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 |
|---|---|
| Semantic Scholar MCP Server briansasaki/semantic-scholar-fastmcp-mcp-server Enables querying academic papers, author profiles, and citation networks through the Semantic Scholar API. Supports full-text and title search, batch paper and author lookups, citation and reference tracking, and single- or multi-paper reco | |
| wlater MCP Server briansbrian/wlater-mcpserver Provides secure, read-only access to Google Keep notes and lists, enabling AI assistants to search, retrieve, and view your Keep data without modification capabilities. | |
| SSH-MCP Secure brianshih/ssh-mcp-secure This is a secure SSH MCP server providing enterprise-grade SSH management with AI assistance, MFA, RBAC, encryption, and compliance auditing. | |
| Jira MCP Server brianstone/jira-mcp-server An MCP server that enables communication with Jira, allowing users to perform operations like getting, searching, creating, and editing issues through natural language interaction. | |
| cfn-lint MCP Server brianterry/cfnlint-mcp Validate AWS CloudFormation templates using cfn-lint, with tools for validation, version checking, and automatic upgrades. | |
| 365rwa RWA Data MCP Server briantian818/365rwa-x402-mcp Enables AI agents to fetch machine-readable real-world asset tokenization data—including project verification verdicts, scored projects, issuances, licences, regulatory updates, and market snapshots—through x402 per-call paid, read-only MCP | |
| rentgpu GPU Market MCP briantian818/rentgpu-x402-mcp Enables agents to query real-time GPU rental prices across 26 platforms, including current lowest quotes, 30-day price history, market movers, platform reliability, and task/budget recommendations. Access is read-only and metered per call v | |
| Paprika MCP Server briantkatch/paprika-mcp Enables AI assistants to search, read, and update recipes in Paprika Recipe Manager, allowing natural language interaction with your recipe collection including ingredients, directions, and metadata. | |
| Claude IPC MCP brianveenstra03786/claude-ipc-mcp Enables AI assistants on different platforms and sessions to exchange persistent messages with each other through simple natural language commands. Supports instance registration, message sending, and inbox checking without any coding. | |
| Sonatype MCP Server brianveltman/sonatype-mcp A Model Context Protocol (MCP) server for Sonatype Nexus Repository Manager that enables AI assistants to interact with Nexus repositories through a standardized interface. | |
| ecobee-mcp brianvia/ecobee-mcp-cloudflare-workers Reads thermostat status and controls HVAC modes, holds, schedules, comfort sensors, settings, vacations, fan runtime, and on-screen messages for a single thermostat account, hosted remotely on Cloudflare Workers with bearer-protected, state | |
| erank-mcp-cloudflare-workers brianvia/erank-mcp-cloudflare-workers Enables keyword research, listing audits, and shop data from eRank through read-only MCP tools, including keyword metrics, related searches, Etsy tags, top listings, bulk keyword analysis, listing audits, shop info, and connected shops. | |
| fcpl-mcp brianvia/fairfax-county-public-library-mcp-cloudflare-workers Enables a Fairfax County Public Library patron account to search the Polaris catalog, read checkouts, holds, and account details, and place or cancel physical-item holds through a remote MCP endpoint. | |
| hatch-sleep-mcp-cloudflare-workers brianvia/hatch-sleep-mcp-cloudflare-workers Enables reading and controlling supported Hatch Rest sound machines, including managing devices, favorites, sounds, lights, volume, clock, and toddler lock through MCP. | |
| oura-mcp-cloudflare-workers brianvia/oura-mcp-cloudflare-workers Enables MCP clients to query Oura Ring health data, including sleep, readiness, HRV, activity, and SpO2, through OAuth2-authenticated tools running on Cloudflare Workers. | |
| tonal-mcp-cloudflare-workers brianvia/tonal-mcp-cloudflare-workers Enables querying a Tonal fitness account for workout history with per-set weights, muscle readiness, strength scores, and lifetime stats through a remote MCP endpoint. | |
| wegmans-mcp-cloudflare-workers brianvia/wegmans-mcp-cloudflare-workers Enables users to search grocery products and stores, manage a cart, sync purchase history, and predict needed items through MCP tools. It also stores food preferences as server instructions so connected agents can respect them automatically | |
