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 |
|---|---|
| StarRocks MCP Server deepajuncker7605/mcp-server-starrocks Enables AI assistants to connect to StarRocks databases for direct SQL execution, schema and metadata exploration, table/database overviews, system metrics access, and Plotly chart generation from query results. | |
| AI Carousel Generator deepak-ai-93/deepak-mcp Enables AI clients to generate premium 4K carousel slides from a single instruction, combining expert copywriting, AI image generation, and premium typography compositing. | |
| memex-mcp deepak-bhardwaj-ps/smriti-mcp A portable memory server for MCP that stores durable memories as markdown files, enabling AI agents to create, search, and organize persistent knowledge. | |
| Advanced MCP HTTP Server deepak31mu/advanced-mcp-host-client-server-app An HTTP-based MCP server that provides filesystem tools and code analysis, enabling LLMs to read, write, list files, and analyze code securely. | |
| Workspace MCP deepak5106/workspace_mcp Enables LLM agents to list Google Drive files, read/write Google Sheets, and query external REST APIs through MCP tools. | |
| Benin OpenData MCP deepak8858/opendata-bj-mcp MCP server to navigate and consume public data from Benin's OpenData portal. | |
| Document Tools MCP Server deepak993/mcp-docs-server MCP server that provides document conversion and processing tools, enabling AI assistants to handle document formats through natural language. | |
| spongebob deepakachu5114/spongebob-mcp Enables agents to turn a JSON content payload into a served, multi-page learning website with interactive sections, and hands back the URL. | |
| Expense Tracker MCP Server deepakbishnoi717/test-remote-mcp-server Enables users to manage expenses with category support, including adding expenses with date, amount, category, and notes, using SQLite for persistence. | |
| fastmcp-fleet deepakdalal1221/fastmcp-fleet Provides a central gateway to 170+ offline mock MCP servers with deterministic fixture-based responses and per-server SQLite state, enabling realistic credential-free agent trajectory testing and multi-step workflow rehearsal. | |
| OffensiveSET deepakdubat/offensiveset Generates realistic, multi-turn penetration testing conversation datasets for training security-focused LLMs. | |
| ServiceNow MCP Server deepakj22/servicenow-mcp-databricks Enables AI assistants and development tools to interact with ServiceNow instances through the Model Context Protocol, supporting incident, change, problem, CMDB, service catalog, knowledge base, and custom table operations. | |
| Knowledge Graph MCP Server deepakjangra239/kgraph Enables fast code analysis and navigation through hybrid semantic search, graph-based relationship tracking, and structure exploration across multiple programming languages with optimized indexing for large codebases. | |
| ServiceNow MCP Server (SSE) deepakjdp/mcpserver-servicenow A browser-accessible Model Context Protocol server that enables AI assistants to manage ServiceNow incidents using Server-Sent Events. It provides comprehensive tools for creating, listing, retrieving, and updating incidents through a type- | |
| expert-answer-mcp deepakji1394/expert-answer-mcp Enables users to ask any question and receive expert-verified answers backed by Gemini. The tool is accessible via Claude Desktop, MCP SDK clients, and a web browser. | |
| Todoist MCP Server deepakjois/todoist-mcp-server-cf A proof-of-concept MCP server that interacts with Todoist using OAuth-based authorization and is deployed on Cloudflare Workers. | |
| Connected Workspace MCP deepakkamboj/connected-workspace-mcp Enables MCP-compatible assistants to search, read, send, and label Gmail messages, manage Google Calendar events and free/busy queries, and read, publish, or delete LinkedIn profile content and posts through explicit tools. It supports sepa | |
| playwright-accessibility-mcp-server deepakkamboj/playwright-accessibility-mcp-server Enables accessibility testing using Playwright and Axe, allowing users to scan URLs, HTML content, and batches for violations, and summarize results. | |
| Color Scheme Generator MCP Server deepakkumardewani/color-scheme-mcp Generates harmonious color schemes for design projects using The Color API, offering eight different palette generation methods including monochrome, analogic, complement, triad, and quad schemes. | |
| policymesh deepakmeena61/policymesh PolicyMesh is a governed agentic data API that enforces SQL validation, role-based access control, PII masking, and audit logging at the MCP tool boundary, letting users query governed data through natural language with three MCP tools: que | |
| Wireshark MCP deepaknarayanans/wireshark_mcp Exposes Wireshark/tshark packet capture, analysis, threat detection, and reporting tools for AI agents and local testing. | |
| Database-MCP deepan2003/database-mcp Enables natural language interaction with a corporate SQLite database, allowing users to set up tables, add records, and search data through plain English commands. | |
| employee-graph-mcp deepan8545/employee-graph-mcp- An MCP server that provides tools to query and analyze an employee knowledge graph in Neo4j, including semantic resume search, person similarity, and read-only Cypher queries. | |
| Trello MCP Server - Optimized deepankar1993/trello-mcp-server-optimize A high-performance MCP server for Trello integration with 97% token reduction through intelligent response optimization, enabling efficient board, card, and list management. | |
| shottr-mcp deepanshumishraa/shottr-mcp An Effect-native MCP server that lets local agents silently capture macOS windows, displays, and exact regions, then produce Shottr-style PNGs with programmable annotations, backgrounds, padding, rounded corners, and shadows. | |
