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 |
|---|---|
| historical-kb-mcp anands-bounteous/historical-kb-mcp Stores and retrieves completed defect-triage analyses to find similar past defects during new ticket triage. Provides tools for storing, searching, updating, and listing historical defect records with hybrid retrieval (dense + BM25). | |
| jira-confluence-mcp anands-bounteous/jira-confluence-mcp This MCP server provides unified read/write access to Jira Cloud tickets and Confluence Cloud pages, enabling search, retrieval, and updates. It automatically downloads log attachments from tickets into a shared directory for the companion | |
| Log Intelligence MCP anands-bounteous/log-intelligence-mcp MCP server for semantic log ingestion, hybrid retrieval, and cleanup, enabling natural-language querying of log files with dense+BM25 retrieval and full provenance. | |
| BulkClix MCP Server ananselabs-org/ananse-tools Enables AI agents to interact with the BulkClix platform for SMS, OTP, airtime, mobile money, bank transfers, data bundles, KYC, contacts, and account management via natural language. | |
| Poe Proxy MCP Server anansitrading/poe-proxy-mcp A FastMCP server that proxies the Poe.com API, allowing users to query various AI models (including Claude 3.7 Sonnet) and share files with models that support it. | |
| Sprite MCP Server anansitrading/sprite-mcp-server Enables management of Sprite VMs through interactive dashboards and terminal interfaces. It allows users to execute commands, create filesystem snapshots, transfer files, and manage VM lifecycles via natural language. | |
| mlops-mcp-server anant-patankar/mlops-mcp-server Enables AI assistants to perform MLOps workflows such as experiment tracking, model registry, dataset management, pipeline orchestration, and data lineage by wrapping DVC, MLflow, and Git. | |
| job-search-mcp ananta888/job-search-mcp MCP server for combined multi-portal job search, connecting StepStone, Arbeitnow, Remotive, and We Work Remotely, with robust error isolation and markdown reports. It respects portal restrictions and avoids scraping protected services. | |
| Nexla DocQA MCP Server anantasingh/nexla-docqa-mcp Enables natural-language question answering over financial annual reports with source-attributed answers, supporting hybrid retrieval and grounded abstention. | |
| Circle MCP Server anantbisht07/circle-mcp Enables AI assistants to interact with Circle.so communities through Google OAuth 2.0, providing 20+ tools for comprehensive community management. | |
| MCP Gateway anantgarg/mcp-gateway A self-hosted MCP gateway with Google OAuth and role-based access control, allowing MCP clients like Claude and Cursor to connect and interact with configured Zendesk and Chargebee connectors through an admin dashboard. | |
| Purse anantha99/purse Enables agents to access a shared portable vault for memory, skills, and API credentials through MCP, so tools can store and retrieve memories, read versioned skill playbooks, and make server-side API calls without exposing secret keys. | |
| SentinelMCP ananthanarayankv/sentinalmcp Enables LLM-driven agents to autonomously detect, diagnose, repair, verify, and prevent software and hardware failures on local and remote systems. Includes built-in safety checks and automatic rollbacks. | |
| semantic-saga-mcp ananthaprakashb/semantic-saga-mcp Enables agentic workflows to execute allow-listed side effects with automatic reverse-order compensation on failure, durable SQLite journaling, and idempotent rollback via MCP tools. | |
| SmartCommute anantm2007/alexa-smart-commute-mcp Enables users to compare live multimodal travel options — bike taxi, metro, AC cab, and city bus — by geocoding any real-world origin and destination and computing actual road distances, travel times, and dynamic INR fares. It filters out a | |
| Octopus Deploy Official MCP Server ananya0553/mcp-server Enables AI assistants to inspect, query, and diagnose deployments, releases, runbooks, tasks, tenants, and infrastructure inside an Octopus instance through its APIs. Supports read-only and write-gated modes, toolset selection, and structur | |
| loci-mcp ananya0615/loci Enables AI agents and MCP hosts to query a local index of scattered notes and documents through hybrid vector and BM25 retrieval, returning section-level citations and exposing tools, resources, and prompts. | |
