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 |
|---|---|
| Langfuse Prompt Management MCP Server chevalier52/mcp-server-langfuse Enables access to and management of Langfuse prompts through the Model Context Protocol, including listing prompts and retrieving/compiling them with variables, plus equivalent tools for broader client compatibility. | |
| System Designer MCP Server chevyphillip/system-designer-mcp Enables AI agents to create, validate, and export UML system models using structured MSON format. Supports generating PlantUML and Mermaid diagrams with direct export to System Designer macOS application. | |
| Thunder Client License Manager MCP Server chezsmithy/thunderclient-license-manager-mcp Provides tools for managing Thunder Client licenses through their API, enabling users to add, retrieve, and remove licenses with simple commands. | |
| receipts-api-mcp chf3198/receipts-api-mcp Enables querying and analyzing receipt data with SQL-style grouped statistics, filtering, and receipt lookup through natural language via MCP-compatible clients. | |
| CodePulse MCP Server chh-dhairya/codepulse Enables AI agents to search code, inspect symbols, navigate call graphs, and analyze change impact across scoped local repositories through the same engine as the CLI and REST API. | |
| WhatsNew-MCPserver chhanz/whatsnew-mcpserver Fetches AWS What's New announcements by month, allowing users to query announcements for a specific year/month via MCP tools. | |
| mcp-graphify-autotrigger chharithoeun/mcp-graphify-autotrigger Provides efficient knowledge-graph queries and unrestricted shell delegation for AI agents, reducing token usage by 80-150x and bypassing app tier restrictions. | |
| atotw-mcp chi-feng/atotw-mcp Enables Claude to access and search over 500 anaesthesia tutorials from WFSA's ATOTW program, with smart embedding-based search and full text retrieval. | |
| codex-commit-review-mcp chi-qhsun/codex-semantic-review Enables auditable, plan-linked Git commit review views for Codex, with interactive file trees, split diffs, line-level explanations, and SHA-256 audit receipts served locally on localhost. | |
| Siri Shortcuts MCP Server chi2941/mcp-server-siri-shortcuts Enables LLMs to list, open, and run shortcuts from the macOS Shortcuts app, with optional input and dynamically generated callable tools for available shortcuts. | |
| Social Media Scraper chi46203/custom-mcp-server Enables AI assistants to retrieve public profile data from LinkedIn, Facebook, and Instagram and to run web searches via the Google Serper API, returning the results as JSON. | |
| tsserver-mcp-server chia1104/tsserver-mcp-server Exposes TypeScript language service tools (completions, go-to-definition, type info, diagnostics) via MCP for use by AI or IDE clients. | |
| managebac-mcp chiang881/managebac-mcp 使AI代理能够通过学生账号读取ManageBac中的截止日期、成绩条目和GPA的MCP服务器。 | |
| octagon-mcp-server chiara01702/octagon-mcp-server Enables natural-language questions about public and prediction markets, returning structured, source-backed answers from SEC filings, earnings transcripts, financial metrics, stock and crypto market data, and prediction markets news and res | |
| MCP Memory Keeper chiara3026/mcp-memory-keeper This MCP server provides persistent context management for Claude AI coding assistants, enabling users to save, restore, search, and checkpoint conversation context across sessions. It uses channels, categories, checkpoints, and batch opera | |
| IMAP MCP Server chiara53777/imap-mcp-server Enables AI assistants to search, read, send, reply to, organize, and bulk-delete email across multiple mailboxes, with automatic SMTP configuration, connection pooling, and AES-256-encrypted credential storage. It also lets users manage acc | |
| Sanity chiara8181/agent-toolkit Gives AI agents direct access to content projects for running GROQ queries, creating, patching, publishing, and unpublishing documents, inspecting and deploying schemas and hosted Studios, and fetching always-current agent rules. Authentica | |
| FHIR MCP Server chiara93879/fhir-mcp-server Enables LLM-based agents and MCP-compatible clients to perform CRUD operations on healthcare resources, process clinical documents, run semantic search, and query LOINC terminology through natural-language prompts. | |
| FirstData MCP chiaradavis63/firstdata Enables users and AI agents to locate authoritative primary data sources and obtain step-by-step website navigation for retrieving specific datasets from official government, international organization, academic, and industry sources throug | |
| multiCAD-mcp chiarakimura00388/multicad-mcp Enables AI assistants to control supported CAD applications through the Model Context Protocol, supporting drawing, layer, entity, block, file, and export operations via direct tool calls or natural language. | |
| Codex Control Plane MCP chiarakowalczyk/codex-control-plane-mcp Enables MCP clients to drive Codex Desktop and codex-app-server as a durable worker for long-running tasks by submitting work and receiving an operationId or workflowId immediately, then polling status, handling Plan Mode approvals and pend | |
| Claude IPC MCP chiarao07/claude-ipc-mcp Enables different AI assistants to exchange messages with each other across platforms and sessions using simple natural language commands. Messages are stored persistently, so they survive restarts, and instances can register names, send me | |
| Codex Control Plane MCP chiarap76619/codex-control-plane-mcp Enables MCP clients to drive Codex Desktop and codex-app-server as a durable asynchronous worker for long-running tasks, with polling, approvals, Plan Mode workflows, retry safety, diagnostics, and final reporting. It also provides recovery | |
| Snippy chiararose750/snippy Enables AI assistants to discover and invoke tools for saving and retrieving code snippets, generating style guides and wiki documentation, and orchestrating multi-agent documentation workflows with semantic search. | |
| web3-research-mcp chiarasuzuki/web3-research-mcp Enables deep crypto token research across CoinGecko, CoinMarketCap, DeFiLlama, and web search through structured plans, multi-source data fetching, status tracking, resource storage, and report generation, locally and without API keys. | |
