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 |
|---|---|
| twentycrm-graphql-mcp decode-data/twentycrm-graphql-mcp MCP server for Twenty CRM that enables AI assistants to interact with the CRM via GraphQL, including schema inspection and query execution. | |
| Rozkoduj MCP decodetick/decodetick-mcp Provides AI assistants with market screening, analysis, and scoring across stocks, crypto, and forex, enabling natural language queries for trading insights. | |
| cryptopunks-mcp-server deconstruct2021/cryptopunks-mcp-server Connects AI assistants to live CryptoPunks data for looking up individual punks, checking floor prices, and analyzing wallet portfolios. It provides 28 tools for market research and rarity analysis without requiring wallet setup or API keys | |
| adh decrypthub/adh-cli Enables Cursor and Claude Desktop to connect to a remote host daemon over stdio and invoke its MCP tools, including device listing and single-tool calls. | |
| MCP Gemini Notebook 2026 decsters01/mcp-gemini-notebook-2026 Enables querying NotebookLM with Gemini 2.5 from Cursor/Claude Code, returning answers grounded in user-provided sources without the model's internal thinking. | |
| GitHub MCP Server decuma02/kage-the-mcp Enables LLM agents to search, read, and create GitHub issues and pull requests via natural language, using the GitHub API. | |
| Remnant Read dedale-project/remnant-connect Search reusable technical experience from AI agents, inspect evidence and limitations, and discover public agent Trust Passports through seven anonymous read-only MCP tools. Apache-2.0 integrations, examples and documentation connect to the | |
| gcal-mcp dedalus-labs/gcal-mcp A Google Calendar MCP server that provides comprehensive tools for managing calendars, events, and settings using OAuth2 authentication via the Dedalus framework. It enables users to perform operations such as event scheduling, searching, a | |
| gmail-mcp dedalus-labs/gmail-mcp A Model Context Protocol server that enables full management of Gmail accounts, including messages, threads, labels, and drafts. It leverages the Gmail API to allow searching, sending, and organizing emails via secure OAuth2 authentication. | |
| linear-mcp dedalus-labs/linear-mcp A Model Context Protocol server that enables interaction with Linear workspaces to manage issues, projects, cycles, and teams through a GraphQL interface. It provides 21 tools for comprehensive task management, search, and workflow coordina | |
| Dedalus MCP Documentation Server dedalus-labs/mcp-server-example-python An MCP server that serves documentation and enables AI-powered search, Q\&A, and document analysis for developer tools and guides. | |
| linear-mcp dedalus-labs/old.linear-mcp An MCP server for Linear that provides tools to manage issues, projects, comments, cycles, teams, and users via GraphQL, with OAuth2 authentication through Dedalus. | |
| Supabase MCP Server dedalus-labs/supabase-mcp Enables secure interaction with Supabase databases via the PostgREST API, supporting full CRUD operations and stored procedure calls. It utilizes the Dedalus MCP framework to provide encrypted credential handling and just-in-time token exch | |
| Roblox Executor MCP dedankschool-oss/roblox-executor-mcp An MCP server that lets AI agents drive a running Roblox client, execute Luau, decompile scripts, spy on remotes, and automate UI, with a bundled Vyre dashboard for live monitoring. | |
| DedcodeMCP File Manager dedcode14/dedcodemcp Enables file management operations on the desktop including creating, reading, editing, moving, renaming, deleting, and listing files through the Model Context Protocol. | |
| ListingGood MCP dedegroup/listinggood-skills A remote MCP server for Amazon sellers to scan, generate, and optimize product listings for AI-recommendation readiness and compliance. | |
| MercadoLibre MCP Server dedero1985/mercadolibre-mcp Enables AI assistants to search, create, update, delete, and manage product listings, orders, shipping, questions, advertising campaigns, and more across 18 Latin American countries via the MercadoLibre REST API. | |
| Codebase MCP dedeveloper23/codebase-mcp A Model Context Protocol server that enables AI agents to retrieve and understand entire codebases at once, providing tools to analyze local workspaces or remote GitHub repositories. | |
| planka-mcp dedieko-priyadi/planka-mcp MCP server that connects Hermes to Planka Kanban, enabling natural language management of projects, boards, lists, cards, and users through the Planka REST API. | |
| agents-mcp dedinc/agents-mcp Enables running AI agents via OpenAI-compatible APIs with custom system prompts, models, and queries. Supports persistent memory, preset agents, and multi-step workflows like pipelines and swarms. | |
| GitLab MCP Server dediwsn/gitlab-mcp Enables AI agents and MCP clients to manage projects, merge requests, issues, pipelines, wiki, releases, tags, milestones, and more through stdio, SSE, or Streamable HTTP with PAT/OAuth authentication. | |
| agentic-dns dedsecorg/agentic-dns Enables AI agents to monitor, trace, query, and manage local DNS resolver chains using MCP, with health checks, packet tracing, Pi-hole log access, and automated failover via natural language. | |
| Frigate MCP Server dedsxc/mcp-frigate Enables AI assistants to interact with Frigate NVR security camera systems, supporting camera management, event detection, snapshots, recordings, and system stats via natural language. | |
| mcp-openmemory dedsxc/mcp-openmemory A FastMCP server that exposes mem0 long-term memory to MCP clients over SSE, enabling AI agents to store and recall facts persistently. | |
| MCP TIDAL Server dedsxc/mcp-tidal Enables AI assistants to access TIDAL Music catalog, including search, playlists, favorites, and recommendations. | |