| MultiZen MCP Server ananya9434/multizen-browser Enables MCP clients to drive isolated, persistent browser profiles — navigating, clicking, typing, extracting, screenshotting, evaluating JS, and managing tabs and cookies — each with its own cookies, fingerprint, and proxy. This lets AI ag | |
| flompt ananyaa6007/flompt Enables Claude Code to decompose raw prompts into structured typed blocks, compile blocks into Claude-optimized XML prompts with estimated token counts, and list all 16 available block types with their canonical ordering. | |
| >lattice-mcp ananyaa6007/matryoshka Enables analysis of documents far larger than an LLM's context window by having the model emit small symbolic commands that execute server-side, returning compact handles instead of bulk data. It also provides a persistent memo pad so agent | |
| Everything Search MCP Server ananyaakamat/everything-search-mcp-server Integrates with Everything Search Engine to provide lightning-fast file search capabilities across Windows systems using natural language queries and advanced filtering options through MCP-compatible applications. | |
| mcp-server-atlassian-bitbucket ananyaalexander7574/mcp-server-atlassian-bitbucket Enables AI assistants to interact with Bitbucket Cloud workspaces, repositories, pull requests, commits, branches, diffs, comments, issues, pipelines, and deployments through MCP tools for listing, reading, creating, updating, deleting, sea | |
| multiCAD-mcp ananyabayrak/multicad-mcp Enables AI assistants like Claude for Desktop or Cursor to control supported CAD applications through MCP, supporting drawing, layer and entity management, block operations, data export, and file/session control via natural language or unif | |
| Luma MCP ananyaharper/luma-mcp Enables AI coding assistants without native vision to analyze images — screenshots, error messages, UI layouts, and documents — through a single image_understand tool. It routes requests across multiple vision LLM providers (GLM, DeepSeek-O | |
| MCP Proxy Server ananyajeong30499/mcp-proxy-server Connects to and aggregates multiple backend MCP servers (Stdio, SSE, and Streamable HTTP), exposing their combined tools and resources through a single unified SSE or Streamable HTTP endpoint, or as a standalone Stdio server. Handles reques | |
| Agent Harness Kit ananyamaas01/agent-harness-kit Enables AI coding providers to run structured multi-agent workflows, manage specs and tracked tasks, record handoffs, and enforce health-gated completion evidence. | |
| MS 365-21V MCP Server ananyavandenberg65/ms-365-21v-mcp-server Enables MCP-capable AI clients to act on a user's behalf against 21Vianet-operated Microsoft 365 through Microsoft Graph China, covering mail reading and sending, calendar conflict checks, OneDrive and SharePoint file search, Teams, contact | |
| planejar_pedido_em_grupo anapbatista/copiloto-parceiro Enables group food ordering by interpreting group messages and private budgets, matching requests to menu items, and computing an exact optimized order across at most two restaurants while enforcing per-person spending limits and minimum-or | |
| readscout anarchiejs/readscout Enables coding agents to delegate the reading of large files, folders, and long logs to local models, returning short answers whose every claim is backed by a quote verified word for word in the source with its real file:line. Everything ru | |
| ui-annotate anarchyghost/ui-annotate Serves coding agents the annotations users leave on elements of a running dev app, including the element selector, DOM context, component name and exact source file:line. Agents can list and watch for pending feedback, link a page to their | |
| nina-mcp anarcoiris/nina-smart-scheduler Enables AI agents to control N.I.N.A. astronomy software remotely, including mount, camera, sequencer, and other equipment via the ninaAPI plugin. | |
| YouTube MCP Server anarcyst/youtube-mcp-server A zero-config server that enables searching YouTube videos, retrieving transcripts, and browsing channel data without requiring API keys. It allows users to search across a creator's entire content library to find specific passages and time | |