| Cinema4D MCP Server chiarawalczak/cinema4d-mcp Connects Cinema 4D to Claude so users can create and manipulate 3D scenes through natural-language prompts. It supports object and primitive creation, cameras and animation, lighting, materials and shaders, MoGraph cloners and fields, dynam | |
| chiark-mcp chiark-ai-dev/chiark-mcp Find the most reliable AI agent for any task. Search 2,000+ agents across A2A and MCP with quality filters — min uptime, max latency, score thresholds. Check if an agent is alive before routing to it. Like Artificial Analysis, but for agen | |
| MCP-Driven Data Management System chibbi1/mcp Enables natural language interaction with heterogeneous databases (MySQL and PostgreSQL) for CRUD operations across customer, product, and sales data with intelligent query routing and visualization capabilities. | |
| ReversePlumbing chibitek/reverseplumbing Enables AI clients to inspect installed software packages and saved browser traffic through read-only local parsers, producing structured evidence about application structure, dependencies, endpoints, and observed authentication schemes. | |
| mcpixel-studio chibivaru1225/mcpixel-studio Enables MCP clients to create and edit pixel art and animations through a local-first editor, sharing the same project, editing commands, and undo history with the GUI. | |
| Jira MCP Server with OAuth chibolar/jira_mcp_sprinthealth Enables seamless Jira integration through browser-based OAuth authentication, providing tools for issue management, JQL search, and project access without manual API token configuration. | |
| Career Intelligence MCP chibuezeonejeme/career-intel-mcp An AI-powered career intelligence platform for job seekers that parses resumes, scrapes and scores job listings, analyzes skill gaps, and prepares for interviews. | |
| hexmux chichou/hexmux MCP server that enables AI agents to control IDA Pro instances via Unix-socket supervisor, providing tools for decompilation, disassembly, and Python scripting. | |
| Algolia Search MCP Server chick-p/algolia-search-mcp-server Enables searching for any text within a specified Algolia index through an MCP-compatible interface. It allows users to integrate Algolia search capabilities into their environment using an application ID and API key. | |
| CNKI Scholar chickensooup/cnki-mcp Enables read-only searching of CNKI literature metadata by topic, keyword, title, author, abstract, or DOI, with filters for year and publication type plus relevance, date, citation, and download sorting. Also retrieves full paper details s | |
| mcp-glpi-it4 chicoia/mcp-glpi-it4 Integrates with GLPI IT4Solução API v2.3 (OAuth2) to manage tickets, computer inventory, and configuration parameters, with safety features like dry-run and rollback. | |
| phishclean-mcp chidhu07/phishclean-mcp Enables security analysis through MCP-compatible clients, including URL phishing checks, email header verification, JWT decoding, password strength analysis, and leaked secret scanning in code. | |
| AgentGate chidhvilasa/agentgate An MCP proxy firewall that evaluates every tool call against a configurable policy, enabling allow/deny/approval decisions, secret redaction, and a tamper-evident audit trail. | |
| FL Studio MCP Bridge chidotaku/fl-studio-mcp-bridge Enables MCP-compatible chat to control FL Studio on Windows, including transport, BPM, channels, mixer, patterns, and note insertion via MIDI bridge. | |
| northbridge-diligence chidrupa99/northbridge-diligence An MCP server that wraps SEC EDGAR APIs to provide company financial data, screening metrics, and disclosure signals for investment diligence, with every figure traced to its source filing. | |
| File System MCP Server chidvilas1234/project-mcp Enables safe file system operations including reading, writing, updating, and deleting files with built-in security safeguards, automatic backups, and comprehensive error handling. Provides directory listing, file metadata extraction, and p | |
| mcp-buttplug chiefautism/buttplug-mcp An MCP server that connects Claude and other MCP clients to buttplug.io, allowing AI models to directly control and orchestrate intimate hardware in real-time. It provides a suite of tools for device discovery and haptic commands like vibra | |
| Remote MCP Server on Cloudflare chiefdecisionarchitect/remote-mcp-server Enables deploying a remote MCP server on Cloudflare Workers with OAuth login, allowing MCP clients like Claude Desktop to connect and use tools over SSE. | |
| adds-mcp chiefff-kiefff/adds-mcp Provides read-only tools for monitoring and investigating Active Directory Domain Services, including users, groups, OUs, computers, GPOs, and domain metadata via LDAPS. | |
| cisco-mcp chiefff-kiefff/cisco-mcp Enables LLMs to run read-only show commands on Cisco IOS/IOS-XE and Nexus switches over SSH, with a two-account model for privilege separation and a fail-closed allowlist for safety. | |
| paperless-mcp chiefmikey/paperless-mcp MCP server for Paperless-ngx document management. Enables AI models to search, retrieve, update documents and manage metadata. | |
| code-security-skill chiehyii/code-security-skill MCP server providing a searchable security knowledge base for AI coding assistants, enabling retrieval of secure-coding instructions and feature-specific security guidance. | |
| youtube-mcp chiekh-a/youtube-mcp A lightweight MCP server for reading public YouTube data, offering tools to fetch video transcripts, playlist contents, and video metadata without requiring an API key. | |
| openproject-mcp-and-skills chien334/openproject-mcp-and-skills MCP server enabling AI agents to interact with OpenProject API v3 for project management, including creating and managing work packages, projects, comments, time entries, boards, and user dashboards. | |
| GMA2 MCP chienchuanw/gma2-mcp An MCP server that lets AI assistants control grandMA2 lighting consoles via Telnet, exposing 41 high-level tools for cue management, fixture control, preset management, executor control, macro editing, appearance assignment, bulk operation |
38,351–38,400 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.