| MCP Gemini Web Search deduble/mcp-gemini-web Provides grounded web search and research capabilities using Google's Gemini models and Google Search, with features like normal and research modes, batch searches, and health checks. | |
| quantum-resource-estimator deduckproject/quantum-resource-estimator-mcp Estimates physical quantum resources (qubit count, runtime) for quantum algorithms on fault-tolerant hardware through natural language queries. | |
| stim-mcp-server deduckproject/stim-mcp MCP server wrapping Google's Stim stabilizer circuit simulator. Wire it up to an LLM and you can build and sample circuits through conversation. | |
| electron-live-i18n dee0917/electron-live-i18n MCP server for live-translating Electron apps: inspect and patch app.asar bundles, serve a translation layer, translate text/locale files, and revert changes—all through natural language commands. | |
| odoo-mcp-bridge deeech2000/odoo-mcp-bridge Enables connecting Odoo to Claude to read vendor account statements and create draft-only vendor bills and payments, ensuring no financial actions are confirmed or published without human approval in Odoo. | |
| xcode-cloud-mcp deeepanshu/xcode-cloud-mcp Local MCP server enabling agents to track Xcode Cloud builds and access TestFlight crash reports through the App Store Connect API. | |
| wais-mcp deegerhq/wais-mcp Universal MCP server for WAIS (Web Agent Interaction Standard) that provides 5 generic tools to discover, register, execute actions, confirm high-risk actions, and check status on any WAIS-compatible site. | |
| MCP Runbook Search Server deekshu05/mcp-document-search-server Enables MCP-compatible clients to semantically search, retrieve, and list engineering runbooks, providing relevant runbooks in response to natural language queries. | |
| T3Code MCP Bridge deel77/t3code-mcp Lets MCP clients connect to T3Code for voice conversations, browsing threads, reading updates, answering questions, reviewing approvals, and starting coding turns over Streamable HTTP. | |
| BookmarkMemory deenihl/bookmarkcontext Enables semantic search and retrieval of bookmarked URLs content using vector embeddings, with support for multiple backends and AI assistant integration. | |
| solveaux-mcp deep-chauhan-04/solveaux-mcp Enables MCP-compatible AI agents to read and store architecture decisions, constraints, and research from a private Solveaux workspace, keeping generated code aligned with team-approved technical direction. | |
| @deepidv/mcp-server deep-identity-inc/deepidv-mcp-server Enables AI agents to perform identity verification, KYC/KYB, PEP & sanctions screening, bank statement analysis, and workflow automation via the Model Context Protocol. | |
| TuringWell MCP Server deep-insight-labs/turingwell-mcp MCP server for TuringWell, the agent-native Q&A platform for executable, verifiable fixes. | |
| TranslationX MCP Server deep-intelligent-pharma/translationx-mcp-server A server that provides translation capabilities using TranslationX API, enabling users to translate files and content through natural language commands. | |
| kubeaid-mcp deep-poharkar/kubeaid-mcp An MCP server that lets AI assistants manage KubeAid GitOps clusters, inspecting ArgoCD apps, pods, events, and resources, with optional write operations like syncing apps and scaling deployments through your own kubeconfig credentials. | |
| HomeFix MCP Server deep19901985/homefix-alexa-mcp Enables AI assistants to search existing repair reports, detect potential duplicates, retrieve repair status, create new reports, add updates, and change priorities after confirmation through a repair management backend. | |
| mcp-weather deep3036/mcp-weather Enables retrieval of current weather conditions for any city or place name, including temperature, feels-like, humidity, precipitation, wind, condition, day/night, timezone, and coordinates. | |
| EchoFM Studio deep360-code/mcp_creartors- Enables AI assistants to manage audio-story series: create, edit, narrate, publish, and generate marketing content like UGC videos and reels through a secure MCP endpoint. | |
| MCP_IDMC deepa-s-chebbi/mcp_idmc A FastMCP server that exposes Informatica IDMC Data Integration APIs as MCP tools, allowing AI agents to query, run, and monitor CDI mappings through natural language. | |
| Mathematical MCP Server deepa11042004/calculator_mcp_server A mathematical MCP server exposing 6 basic arithmetic and secure symbolic expression evaluation tools (add, subtract, multiply, divide, power, evaluate_expression) with structured JSON responses, input validation, and safe AST-based parsing | |
| file-reader-mcp deepa11042004/file-reader-mcp Enables LLM agents to securely explore, read, search, and analyze text-based files within a sandboxed environment. | |
| AWS FinOps MCP Server deepa19018/aws-finops-mcp-server Enables querying AWS cost and usage data, monitoring budgets, and auditing for waste such as stopped EC2 instances, unattached EBS volumes, and unassociated Elastic IPs through natural language across multiple AWS profiles and regions. Runs | |
| claude-soul deepabrooks32776/claude-soul Enables persistent cross-session memory, correction-pattern tracking, and evolving behavioral frameworks within Claude Code, exposing 15 MCP tools for saving and semantically searching facts, decisions, and lessons, loading identity and fra | |
| cityflo-ontime-mcp deepachaudharyoct10/cityflo-ontime-mcp MCP server for analyzing bus route on-time performance, providing lateness summaries, trip drill-downs, and flagged data reports. | |
| NotionMCP deepactionpotential/notionmcp Enables AI assistants to search, read, summarize, and analyze sentiment of Notion pages and databases, turning your Notion workspace into an intelligent, queryable knowledge system. |
43,301–43,350 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.