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 |
|---|---|
| cheminformatics_mcp_headless asinansaglam/cheminformatics_mcp_headless A self-driving cheminformatics MCP server that dynamically exposes a growing library of RDKit-based molecular analysis tools (fingerprints, descriptors, substructure matching, drug-likeness filters, and more) as MCP tools, with each skill a | |
| Local Snowflake MCP Server asingh49-cmd/local-snowflake-mcp-server Enables Claude Desktop to interact with Snowflake databases through natural-language SQL queries. Built in Python, it allows secure local integration between LLMs and enterprise data systems for database operations and analysis. | |
| dnd-5e-mcp asinkluno/dnd-5e-mcp Enables an LLM to search the D&D 5e (2014) rule catalogue and fetch any wiki page as Markdown. | |
| Prelo MCP Server asiqueira1973/prelo-mcp MCP server for Prelo, the Brazilian literary releases aggregator. Enables searching the catalog by month, publisher, or author. | |
| LinkedIn MCP Server asisaga/linkedin.asisaga.com Enables AI assistants to interact with LinkedIn using the official API for profile access, company management, and job postings. | |
| agent-gateway asish-singh/mcp-site-gateway Converts any website into an MCP server, enabling AI assistants to search and interact with the site beyond just reading. | |
| SheetMaster Todo MCP asisrasyid/mcptodo Enables managing boards, tasks, subtasks, labels, and assignees in a Google Apps Script-backed todo system through MCP tools, with secure API key authentication and remote deployment support. | |
| ContextForge asit-piri/agentic-knowledge-to-action An open source registry and proxy that federates MCP, A2A, and REST/gRPC APIs with centralized governance, discovery, and observability. It optimizes agent and tool calling, and supports plugins. | |
| openact asjames18/openact Exposes every installed .act.yaml blueprint as a deterministic MCP tool, letting AI agents fetch structured data or perform actions from websites and portals via a tiered HTTP, HTML-extraction, and headless-browser fallback chain. This repl | |
| eigen-plc-mcp asjnk/plc-mcp Enables AI agents to generate and validate Siemens S7-1200 SCL code from process descriptions, leveraging an industrial automation knowledge base. | |
| agenticflow ask-me-anything-dot-work/agenticflow Self-hosted MCP gateway that connects productivity tools like Jira, Confluence, and Obsidian to AI assistants via a single endpoint. | |
| @ama-work/mcp-atlassian ask-me-anything-dot-work/ama-mcp-atlassian Enables interaction with Atlassian Jira and Confluence via their REST API, providing tools for searching, creating, updating, commenting, and retrieving issues, pages, projects, and spaces. | |
| dsh-mcp ask33r/omp-dsh-workers Enables Claude Code to act as a director of persistent DeepSeek Harness (DSH) workers through six tools — dsh_spawn, dsh_wait, dsh_list, dsh_kill, dsh_send, and dsh_answer — using blocking polls instead of push events. | |
| askahuman-mcp askahumanonline/askahuman-mcp-server An MCP server that enables AI agents to request human verification for tasks requiring real-world understanding, paying via the Lightning Network, and receiving verified answers. | |
| zentao-mcp askairo/zentao-mcp Provides an MCP server for ZenTao (禅道) project management. It enables read-only queries for projects, tasks, bugs, users, and stories, and supports write operations like task assignment, progression, and bug resolution when explicitly confi | |
| MCP Starter Server askarthikey/mcp-prac Provides a Model Context Protocol server with tools for arithmetic and system status, resources for info and configuration, and prompts for code review and summarizing meeting notes. | |
| Cal MCP Server askcal/cal-mcp-server Enables AI assistants to answer mortgage-related queries by providing tools for lender search, loan limit lookup, down-payment assistance programs, and more, with data sourced from real wholesale lenders and broker-curated intel. | |
| pgroonga-mcp askdkc/pgroonga-mcp Provides read-only PostgreSQL search and diagnostics over Model Context Protocol, using PGroonga indexes for full-text search, normalization, and variant lookup. | |
| ai-disclosure askeleven/ai-disclosure Enables AI agents to ask, before sending each message, whether disclosure laws require them to admit they are an AI, returning the rules in force with citations and suggested wording. It also grades recorded conversations against 47 US, EU, | |
| bot-tells askeleven/bot-tells Enables an agent to check its own drafted messages for the wording, leaked placeholders, and chat wrappers that make readers think a bot wrote them, returning a verdict, 0-100 score, and per-finding suggestions. It also applies the safe fix | |
| loop-breaker askeleven/loop-breaker Checks a message thread before an agent replies, returning a keep/review/fail verdict with the reasons behind it so replies to autoresponders, bounces, or other bots are stopped. Also classifies single messages and, with a ledger, records s | |
| prompt-fence askeleven/prompt-fence Enables agents to scan incoming emails, web pages and messages for instructions aimed at the AI, wrap that untrusted content in a nonce-bounded fence the content cannot forge, and expose a check_action tool so the model's tool calls can be | |
| send-guard askeleven/send-guard Enables agents to verify an email list before sending, returning a pass/fail plus keep, remove, and review categories with reasons. It exposes check_emails and check_file tools over stdio, with optional Analyzemail mailbox verification. | |
| sms-guard askeleven/sms-guard Enables agents to validate a text message before sending it, checking segment count and encoding, recipient local send time, and opt-out wording, and to split an over-long message into ordered parts that each fit. It exposes check_sms and s | |
| cfmail askie/cfmail Enables AI agents to autonomously receive, search, read, reply to, and forward email through a self-hosted Cloudflare service accessible via MCP or CLI, with no web interface. | |
| cloudflare-email askie/cloudflare-email An MCP server that receives emails on your domain and allows AI assistants to search, read, and manage them via natural language queries. | |
| fortra-fim-mcp askjarv/fim-mcp MCP server for interacting with Tripwire Enterprise REST API, enabling file integrity monitoring workflows such as node management, policy tests, element versioning, and promotions. | |
| Wallet MCP Server askjimmy/getonyx-mcp Enables AI agents to generate or import multi-chain keys, sign messages and unsigned transactions, broadcast them, and query native balances across Ambient, Solana, BSC, and Arbitrum. Private keys stay encrypted on the local machine, so age | |
| Doc Scraper MCP Server askjohngeorge/mcp-doc-scraper Converts web-based documentation into markdown format using jina.ai's conversion service, allowing users to scrape documentation from any URL and save it as markdown files. | |
| Asklear Browser MCP asklear/asklear-browser-mcp A local stdio MCP server that drives your Chrome browser through the Asklear extension, offering six browser tools for navigation, observation, clicking, filling, scrolling, and extraction — all operations remain on your machine. | |
| open-docs-mcp askme765cs/open-docs-mcp An open-source MCP implementation providing document management functionality.
