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 |
|---|---|
| borg-mcp borgbackup/borg-mcp A read-only MCP server for BorgBackup that lets AI agents query backup status, repository info, archive listings, and prune previews without modifying or destroying backups. | |
| research-workflow-studio borgdiven/research-workflow-studio Enables AI clients to create and read structured research records—projects, questions, specifications, implementations, executions, artifacts, evidence, evaluations, comparisons, analyses, and reports—through MCP while keeping scientific ju | |
| claude-second-opinion-mcp borge-labs/claude-second-opinion-mcp Enables any MCP client to request an independent second opinion from a fresh Claude Code session without blocking, useful for plans, architecture, debugging, security reviews, and final checks. | |
| mcp-server-action1 borgels/mcp-server-action1 Enables management of endpoint inventory, patching, and vulnerabilities through the Action1 REST API, with read-only access by default and optional write support for update approvals. | |
| mcp-server-apollo borgels/mcp-server-apollo MCP server for Apollo.io B2B data discovery and enrichment, enabling company search, people search, contact enrichment, and organization firmographics through Apollo's REST API. | |
| mcp-server-corpayone borgels/mcp-server-corpayone Enables managing Corpay One accounts-payable workflows including expense listing, coding, and policy-controlled writes, with read-only defaults and audit logging. | |
| mcp-server-dalux borgels/mcp-server-dalux MCP server for the Dalux Build API, enabling read and write access to Dalux Field and Box data including projects, tasks, files, and more. | |
| mcp-server-enablebanking borgels/mcp-server-enablebanking Enables read-only access to a single company's bank accounts via Enable Banking (PSD2 account information), so users can list registered accounts, read balances and account details, and retrieve transactions for a period with filtering and | |
| mcp-server-fatsecret borgels/mcp-server-fatsecret Enables searching FatSecret's food and recipe database, and managing personal food diary, weight, exercise, saved meals, and favorites, with multi-user support and secure OAuth authentication. | |
| mcp-server-fooddata-dk borgels/mcp-server-fooddata-dk Provides access to Danish food and nutrition data from Open Food Facts and DTU Frida, enabling keyword search, barcode lookup, and detailed food information with per-100g macros and source attribution. | |
| mcp-server-garmin borgels/mcp-server-garmin MCP server for Garmin Connect that enables users to access and manage their personal health and fitness data, including daily summaries, heart rate, sleep, HRV, stress, body composition, activities, and training readiness, with secure per-u | |
| mcp-server-hevy borgels/mcp-server-hevy Enables access to Hevy strength-training data—workouts, routines, exercise history, and progression—via an MCP server with per-user credential encryption and optional write support. | |
| MCP Server for Visma Intempus borgels/mcp-server-intempus Enables employees, approvers, and admins to register and manage time, view balances, cases, employees, and planning through Visma Intempus, with per-user scoping and fail-closed identity. | |
| mcp-server-kilango borgels/mcp-server-kilango MCP server that wraps Kilango's operator/control API as tools so an AI assistant can build and manage portals in a Kilango workspace — creating/managing portals, pages, blocks, widgets, apps, and connections, with drag-and-drop reordering a | |
| mcp-server-lager borgels/mcp-server-lager Acts as a thin, permission-delegating facade over bcc's inventory API so an Entra-verified user can browse their own projects, tools, consumables, bookings and orders, with extra read tools and overviews for warehouse managers. Optional wri | |
| mcp-server-microsoft365 borgels/mcp-server-microsoft365 Enables identity provisioning and management for Microsoft 365/Entra ID via Microsoft Graph, including user creation, license assignment, group membership management, and more, with a focus on least-privilege and idempotency. | |
| mcp-server-outline borgels/mcp-server-outline Enables interaction with the Outline knowledge base API, allowing search, document and collection management, comments, and more. | |
| mcp-server-personio borgels/mcp-server-personio MCP server for the Personio HR API with employee and HR profiles, enabling self-service and HR operations like managing absences, attendances, documents, and organizational data. | |
| mcp-server-productive borgels/mcp-server-productive Enables policy-aware access to the Productive.io API v2 for managing projects, tasks, time tracking, resource planning, financials, CRM, and reports, with safe defaults and staged writes for sensitive operations. | |
| mcp-server-saxo borgels/mcp-server-saxo Enables interaction with Saxo Bank OpenAPI for trading, portfolio management, market data, and account operations through natural language. | |
| mcp-server-snipe-it borgels/mcp-server-snipe-it MCP server for the Snipe-IT asset management REST API, enabling read and write operations on assets, licenses, accessories, and more. | |
| mcp-server-telgea borgels/mcp-server-telgea Enables AI assistants to manage a Telgea business mobile operator account end to end: users, teams, plans, lines and eSIMs, live connection status, number port-ins, usage and analytics, data pools, rates and cost thresholds. Read-only tools | |
| mcp-server-withings borgels/mcp-server-withings MCP server for the Withings Health API with per-user OAuth2, enabling users to securely access their own health data (measures, activity, sleep, workouts, heart rate, devices, and goals) and optionally add measurements. | |
| JobSpy MCP Server borgius/jobspy-mcp-server Enables AI assistants to search for jobs across multiple platforms (Indeed, LinkedIn, Glassdoor, etc.) using the JobSpy tool, with filtering and structured output. | |
| kanban-lite borgius/kanban-lite MCP server for AI agents to manage a lightweight kanban board stored as markdown files, enabling task creation, updates, and column movements. | |