| Universal DB MCP anarkh-lee/universal-db-mcp Enables Claude Desktop to interact with MySQL, PostgreSQL, and Redis databases using natural language for data querying and schema analysis. It provides a secure interface with a default read-only mode to prevent unauthorized database modif | |
| Postman MCP Server anarsyakir/postman-mcp Enables interaction with Postman workspaces, collections, requests, responses, and monitors through the Postman API. Allows users to manage API collections, create and update requests/responses, and execute monitors directly from chat. | |
| mermaid-mcp anas-alward/mermaid-mcp Enables AI agents to list, read, create, update, and delete Mermaid diagrams and collections via the Mermaid REST API over stdio or stateless Streamable HTTP. | |
| AchPay anas-github-acc/achpay Enables AI agents to securely search products, obtain signed quotes, create checkouts, and track orders without directly handling prices or payment amounts, enforcing spending policies and audit trails. | |
| AgentQL MCP Server anas6260/agentql-mcp Enables extracting structured data from web pages by supplying a URL and a prompt that describes the desired fields. Exposes an extract-web-data tool for MCP-compatible clients. | |
| Instagram MCP Server anas7272/instagram-mcp A professional MCP server for managing and posting Instagram content, including PDF-to-image conversion, carousel batches, auto-posting, and Cloudinary hosting. | |
| outlook-classic-mcp anasahmed07/outlook-classic-mcp Enables MCP-aware agents to interact with the classic Outlook desktop client for mail, calendar, contacts, tasks, and Out-of-Office settings via the COM API, without Azure or OAuth. | |
| TradingView MCP Bridge anasbalochh/tradingview-mcp Enables AI-assisted chart analysis, Pine Script development, and workflow automation by connecting to a locally running TradingView Desktop app via Chrome DevTools Protocol. | |
| Classroom Suite MCP anasdevai/classroom-suite-mcp Unified MCP server for Google Classroom, Drive, and Docs, enabling AI assistants to manage courses, assignments, files, and documents. | |
| MCP Code Mode anaseqal/codemode Universal Python code execution MCP server that lets LLMs write and run Python for any task, with auto-install packages, streaming output, and automatic file display. | |
| AWS SecurityHub MCP Server anaskhillo/aws-securityhub This server implements the Multi-Agent Conversation Protocol for AWS SecurityHub, enabling interaction with AWS SecurityHub API through natural language commands. | |
| ACA PoC MCP Tools Server anasmithdell/mcp_tools Provides financial audit reporting and ledger query tools for AI agents, enabling generation of compliance, risk, and transaction reports and querying of transaction data, balances, and summaries from an in-memory SQLite database via MCP. | |
| ACA PoC MCP Tools Server anasmithdell/mcp_tools_vulnerable Enables AI agents to generate audit reports and query financial ledger data via MCP. This demo version contains intentional security vulnerabilities for security testing and should not be used in production. | |
| JIAD Bukku MCP anasmotawh/jiad-bukku-mcp Enables AI assistants to securely access and work with JIAD accounting and finance data in Bukku through a remote MCP endpoint. | |
| Stock Analysis MCP Server anasosama2/financial-stock-analysis-mcp Provides financial stock analysis for U.S. public companies via SEC EDGAR APIs, offering tools to resolve companies, retrieve filings, calculate profitability metrics, compare periods, detect red flags, and get audit evidence, all without A | |
| Qevyra anasrz/qevyra Gives AI agents a single MCP interface to discover, inspect, scope, and execute external capabilities—downstream MCP servers, HTTP APIs, and local tools—resolved on demand from a local index instead of preloaded catalogs. Enforces agent sco | |
| Intelligent PostgreSQL MCP Client anass1209/mcp_postgresql Enables natural language querying of PostgreSQL databases with intelligent SQL generation using LLMs. | |
| Shopify MCP Server anass319/shopify-mcp Enables interaction with Shopify store data via the GraphQL Admin API for managing products, customers, and orders. It allows users to search, retrieve, create, and update store records through natural language commands. |
28,451–28,500 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.