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 |
|---|---|
| HKUST Canvas MCP amzonmeeee/hkust_canvas_mcp Enables users to access and manage course data, assignments, grades, announcements, discussions, pages, modules, and files from their institution's learning management system via terminal commands or MCP-compatible AI agents, including prev | |
| atlassian-mcp amzu-dev/atlassian-mcp Enables Claude and Claude Code to interact with Atlassian Cloud (Confluence and Jira) through natural language, supporting full CRUD operations, search, comments, and attachments. | |
| akm-mcp an-idd/stillyou This MCP server enables AI agents to manage artifacts across sessions by providing tools for searching, retrieving, and registering entries in a persistent ledger, ensuring consistency and traceability of agent outputs. | |
| mcp-security-compliance an0malous/mcp-custos Integrates authoritative security compliance frameworks (ISO 27001, NIST 800-53, OWASP ASVS, NIST SSDF) into AI-assisted development, offering control lookups, cross-framework mappings, build-time guardrails, and automated audit evidence ge | |
| Fatebook MCP Server an1lam/fatebook-mcp Enables AI assistants to create, manage, and track predictions on Fatebook, a prediction tracking platform. Supports making forecasts, updating probabilities, resolving questions, and managing prediction history through natural language. | |
| MCP Database Server an8888allen-maker/mcp-database-server Enables Claude to connect to and interact with SQLite, SQL Server, PostgreSQL, and MySQL databases through natural language. Supports executing queries, managing tables, exporting data, and storing business insights with authentication opti | |
| Snippy ana16267/snippy Enables AI assistants to save and retrieve code snippets with vector-embedding semantic search, and to generate language-specific style guides or wiki documentation from them. It also orchestrates multi-agent workflows that combine these ca | |
| Meta Ads MCP Server ana1729/meta-mcp Enables account setup, campaign/ad set/creative/audience management, reporting insights, and batch workflows against the Meta Marketing API, with OAuth-backed multi-tenant workspace authentication. | |
| Frappe MCP ana8729/mcp Enables Frappe Framework applications to act as Streamable HTTP MCP servers, exposing registered Python functions as tools that MCP clients and LLMs can discover and call. | |
| MCP Jenkins ana8729/mcp-jenkins Enables secure, contextual AI interactions with Jenkins tools, allowing users to query items, manage builds, inspect nodes, views, and plugins, run Groovy scripts, and more through natural language while maintaining data privacy and securit | |
| IMAP MCP Server ana91536/imap-mcp-server Enables AI assistants to connect to multiple IMAP and SMTP mailboxes for searching, reading, sending, replying, forwarding, organizing, and bulk-deleting email. Credentials are stored with AES-256 encryption, with connection pooling, folder | |
| Google Docs + Gmail MCP Server anaagh05/mcp-server Enables appending content to Google Docs and creating Gmail drafts via a lightweight MCP-style server with OAuth authentication and human-in-the-loop approval. | |
| gdrive-write-mcp anaborne/gdrive-write-mcp Enables AI assistants to make real in-place edits to Google Drive files—preserving file IDs, revision history, comments, and sharing—while also supporting appends, targeted find-and-replace, reads, searches, and file creation. | |
| gmail-multi-mcp anaborne/gmail-multi-mcp Enables simultaneous management of multiple Gmail accounts through MCP, allowing per-account reads and writes with verified labels and parallel search across all mailboxes. | |
| Interactive Curriculum MCP Server anacatavc/anacatalina-mcp Enables AI assistants and LLM clients to query a professional CV and portfolio, including work history, technical skills, projects, job compatibility evaluation, education, and contact details. | |
| ollama-search-mcp anaconda110/ollama-search-mcp Enables MCP clients to search the live web and fetch any URL as clean text through Ollama's web search and fetch APIs, returning ranked results with page text and outgoing links. Runs as a single dependency-free stdio server, so agents can | |
| Bygglov Ärendesystem MCP Server anadolf/bygglov-arendesystem-mcp-demo Enables interaction with a Swedish building permit case management system, allowing case overview, listing, retrieval, summarization, status updates, note addition, and creation of cases through natural language. | |
| Recall anafedorov/recall Enables Claude and other AI agents to persistently store, retrieve, and organize memories across sessions, surviving restarts and context compaction, with optional team sharing via managed cloud or self-hosted Redis/Valkey storage. | |
| MCP Flow anagai/mcp-flow Enables turning existing REST APIs into governed, agent-callable MCP servers by analyzing OpenAPI schemas, generating tool definitions, and gating releases behind automated evals. | |
| Sentinel-MCP anahadhbirdh/sentinel-mcp Extensible trading-intelligence MCP server with diagnostic tools, structured logging, and tool registration; currently provides server info tool with plans for market data adapters. | |
| Anahita MCP anahitasocial/anahita-mcp Enables MCP clients to search and read Anahita's documentation and API reference locally, so agents can answer current questions about setup, federation, routes, parameters, and response shapes, including offline from cached copies. | |
| Niblet anaik469/niblet-skill-mcp Enables coding agents to ground UI work in real product screens by returning concrete screen references as inline images, licensed fonts, icons, and the colors, typography, and components behind a chosen web screen. It also serves token-fre | |