| Taskade MCP Server brianzakharov48550/mcp Enables AI assistants and IDEs to manage workspaces, projects, tasks, and AI agents through natural language, including creation, updates, completion, assignment, and automation. It also supports generating MCP tools from arbitrary OpenAPI | |
| MediaWiki MCP Server brianzakharov48550/mediawiki-mcp-server Enables LLM clients to read, search, create, update, delete, move, protect, and upload content on any MediaWiki wiki through MCP tools and resources. It also supports wiki management, OAuth, and extension-specific queries for NeoWiki, Seman | |
| sparkmedic-mcp brianzavareh/sparkmedic Enables AI assistants to perform automated root-cause analysis of slow Apache Spark and Databricks jobs by listing applications, planning and running diagnoses, retrieving stage and SQL plan details, and listing diagnosis rules via read-onl | |
| CVE-Search MCP Server bricci571/cve-search_mcp Enables querying the CVE-Search API to browse vendors and products, retrieve CVEs by ID, list recent CVEs with CAPEC/CWE/CPE expansions, and check database update status. | |
| AnythingMCP bricefpv-lab/oriq-anythingmcp-fork A self-hosted MCP gateway that turns REST, SOAP, GraphQL, and SQL endpoints into MCP tools, enabling AI clients like Claude and ChatGPT to interact with legacy and modern APIs without code changes. | |
| Roster brickshubkuwait/roster-cli-mcp Enables querying your team's work (stats, overdue, workload, active members, etc.) via natural language, scoped to your department with read-only signed-token access. | |
| Mobbin Remote MCP Server bridevmx/mobbin-mcp-server A Docker-ready MCP remote server that connects MCP clients like OpenCode to the Mobbin REST API using API keys, enabling access to Mobbin app design patterns and data without OAuth. | |
| pre820-mcp-server bridgetek/pre820-mcp-server Enables AI-assisted Pre820 EVE development by indexing EveApps samples and APIs to provide sample discovery, API guidance, scaffold generation, code validation, and build command generation. | |
| MCP Serverless Functions Example bridgpal/mcp-test-2 A basic example of developing and running serverless Model Context Protocol (MCP) using Netlify Functions, demonstrating how to deploy and access serverless functions with customized URLs. | |
| brief-mcp brief-md/brief-mcp MCP server for BRIEF.md that captures decisions, constraints, and questions during AI chats, enabling seamless project re-entry across different AI tools. | |
| codex-telegram briejhxh/codex-telegram Enables local, privacy-first control of a personal Telegram account through MCP, using TDLib to read chats, send and reply to messages, search, transfer files, and interact with approved inline buttons. | |
| podcast-generator brienalkire/podcast_generator Enables an AI client to write, queue, convert, and monitor markdown podcast scripts into spoken-word audio locally using the same configured folders and environment. | |
| Kibana Dashboard Builder brienhackney/kibana-mcp-server Enables AI agents to create and manage Kibana dashboards, Lens visualizations, and data views via the Kibana Saved Objects API. It allows for programmatically listing existing resources and assembling new visualizations into dashboards thro | |
| The Web MCP bright-cn/brightdata-mcp Enables AI assistants to access real-time web data through search, markdown scraping, and browser automation while bypassing anti-bot protections. It provides tools for web research, e-commerce monitoring, and data extraction from across th | |
| ansim-gil-dongmu brightalot/ansim-gil-dongmu-mcp An MCP server that reviews routes for elderly and disabled pedestrians, checking station accessibility and providing safer alternatives. | |
| music21-mcp-server brightlikethelight/music21-mcp-server A multi-interface music analysis server providing MCP, HTTP, CLI, and Python interfaces for music21-based analysis. | |
| NetworkX MCP Server brightlikethelight/networkx-mcp-server Comprehensive Model Context Protocol server for advanced graph analysis using NetworkX, enabling graph creation, manipulation, and algorithm execution through natural language. | |
| mcp-server-say-hello brightlin/mcp-server-say-hello-py MCP server that provides a greeting tool to say hello to users. | |
| terraform-docs brightredchilli/terraform-docs Provides hybrid (BM25 + vector) search over Terraform AWS and Google provider documentation, with tools for ranked search and full document retrieval. | |
| Bright Security MCP brightsec/mcp The new Bright MCP Server enables AI assistants to directly interact with Bright and manage security scans end-to-end.