| mcp-dataview borgphil/mcp-dataview Enables secure, read-only querying of only predefined logical database views through MCP tools and a REST API, using validated SQL and semantic view metadata. | |
| CodeSherpa boridon/code-sherpa Remote MCP server enabling AI clients to securely inspect repositories over SSH with read-only tools. | |
| DesktopOS boring-hong/desktopos Enables AI agents to operate Windows through persistent PowerShell sessions, dual-channel desktop perception, element-level UIA, CDP browser control, verified actions, and failure self-healing. | |
| zh-prompts boring-hong/zh-prompt-search-mcp Enables MCP-compatible agents to retrieve Chinese expert documents, prompt examples, and task skeletons before writing Chinese prompts. | |
| Boring Gemini boring206/boring-gemini An autonomous AI development agent that enables full-stack coding, automated verification, RAG-powered code search, and quality assurance through MCP tools. Supports Gemini CLI, Claude Code CLI, with features like parallel verification, sec | |
| email-mcp boringfy/email-mcp A local MCP server for Gmail with strict alias whitelisting, allowing AI clients to search, read, reply to, and send emails only from explicitly whitelisted alias addresses while keeping all other mailbox content unreachable. | |
| mcp-gitea boringstudio-org/mcp-gitea MCP server for interacting with Gitea, enabling issue and PR management, repository browsing, file reading, and safe git command execution. | |
| Gitea MCP Proxy Agent boringstudio-org/mcp-gitea-proxy A comprehensive MCP server suite that enables AI interaction with Gitea for repository management, secure command execution, and Docker monitoring. It provides additional tools for long-term memory, filesystem access, and web searching to s | |
| rlm-mcp borinquenkid/rlm-mcp Transforms your local repository into a shared project brain using recursive reasoning and local LLMs to analyze, reason, and remember project architecture. | |
| Giphy MCP Server boris-song/giphy-api An MCP (Multi-Agent Conversation Protocol) Server that enables interaction with the Giphy API, allowing users to search, retrieve, and manipulate GIF content through natural language commands. | |
| mcp-screaming-frog boris0024/mcp-screaming-frog MCP server for controlling Screaming Frog SEO Spider through AI assistants, enabling crawling, SEO issue analysis, and quick page checks via natural language commands. | |
| codebadger boris689/codebadger Enables AI agents and LLMs to build Joern Code Property Graphs from repositories, local paths, or code snippets and query them over MCP, supporting CPGQL queries, data-flow and taint tracing, program slicing, and vulnerability hunting acros | |
| LeetCode MCP Server borish62526/leetcode-mcp-server Enables automated access to LeetCode's problems, solutions, contests, and public data, with optional authentication for user-specific features on leetcode.com and leetcode.cn. | |
| After Effects MCP borishalachev1/after-effects-mcp Connects your AI assistant to afterAI, a hosted After Effects pipeline. Edit raw clips into finished short videos with upscaling, color grade, subtitles, zoom, and beat-synced effects. | |
| Nexus MCP borishalachev1/nexus-mcp.git- MCP server with X402 payment integration, enabling AI agents to access paid tools like weather, web search, and image generation with crypto payments via MetaMask on Base network. | |
| mcp-retrieval-probe borisknight/mcp-retrieval-probe An evaluation harness that probes MCP-based retrieval servers for calibration, relevance, coverage, citation integrity, and more, also exposing the probes as MCP tools for assistants and CI agents. | |
| italia-mcp borislandoni/italia-mcp Provides Italian-language MCP tools for current weather, forecasts, Civil Protection alerts, air quality, ANSA news, editorial updates, and voice-friendly reminders, designed for lightweight clients such as ESP32 chatbots. | |
| Blender Open MCP borislee56/blender-open-mcp Enables AI agents to control a live Blender session over the Model Context Protocol, creating, modifying, and inspecting scene objects, applying materials, rendering images, and pulling PolyHaven assets. Prompts can be routed through a prov | |
| Claude Patent Creator MCP Server borism22914/claude-patent-creator Enables MCP-compatible clients to search patent rules and prior art across MPEP/USC/CFR and 100M+ patents, run automated 35 USC 112 compliance checks, and generate patent-style diagrams. | |
| rumors-lines-mcp borisowlexa2010-star/rumors-lines-mcp Read-only MCP server over the multilingual pick-up line corpus of rumors.app (Tagalog, Brazilian Portuguese, Indonesian, Hindi and more), curated by native editors with literal English glosses. Stdio and Streamable HTTP transports. | |
| Blender Open MCP borisphoenix509/blender-open-mcp Enables AI agents to control a live Blender session by creating, modifying, rendering, and managing scene objects, textures, and PolyHaven assets through MCP tools. It also routes prompts across configurable local or OpenAI-compatible LLM b | |
| OpenClaw MCP Server boriss3659/openclaw-mcp Enables Claude.ai and Claude Desktop to securely connect to self-hosted AI assistant gateways via OAuth2, exposing chat, status, multi-instance routing, and asynchronous task tools. Supports per-instance authentication, isolation, and task | |
| ImagePME borissauvage/mcp-imagepme Enables retrieving ImagePME economic indicators (TVA and TDFC data) from the Ordre des experts-comptables by driving a real browser to log in, fill the form, and download results as Excel or PDF. | |
| FRED MCP Server borissenturk43109/fred-mcp-server Enables universal access to 800,000+ Federal Reserve Economic Data time series through tools for browsing categories, releases, and sources; searching by keywords, tags, or filters; and retrieving series data with transformations and date r | |
| auto-markt borissmaznov/auto-markt-at Enables LLM agents to answer questions about Austrian passenger car registrations from an SQLite database, with tools for market overview, brand trends, brand rankings, and top models. |
35,101–35,150 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.