This project aims to replicate Cursor's @Docs functionality. | |
| supabase-mcp-guard askmeishi/supabase-mcp-guard A local policy wrapper for Supabase MCP that secures access tokens and enforces strict execution models, including project allowlists and write-access restrictions. It provides a safety layer to prevent AI agents from accidentally executing | |
| Expense Tracker MCP askmohan/mcp Stores and manages expenses in SQLite. Enables adding, removing, and listing expenses with filtering, and exposes expense categories via a resource. | |
| memex askmohanty/memex Centralized agentic memory and MCP gateway for LLMs, enabling persistent memory recall, validation, and integration with upstream MCP servers. | |
| Surf MCP Server asksurf-ai/surf-mcp Enables access to 86 crypto data endpoints from the Surf API, including market data, wallets, social sentiment, on-chain queries, and more, through dynamically generated MCP tools. | |
| gmail-mcp asktree/gmail-mcp Lets Claude search, read, draft, send, label, archive, and trash Gmail threads using Gmail query syntax, with Google sign-in handled through a self-hosted remote connector and an email allowlist. Access is scoped to gmail.modify, so nothing | |
| IDB-MCP askui/idb-mcp MCP server to control iOS simulators for automation, enabling device management, input control, and screen capture via Facebook IDB. | |
| mcp-server-atlassian-jira asky74/mcp-server-atlassian-jira An MCP server for interacting with Atlassian Jira, enabling issue management, attachments, and other operations via natural language. | |
| idapin-mcp askyeye/idapin-mcp Enables any MCP-capable AI to headlessly launch and dynamically instrument Windows executables via IDA Pro's PIN tracer, with tools for breakpoints, register/memory access, execution control, and instruction tracing without opening the IDA | |
| Clockify MCP Server aslamanver/mcp_clockify Enables AI assistants to interact with Clockify time tracking API to manage time entries, projects, tasks, and workspaces through natural language commands. | |
| Hyperlink aslamwebz/hyperlink Enables AI agents to connect once to a local MCP endpoint and access tools from all configured MCP servers, add or remove connectors live, and generate sandboxed connectors for services that lack one. It centralizes multi-server access whil | |
| temporal-invoice-mcp aslan11/temporal-invoice-mcp Enables managing invoice workflows using Temporal, allowing submission, approval, rejection, and status checking of invoices through MCP tools. | |
| mcp-switchboard aslanpour/mcp-switchboard Intelligent MCP server orchestrator that automates configuration, orchestration, and lifecycle management of other MCP servers for AI agents. | |
| S&P 500 MCP Server asli05142/sp500-mcp-server Enables querying S&P 500 company data from Supabase, including company fundamentals, annual financial metrics, historical OHLCV price data, news with sentiment filtering, executive officers, and SEC filings. It supports elicitation to disam | |
| Matryoshka asli179/matryoshka Enables analysis of documents far larger than an LLM's context window without vector databases or chunking, by having the model emit constrained symbolic S-expression commands that a logic engine parses, validates, and executes over the sou | |
| msw-mcp asli57817/msw-mcp Enables AI agents to dynamically add, update, and remove Mock Service Worker network mocks at runtime, without reloading the browser or restarting the application. It also scaffolds MSW setups and brokers handler updates to the browser over | |
| Deep Code Reasoning MCP Server aslimazur573/deep-code-reasoning-mcp It enables Claude Code to route complex code analysis tasks to Google Gemini, supporting execution-flow tracing, cross-system impact analysis, performance bottleneck detection, and hypothesis testing over large codebases and logs. | |
| LeetCode MCP Server aslimitchell176/leetcode-mcp-server Enables automated access to programming problems, contests, official editorials, user-submitted solutions, and user profiles on both leetcode.com and leetcode.cn. Optional session-cookie authentication unlocks private features such as notes | |
| LINE OA MCP Ultimate aslimitchell176/line-oa-mcp-ultimate Lets AI agents run one or many LINE Official Accounts through natural conversation, covering broadcasts, Flex and tappable Rich Messages, Thai-ready rich menus, coupons, audiences, insights, and LINE Shopping via 51 tools. It adds pre-fligh | |
| kali-mcps aslin75978/awsome_kali_mcpservers Enables running Kali Linux security tools through an MCP client, including Nmap network scanning, nm symbol analysis, objdump binary disassembly, strings extraction, and tshark traffic capture. It also provides a Docker-based sandbox for is |
31,251–31,300 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.