Using natural language prompts, AI can now analyze existing coverage, identify missing or hidden entrypoints, add them t | |
| airc-mcp brightseth/airc-mcp Connect Claude Code to other AI agents for messaging, registration, presence, and capability discovery. | |
| rsbuild-plugin-vue-mcp brightx/rsbuild-plugin-vue-mcp This server runs inside an Rsbuild or Rspack dev server to expose MCP tools for inspecting and editing live Vue component state, component trees, Vue Router info, and Pinia stores. | |
| flompt brigitte14440/flompt Enables decomposing raw prompts into structured, typed blocks and compiling them back into Claude-optimized XML prompts directly inside Claude Code conversations. Also exposes the available block types and their recommended ordering for man | |
| Remote MCP Server with Azure Functions (Python) brigittea28/remote-mcp-functions-python Publishes sample Python implementations that expose tools such as snippet CRUD, QR code generation and batch operations, resources, and prompts like code review checklists and doc generation, plus an interactive weather app, to MCP clients. | |
| fcp-mcp-server brigittel69/fcp-mcp-server Enables Claude to read, edit, and generate real Final Cut Pro timelines through FCPXML, covering cut detection, markers, roles, transcript-based editing, rough cuts, keyframes, speed curves, cross-NLE export, and direct pushes into a runnin | |
| Academic Paper Search MCP Server brigitteo2857/academic-search-mcp-server Enables LLMs and compatible clients to search for and retrieve academic paper information, including metadata, abstracts, and available full text, from Semantic Scholar and Crossref through MCP tools. | |
| AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server brigittepatel0498/aws-cost-explorer-mcp-server Enables querying AWS spend data via Cost Explorer and Amazon Bedrock usage data from CloudWatch logs using natural language. Supports cross-account access, local and remote deployment, and integration with Claude Desktop and LangGraph agent | |
| Typst MCP Server brigitteunal/typst-mcp Enables AI models to interact with the Typst typesetting system by converting LaTeX to Typst, validating Typst syntax, retrieving documentation chapters, and rendering Typst code to PNG images. | |
| mcp-translate brigsd/mcp_translate An MCP server that translates user messages from Portuguese to English and Claude's responses back to Portuguese, reducing token costs by processing only English with Claude. | |
| mcp-ia-web brigsd/mcp-ia-web MCP server that provides AI access to a local terminal, enabling command execution, directory navigation, and system operations with persistent session state. | |
| mcp_starter_project brijeshp09/mcp-learning This MCP server powers a chat CLI for Claude or Gemini, letting users reference local documents by ID and execute MCP prompts through natural language. | |
| pptx-mcp brijeshshetty/pptx-mcp A local MCP server for Claude to create, edit, and export PowerPoint presentations on Windows, with support for SAP corporate templates and full auditing. | |
| Meta Marketing API MCP Server brijr/meta-mcp Enables AI assistants to manage Facebook and Instagram advertising via the Meta Marketing API. It provides comprehensive tools for campaign lifecycle management, performance analytics, audience targeting, and creative optimization. |
35,601–35,650 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.