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 |
|---|---|
| Salesforce MCP Server abhishek-kumawa/mcp Enables AI agents to manage Salesforce leads and permission sets via the MCP protocol. | |
| AI Sales Analytics MCP Server abhishek-maheshwari-778/_my_mcp_server Automates sales data analysis by cleaning CSV, generating AI insights, creating interactive HTML dashboards, exporting PDF reports, and emailing them, all via MCP tools and multi-model AI fallback. | |
| Atlassian MCP Server abhishek249/atlassian-mcp-server Enables AI assistants to manage Jira issues and Confluence pages, including creating, updating, searching, commenting, and transitioning work items through natural language. | |
| proofline-mcp abhishek249/gavel-mcp Enables AI agents to validate candidate data pipelines against a trusted reference, running deterministic checks and returning evidence reports through MCP. | |
| SIFTAgent abhishek2f24/siftagent An MCP server that transforms Claude Code into an autonomous DFIR analyst by providing typed, audited forensic tools for disk, memory, timeline, registry, and IOC analysis on the SANS SIFT Workstation. | |
| Contentstack App MCP Remote Server abhishek305/contentstack-app-mcp-remote Enables remote access to Contentstack App MCP tools over HTTP, deployable to platforms like Vercel or Contentstack Launch. | |
| Weather MCP Server abhishek3689/weather_mcp_server Enables AI assistants to fetch real-time weather data, forecasts up to 10 days, and compare weather conditions between cities using WeatherAPI.com with support for both Celsius and Fahrenheit units. | |
| BRAINS MCP Server abhishek42638/brains Provides MCP tools for lead qualification, enabling evidence gathering from CRM, scoring, and knowledge base with role-based access and deterministic decision gating. | |
| NVIDIA NIM MCP Server abhishek4512009/mcp Enables local task execution using the user's NVIDIA NIM API quota, with tools to process file contents through LLMs, send chat prompts, and list available models. | |
| openstack-mcp abhishekambad-leapswitch/openstack-mcp Enables AI assistants to inspect and manage OpenStack clouds, including listing instances, checking quotas, and retrieving console logs. It supports opt-in write operations for creating and deleting servers, with a read-only default. | |
| moss-image abhishekaryan23/moss-image-mac Enables local text-to-image generation on Apple Silicon Macs through any MCP app, with reliable text rendering, bounding-box layout placement, inpainting and image-to-image edits, and transparent cutouts. Images are returned inline and save | |
| VCF Enterprise MCP abhishekaryan23/vcf-ent-mcp Lets AI assistants operate VMware Cloud Foundation 9.x environments (SDDC Manager, vCenter, NSX, VCF Operations, and experimental Automation/Orchestrator) without exposing VCF credentials or raw infrastructure APIs to the language model. It | |
| mcp-server-code-assist abhishekbhakat/mcp_server_code_assist A Model Context Protocol server that provides tools for code modification and generation via Large Language Models, allowing users to create, modify, rewrite, and delete files using structured XML instructions. | |
| phone-a-friend-mcp-server abhishekbhakat/phone-a-friend-mcp-server Enables AI-to-AI consultation for critical thinking and complex reasoning via OpenRouter, allowing one AI to delegate tasks to another AI model. | |
| Family Caretaker MCP Agent abhishekingle9090-debug/family-mcp Enables caregivers to check home supply inventory and available delivery slots, then book a delivery only after explicit confirmation, with bookings persisted in a cloud database so they survive restarts. It also lists existing appointments | |
| Sonic Pi MCP abhishekjairath/sonic-pi-mcp A Model Context Protocol server that allows AI assistants like Claude and Cursor to create music and control Sonic Pi programmatically through OSC messages. | |
| MCP Learning Server abhishekmishra06/mcp-learning-server A beginner-friendly MCP server built in plain Node.js/JavaScript that exposes five tools (calculator, UUID generator, read notes, get weather, password generator) to teach how the Model Context Protocol works under the hood. | |
| LiteLLM MCP Server Bridge abhishekmore-1/litellm-proxy-mcp Connects Antigravity to a LiteLLM instance, enabling chat completions, model listing, health checks, and more via the Model Context Protocol. | |
| Appium MCP Server abhishekmprovoke/mobile-mcp Enables AI-powered mobile app testing and automation through Appium, using Azure OpenAI to intelligently navigate mobile applications and generate test cases. | |
| Postman MCP Generator abhishekms1047/postman-mcp-server Generates MCP servers from Postman API requests, automatically creating JavaScript tools that enable LLMs to interact with any API documented in Postman collections. Supports authentication configuration and deployment via STDIO or SSE. | |
| MCP Real Estate Intelligence Server abhishekpendyala06/mcp-real-estate-intelligence Provides comprehensive real estate market intelligence, property valuation, and investment analysis for AI agents. Unifies data from multiple sources like Zillow, Redfin, and public records into a single MCP interface. | |
| agent-comms abhishekq10/agent-comms Enables agents to communicate asynchronously via private inboxes and to ask a human a question and block until answered. Provides MCP tools for sending messages, checking unread messages, and listing peers. | |
| VulScan-MCP abhishekrai43/vulscan-mcp MCP server that scans project dependencies for security vulnerabilities (CVEs) and provides fix instructions directly in VS Code via Copilot. | |
| Weather-MCP-Server abhishekraj0037/weather-mcp-server Provides weather intelligence as MCP tools (current weather, forecast, air quality, UV index, alerts) with agentic orchestration, memory, and citation-grounded RAG. | |
| Motion.dev MCP Server abhishekrajpurohit/motion-dev-mcp Provides AI assistants with comprehensive access to Motion.dev animation library documentation and code generation tools. Enables LLMs to generate Motion animations for React, JavaScript, and Vue with proper documentation backing and framew | |