| Website Security Auditor MCP Server deepanshuverma022/mcp Provides a 'scan_website' tool to analyze target websites for security vulnerabilities by consuming the Website Security Auditor REST API. | |
| Redshift MCP Server deeparajareddy/redshift_mcp_server Enables AI agents to interact with Amazon Redshift databases using natural language to execute queries, list tables, describe schemas, and retrieve sample data. | |
| . deepaross0642/email-mcp Enables AI assistants to read, search, send, reply, forward, schedule, organize, and analyze email across multiple IMAP/SMTP accounts, with provider-aware labels, drafts, templates, and bulk operations. Additional capabilities include real- | |
| MCP Dota 2 Match Analysis Server deepbluecoding/mcp-replay-dota2 FastMCP server for Dota 2 match analysis using replay files and OpenDota API, with built-in coaching instructions for LLMs. | |
| MCP Weather Server deepcodes7/mcpserverweather Enables AI agents to retrieve real-time weather conditions and forecasts via OpenWeatherMap API. Supports interactive weather queries and travel planning through MCP tools, resources, and prompts. | |
| codex-gpt-bridge deepcogneural/codex-gpt-bridge Streamable HTTP MCP bridge that allows ChatGPT to delegate code execution requests to a local official Codex MCP server with configurable safety policies. | |
| MCP Server Basic Example deepdik/mcp-server Basic MCP server demonstrating tools for arithmetic operations (add, subtract) and a personalized greeting resource. | |
| arabimaak-gulf-arabic deepdiver4ai/arabimaak-mcp Look up Gulf Arabic words with pronunciation, example sentences, and cultural context. 30 essential words for learning Arabic used in Saudi Arabia, UAE, Qatar, Kuwait, Bahrain and Oman. | |
| Databento MCP deepentropy/databento-mcp A Model Context Protocol server that provides access to Databento's historical and real-time market data, including trades, OHLCV bars, and order book depth. It enables AI assistants to perform financial data analysis, manage batch jobs, an | |
| mssql-mcp-server deepesh112/mcp_tool_sql Production-ready, cross-platform Microsoft SQL Server MCP server that lets AI assistants work with SQL Server through the Model Context Protocol. | |
| Replicate MCP Server deepfates/mcp-replicate Enables users to access and manage Replicate's AI models and predictions via the Model Context Protocol, offering tools for creating, canceling, and retrieving model predictions and parameters. | |
| agent-pay-mcp deepfirsthq/deepfirstsearch MCP server with paid_fetch, list_merchants and budget_status tools: AI agents pay x402 APIs in USDC on Base inside an owner-signed, on-chain budget, so a prompt-injected agent can't overspend or pay an attacker. | |
| overleaf-mcp deepghs/overleaf-mcp Enables collaborative LaTeX editing on Overleaf with tracked changes, review comments, compilation, file management, and downloads via a single MCP connection. | |
| Deepgram MCP deepgram/mcp Provides AI editors with access to Deepgram's speech-to-text transcription and audio intelligence tools. Dynamically fetches available capabilities from Deepgram's API at runtime, ensuring access to new features without package upgrades. | |
| Deephaven MCP deephaven/deephaven-mcp Enables AI assistants to interact with Deephaven real-time data systems, allowing natural language queries, script execution, and management of both Community Core and Enterprise deployments for live data analysis and streaming workflows. | |
| Broker Buddy MCP Server deepjyotk/broker-buddy-mcp-server FastMCP server exposing brokerage and market tools (Angel One, Coinbase, News) via the Model Context Protocol, enabling portfolio queries and trade execution through natural language. | |
| deepkolor-mcp deepkolor/deepkolor-mcp An MCP server enabling AI image and video generation through DeepKolor's API with 'generate_image', 'generate_video', and 'get_task' tools for asynchronous media creation. | |
| DeepL MCP Server deepl/deepl-mcp-server A Model Context Protocol server that enables AI assistants to translate and rephrase text between numerous languages using the DeepL API. | |
| EpiDash deeplearn-ped/epidash Enables MCP clients holding a control key to create, update, publish, and unpublish dashboards and their charts, plus read-only access to dashboards, view stats, and audit logs. Published dashboards are viewable through public links in a mi | |
| DeepLinkNow MCP Server deeplinknow/dln-mcp Enables coding agents to add deferred deep linking to iOS, Android, React Native, Expo, or Flutter apps, check Universal Links and App Links setup, migrate from Firebase Dynamic Links, Branch, AppsFlyer, or Adjust, and manage links when con | |
| Offramp MCP Server deepmajithia/offramp2 Provides retirement planning computations for AI agents, including Monte Carlo simulations, tax burden modeling across all US states, Social Security claiming optimization, and cost-of-living comparisons. | |
| Azure Diagram MCP Server deepmalh44/azure-diagram-mcp Enables creation of Azure architecture diagrams from natural language descriptions, generating PNG images automatically. | |
| DeepMap AI MCP Server deepmapai/deepmap-mcp-server Provides 25 geophysical intelligence tools for multi-hazard risk scoring, earthquake/volcano/tsunami/sinkhole prediction, weather intelligence, insurance underwriting, climate migration, and parametric triggers. | |
| Earth Grounding MCP deepmapai/earth-grounding-mcp Enables AI agents to query verifiable physical-world ground truth for any point on Earth — water availability, seismic and space-weather hazard, ground stability, and resource indications — with every answer backed by a Bitcoin-anchored pro | |
| DeepMyst MCP Server deepmyst/deepmyst-mcp Enables intelligent LLM optimization and routing for Claude Desktop and HTTP clients, reducing token usage and automatically selecting the best model for each query. |
43,351–43,400 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.