
| mcp-server-kubernetes acrt-eval/mcp-server-kubernetes-308-cr5 Enables connecting to a Kubernetes cluster to manage it, including listing pods, services, deployments, nodes, and namespaces, creating and deleting pods, describing pods, and retrieving logs for debugging. | |
| mcp-server-kubernetes acrt-eval/mcp-server-kubernetes-308-cr7 Connects to a Kubernetes cluster through the current kubectl context and enables listing, creating, deleting, and describing pods, services, deployments, nodes, and namespaces, plus retrieving logs for debugging. | |
| mcp-server-kubernetes acrt-eval/mcp-server-kubernetes-308-cr9 Connects to a Kubernetes cluster using your current kubectl context, letting an assistant list pods, services, deployments, nodes, and namespaces, create, delete, and describe pods, and pull logs for debugging. It turns everyday cluster man | |
| n8n-MCP acrt-eval/n8n-mcp-72-cr1 Gives AI assistants deep, structured knowledge of n8n's 500+ automation nodes, including their properties, operations, and documentation, so they can build and validate workflows. With n8n API credentials configured, it also lets them creat | |
| n8n-MCP acrt-eval/n8n-mcp-72-cr10 Enables AI assistants to access n8n node documentation, properties, and operations for 535+ workflow automation nodes, and optionally create, update, and execute n8n workflows through the n8n API. Supports building n8n workflows for Claude | |
| n8n-MCP acrt-eval/n8n-mcp-72-cr11 Enables AI assistants to access detailed n8n node documentation, properties, operations, and validation tools, with optional API-based workflow management capabilities. | |
| n8n-MCP acrt-eval/n8n-mcp-72-cr5 Enables AI assistants to access comprehensive n8n node documentation, schemas, operations, and validation tools, and optionally create, update, and execute workflows through the n8n API. |
23,451–23,500 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.