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 |
|---|---|
| Журнал commelias/byt-agent Enables the agent to record meals, workouts, and check-ins, and to retrieve daily summaries, history, and settings through MCP tools. | |
| commentkeyword-mcp commentkeyword/instagram-mcp-server Enables AI agents to create, update, list, pause and delete Instagram "comment a keyword → auto-DM" automations through the CommentKeyword API, including choosing keywords, DM and public reply variants, targeting next or specific posts, and | |
| SAP Commerce MCP Server commerce-cloud-integrations/sap-commerce-mcp-server Enables interaction with SAP Commerce systems through OCC APIs, supporting product discovery, cart management, customer support operations, and store information retrieval. Provides both local and remote connectivity options for AI agents t | |
| Commerce Layer Metrics MCP Server commercelayer/mcp-server-metrics Enables AI agents to query commerce metrics data such as orders, carts, and returns via breakdowns, stats, and searches through the Commerce Layer Metrics API. | |
| commercetools Commerce MCP commercetools/commerce-mcp Enables AI agents to interact with commercetools APIs to manage products, categories, orders, carts, and customer data. It provides a comprehensive set of tools for both read-only and full-access operations through secure authentication met | |
| commercetools MCP Essentials commercetools/mcp-essentials An MCP server that enables AI agents to interact with the commercetools Composable Commerce platform. It provides tools for managing products, categories, orders, carts, and customer data through secure read and write operations. | |
| Commertize Agents MCP Server commertize-inc/mcp-server Exposes public marketplace data — offerings, screening and comparison, news, sponsor listings, and platform reference text — as typed read-only tools any MCP-compatible agent can call without an API key or account. Every response carries pr | |
| Argus commet/argus Enables users to turn a decision into an append-only judgment record that keeps their own wording and premises separate from the AI's suggestions, then returns on a chosen event or fallback date so reality and later answers can be appended | |
| SAY commet/say-mcp Converts family notices (hospital, government, insurance, delivery) into action cards with confirmed facts and pending verifications, enabling collaborative family confirmation and completion. | |
| fanqie-writer-mcp commitbyryan/fanqie-writer-mcp Enables agents to batch-upload chapters from local manuscript directories to a Fanqie Novel author backend that only accepts one chapter at a time, with dry-run planning, draft or publish modes, volume routing, chapter range selection, and | |
| OpenF1 MCP Server commitnotfound/openf1_mcp Enables AI assistants to query real-time and historical Formula 1 data through the OpenF1 API, providing tools for driver info, lap times, telemetry, race events, and more. | |
| qiskit-mcp-server common-good-intelligence/qiskit-mcp-server An MCP server that gives Claude hands-on access to quantum computing via Qiskit, enabling building circuits, simulation, statevector inspection, transpilation, and optional execution on real IBM quantum computers. | |
| codex-antigravity-bridge common-ka/codex-antigravity-bridge Enables MCP-compatible clients like Codex to delegate tasks to the Antigravity CLI, using ConPTY on Windows to reliably capture responses. | |
| Blender MCP commonsensemachines/blender-mcp Enables AI-assisted 3D modeling workflows by connecting Blender with LLMs and CSM.ai, allowing text-based editing, asset retrieval from CSM.ai sessions, and humanoid animation using Mixamo files. | |
| CommonTrace MCP Server commontrace/mcp Connects AI coding agents to a shared knowledge base by allowing them to search, retrieve, and contribute coding traces. It acts as a protocol adapter for the CommonTrace API, facilitating collaborative knowledge sharing through natural lan | |
| commune-mcp commune-dev/commune-mcp Give Claude (or any MCP client) a real email inbox and SMS. Your AI agent can read and send email, manage inboxes, track delivery, and handle SMS. | |
| VyMCP community-vyprojects/vymcp MCP server for VyOS routers via VyManager, enabling AI agents to read and manage router configurations with RBAC, audit, and commit-confirm safety. | |
| poke-interconnect communitypoke/hivemind-public Enables independent Poke instances to discover each other's capabilities and exchange cryptographically signed, consented, idempotent messages and data through MCP tools, resources, and prompts. Provides handshake, message sending, data exc | |
| remote-mcp-scraper-vercel communitypokeorg/remote-mcp-scraper-vercel Enables remote web scraping through MCP tools over SSE, including stealth HTTP fetching, headless Chromium screenshots, and movie metadata lookup from public sources. | |
| Commvault MCP Server commvault/commvault-mcp-server Enables AI agents to securely access and manage Commvault environments, including job control, backup schedules, client/storage management, SLA monitoring, and optional DocuSign envelope backup integration. | |
| Kachaka MCP Server comoc/kachaka-mcp Enables AI models to monitor and control Kachaka robots via MCP, including navigation, shelf operations, and sensor data access. | |
| homelab-mcp compactly8274/homelab-mcp MCP server for homelab diagnostics + auto-update pipeline, managing Docker hosts via SSH with read-only diagnostics, image-drift visibility, and automated update execution with rollback. | |
| ProjectHub MCP Server compagnt/projecthub-mcp Enables AI assistants to interact with ProjectHub for comprehensive project management through natural language. It provides 25 tools to manage tasks, workspaces, time tracking, notes, and discussions via the ProjectHub API. | |
| hh-vacancy-mcp compans/hh-vacancy-mcp Enables searching HH.ru vacancies through an authenticated browser session and scoring results against a resume with a configurable minimum match threshold. | |