| Analytics MCP abhishekshankar/mcp-metrics Automates Google Analytics 4 and Google Tag Manager setup, management, and health monitoring with blueprints, multi-environment support, and MCP tools for AI agents. | |
| Databricks MCP Server abhisheksharma637/databricks_mcp Enables AI agents to access enterprise data from Unity Catalog (vector search, functions, Genie spaces) and perform developer actions in Databricks like managing notebooks and running jobs. | |
| ext_ZavaSupportDemo abhisheksinghcs/a365mcptest Demonstrates Agent 365's bring-your-own-MCP flow by enabling natural-language search of a Zava IT support knowledge base, retrieval of support ticket statuses, and creation of new support tickets. | |
| Dialtone Watcher abhisheksinha1506/mcp Enables local, offline inspection of computer activity by collecting visible process, connection, and automatic-launch metadata and letting MCP clients explain rule matches and process context. It is read-only toward processes and system se | |
| MCP From-Scratch Implementation abhisheksonsale/mcp_implementation Enables learning and integration testing of the Model Context Protocol by evolving from a minimal server toward production-grade tools, resources, prompts, and agent interoperability. | |
| mcp-server abhisheksonsale/mcp-sdk-implementation A minimal MCP server built with the official Python SDK that runs over stdio and exposes a health capability, providing a practical integration-testing target for AI and agent codebases. | |
| agent-fastpath abhishekswe/agent-fastpath Enables coding agents to offload quick judgment calls like shipping readiness, file triage, and claim verification to a fast local MCP server with calibrated confidence and safe fallbacks. | |
| pdf-agent-toolkit-mcp abhishektangudu/pdf-toolkit-mcp Enables AI agents to perform comprehensive PDF operations locally, including compression, text extraction, PII redaction, page organization, splitting, merging, watermarking, creation, and form filling, all without cloud uploads. | |
| OpenSCAD MCP Server abhishekv87bit/openscad-mcp Enables AI assistants to render 3D models by providing tools to execute OpenSCAD code and generate single or multi-perspective views. It returns high-quality PNG renderings directly to LLM applications for visual feedback and 3D model visua | |
| Broker abhishekvoid/broker-mcp Enables AI agents to securely perform privileged actions like creating GitHub issues by minting short-lived, single-purpose tokens on demand, with policy enforcement and audit logging. | |
| AccessLens MCP abhishekx-dev/accesslens-mcp Enables accessibility auditing of rendered pages with multi-engine evidence, human-in-the-loop review, and fix verification across agent sessions. | |
| Remote MCP Server (Authless) abhisheky495/test-mcp-server Deploys a remote MCP server on Cloudflare Workers without authentication, enabling connection to Cloudflare AI Playground and Claude Desktop. | |
| Repo Recap abhishrek07/repo-recap Enables Claude to query GitHub repositories in plain English, fetching recent activity, release notes, issue triage, and health summaries via the GitHub API. | |
| PantryPilot abhisuman2001/pantrypilot-alexa-mcp This MCP server gives Alexa+ a persistent household pantry and Bedrock-generated recipes that use the soonest-expiring food first, with tools for adding and using items, listing the pantry, checking expiring soon, and suggesting recipes. | |
| Activity Log MCP Server abhiteksingh-stfox/save-mcp A persistent activity log server that allows MCP-compatible AI assistants to log events, decisions, and system logs over HTTP, with a built-in web dashboard for monitoring and searching logs. | |
| Sandbox MCP abhiteshpundir/sandbox-mcp Enables AI coding agents to safely run commands, install dependencies, test, and modify code inside disposable, policy-enforced Docker sandboxes isolated from the host, returning results and diffs. | |
| Gmail MCP Server abhitkumar89/gmail_mcp_tool MCP server that lets AI assistants send, read, and manage Gmail through natural language, including email sending, inbox management, and template-based outreach. | |
| myday-mcp abhitsian/myday Enables AI assistants to query a user's recorded work sessions, notes, and browsing history, allowing them to resume tasks or answer questions about past work without re-explanation. | |
| OneNote-MCP-For-GeminiSpark abhivishwa2/onenote-mcp-for-geminispark A robust MCP server that transforms OneNote notebooks into an AI-accessible knowledge base for Gemini Spark, enabling natural language queries to list, read, and search notes via Microsoft Graph API. | |
| img-vid-mcp abhixnav0x1x/img-vid-mcp Enables AI agents to search the web for images and videos, download them into website projects with automatic optimization, and receive paste-ready HTML snippets, all self-hosted and without API keys. | |
| Todoist MCP Server abhiz123/todoist-mcp-server An MCP server that integrates Claude with Todoist, enabling natural language task management including creating, updating, completing, and deleting tasks. | |
| mcp-memory-hnsw abho7/mcp-memory-server Provides persistent semantic memory for Claude Code and Claude Desktop with fully offline local embeddings and HNSW indexing, enabling memory storage, semantic search, listing, and deletion across sessions. | |
| Solo Desktop Commander MCP abhradeepnet2026/solo-commander-mcp- A free, open-source MCP server that gives AI agents real filesystem, terminal, git, and process control over your machine for inspection, diagnosis, and repair. | |
| Self-Learning MCP abhraweb-boop/self-learning-mcp An MCP server that gives AI coding assistants durable long-term memory, reusable skills, and evidence-based decision intelligence, running fully offline with no external API keys. | |
| claude-chat-connecter abhubx/claudechatconnecter Enables exporting a conversation as a shareable code and importing it into another chat — even one on a different account — so the full context, code and decisions carry over and work can resume where it left off. |
23,151–23,200 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.