| mcp.companygraph.io companygraph/mcp-companygraph-io Enables connecting to CompanyGraph's mental-model as a remote MCP endpoint, allowing agents like Claude, ChatGPT, and Gemini to query the model's types, schemas, rules, and entities without authentication. | |
| CompanyGraph MCP Server companygraph/mcp-server Enables agents to query a CompanyGraph instance read-only, retrieving types, schemas, entities, skill evidence, and search results with verbatim answers from a specific model commit. | |
| Redmine MCP Server compasify/redmine-mcp-server Model Context Protocol (MCP) server for Redmine that provides comprehensive access to the Redmine REST API, enabling users to operate Redmine from MCP clients such as Claude Desktop. | |
| Compass DaaS compass-food/compass-mcp Compass DaaS exposes vegan-friendly restaurant search, restaurant enrichment, and dietary fit decision tools over the Model Context Protocol. | |
| compcode-mcp compcode-ai/mcp Official CompCode MCP server that treats commission plans as code, exposing tools to author plans, assign reps, set quotas, simulate commissions, recalculate, and export payroll. It integrates with Claude Code, Cursor, and any MCP client. | |
| File Context MCP compiledwithproblems/file-context-mcp This server provides an API to query Large Language Models using context from local files, supporting various models and file types for context-aware responses. | |
| Adobe Premiere Pro MCP compimprove/adobe-premiere-mcp Operates local Adobe Premiere Pro projects through MCP, exposing 284 tools for AI-driven video editing including timeline editing, effects, exports, and guided assembly workflows. | |
| Connhex MCP Server compiuta-origin/connhex-tools Enables natural language interaction with Connhex IoT platform APIs for managing devices, telemetry, rules, and resources via MCP tools. | |
| Cloud PC Management MCP Server complexdevel/mcp-cloud-pc Enables management of Azure Cloud PCs using the Microsoft Graph API, allowing users to list available Cloud PCs in their tenant through Claude Desktop. | |
| Complexity Source MCP complexity-ml/complexity-source-mcp Read-only MCP server providing AI access to verifiable web, GitHub, and local sources, plus a managed fantasy entity catalog, with strong security and provenance tracking. | |
| CompliAPI compli-api/compliapi-plugin Real-time OFAC and global sanctions screening for AI agents: screen crypto addresses, emails, websites, government IDs, and countries against OFAC SDN and 10+ sanctions/crime/risk lists, plus PEP screening, VPN detection, and IP geolocation | |
| ComplianceCow MCP Server compliancecow/cow-mcp Enables AI agents to interact with the ComplianceCow platform to retrieve compliance insights, dashboard data, and auditable evidence through a Compliance Graph. It also supports automated remediation actions such as fixing policies and cre | |
| complyeah-mcp complyeah/complyeah-mcp MCP server for complyeah that enables AI assistants to list domains and scans, read findings, and start external penetration tests through the complyeah API. | |
| ComplyEdge TrustLint complyedge/complyedge Offline MCP server that checks and scans your own AI prompts and outputs against a local compliance rule corpus. Returns rule ID, severity, citation, and remediation per finding — no API key, Apache 2.0. | |
| ff-mcp complynx/ff-mcp MCP server that gives local clients controlled access to a Firefox profile, enabling tab listing, reading, interaction, scripting, and screenshots with granular, revocable permissions. | |
| Jupyter Collaboration MCP Server complyue/jupyter-collaboration-mcp Enables AI agents to interact with collaborative Jupyter notebooks and documents in real-time, supporting notebook operations, document editing, user awareness tracking, and session management through Jupyter's RTC capabilities. | |
| Browser Controller compnew2006/browser-controller Gives MCP-compatible AI agents direct control of your real browser with existing sessions, logins, and cookies. Supports multiple agents concurrently with tab targeting. | |
| QuickBooks Desktop MCP compolaga/quickbooks-desktop-mcp Enables MCP clients such as Claude Desktop to read and, after per-transaction confirmation, write accounting data—invoices, customers, items, payments, deposits, checks/bank charges, and journal entries—with two-step confirmation and revert | |
| Open Workbook components-kit/open-workbook Local-first MCP runtime for fast, reversible, template-aware Excel automation, enabling agents to manipulate live Excel workbooks with safety features like snapshots and rollbacks. | |
| CompoundPulse Proof compoundpulse/proof-mcp A second opinion on any ticker, before you act. The case for it, the case against it, and the price that proves it wrong. | |
| compresh-mcp compresh/compresh-mcp Provides production-grade context compression for LLM agent conversations with Q-protective ranking, epistemic markers, and semantic store, reducing token usage while preserving equivalence. | |
| Prowler MCP Server comprowler/compler_mcp Analyzes Prowler security scan results for cloud environments, providing detailed security analysis and summary reports through Claude Desktop. | |
| Prowler MCP Server comprowler/project_compler Enables analysis of Prowler security scan results, providing detailed security analysis, security summary, and file retrieval capabilities. | |
| PresentationMcpServer compsciguyit/presentationmcpserver Autonomously generates university-level educational presentations as interactive Reveal.js decks with time-synced presenter scripts from source materials, respecting target audience pedagogical level. | |
| Kali MCP compufreq/kali-mcp Enables authorized security testing by letting LLM clients run Kali Linux tools inside an isolated Docker container. | |
| cvi-mcp computational-value-investing/cvi-mcp MCP server that makes the CVI Platform a native tool for AI assistants, enabling stock screening, company analysis, and point-in-time research via natural language. |
40,101–40,150 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.