| kubera-3p-mcp anaisbetts/kubera-3p-mcp MCP server that exposes a typed TypeScript client for the Kubera (api.kubera.com) REST API, enabling users to access their financial data (user info, portfolios, charts) via Cognito-authenticated tools, including white-label account support | |
| stonex-mcp anaisbetts/stonex-mcp MCP server exposing StoneX Client REST API endpoints as tools, enabling account balances, positions, activity, and performance retrieval via natural language. Requires a user-supplied access token or session cookie. | |
| figma-mcp anakintano/figma-mcp Enables AI agents to read, inspect, and export Figma designs programmatically. Provides tools for listing components, styles, and exporting assets in various formats. | |
| agent-session anaknegeri/agent-session Universal session & handoff layer for AI coding agents: shared task, decision, blocker and test state, checkpoints, and deterministic handoff between Claude Code, Codex, OpenCode, Cursor, Cline, pi and omp. Local SQLite, git-aware, 25 tools | |
| mcp-virustotal analeclerc546/mcp-virustotal Enables AI agents to query the VirusTotal v3 API for detection reports and analyst-style pivots on files, URLs, IPs, and domains, including contacted hosts, dropped files, resolutions, and threat actors. Provides relationship paging, corpus | |
| yahoo-furigana-mcp analekt/yahoo-furigana-mcp Adds furigana (reading) to Japanese text using Yahoo! JAPAN's Furigana API, supporting multiple output formats like HTML ruby, brackets, and roman. | |
| Firestarter MCP Server analog-labs/firestarter-mcp Enables AI assistants to search real products, purchase with user approval, track deliveries, and run a seller business end to end via the Firestarter commerce platform. | |
| robotsshop-mcp analoghubris/robotsshop-mcp MCP server for verifying agent payment integrity on x402, providing tools to check payTo mismatches, market stats, and lookup endpoints. | |
| ViraStack Agent Bridge analogpi/virastack-agent-bridge Enables any MCP or shell-capable agent to interact with native ViraStack tasks in Cadence Virtuoso, including selecting sessions, submitting requests, polling jobs, cancelling tasks, and replying to pending questions. | |
| Playwrightium analysta-ai/playwrightium An MCP server for browser automation that allows AI to perform web tasks using Playwright through direct commands, reusable YAML shortcuts, or custom scripts. It features secure environment variable management and guided automation creation | |
| BinanceMCPServer analyticace/binance-mcp-server AnalyticAce | |
| snowflake-analytics-mcp-server analytics-model-ltd/snowflake-analytics-mcp-server An MCP server for Snowflake that enables table discovery, metadata inspection, and SQL query execution through natural language, supporting password, key-pair, and OAuth authentication. | |
| ga4-mcp analyticsrhd/ga4-mcp Enables MCP clients to directly access Google Analytics 4 data, including property metadata, custom dimensions and metrics, reports, real-time reporting, annotations, and Google Ads links. | |
| inbound-guard analyzemail/inbound-guard Enables an agent that reads a person's inbox to check a raw or .eml message and receive a 0-100 cold-outreach score with the reasons behind it. The agent can then avoid replying on the person's behalf to a cold message, or surface a likely | |
| Analyzemail MCP Server analyzemail/mcp Enables an AI agent to verify a single email address in real time, clean an entire uploaded list file with per-address verdicts, and download the results as CSV with the addresses that are safe to send to. It runs on npm with zero dependenc | |
| Anam MCP Server anam-org/anam-mcp Enables managing AI personas, avatars, voices, and sessions from any MCP client, for integration with Anam AI. | |
| Proto OS anamized/proto-os Provides a JSON-RPC MCP server that exposes policy-governed agent tools, including paid tools, tool muxing, and OpenAPI-to-MCP conversion, enabling agents to discover, coordinate, and execute tasks within the ProtoOS ecosystem. | |
| BOE & EUR-Lex MCP Server anamtb/boe-mcp Enables querying and analyzing Spanish (BOE) and EU (EUR-Lex) legal documents, with advanced search, PDF extraction, and cross-reference detection. | |
| mcp-indesign-agent anananaterra/mcp-indesign-agent MCP server for editing Adobe InDesign via natural language in Cursor. It bridges to InDesign through AppleScript and ExtendScript, providing semantic tools for batch operations, styles, assets, and layout fixes. | |
| Insta MCP Server anand-kamble/mcp-instagram MCP server that enables integration with Instagram, allowing interaction with Instagram features through the Model Context Protocol. | |
| Multi-Cloud MCP Server anandapurva55/multi-cloud-mcp-server Enables LLM clients to inspect and query your own GCP and AWS infrastructure, including BigQuery/Athena, CI build systems, container/serverless runtimes, and their logs through configurable environments. | |
| multi-source-mcp-benchmark anandapurva55/multi-source-mcp-benchmark Enables reproducible evaluation of AI agents on multi-source evidence investigation tasks, providing Docker-based scenarios, MCP tools, and automated scoring for payout reconciliation, performance-claim verification, and incident reconstruc | |
| bleurs anandb71/bleurs MCP server for Python API verification and projection, enabling AI coding agents to detect non-existent APIs and retrieve exact API surfaces before writing code. | |
| CargoMind MCP Server anandb71/cargomind Enables agents and clients to query shipments, lanes, trucks, SKUs, routes, inventory, dispatch, and proactive logistics alerts across an India-wide 3PL network. | |
| Chrome History & Bookmarks MCP Server ananddharne/chrome-history-mcp-server Enables AI assistants to search and analyze Chrome browser history and bookmarks data locally, including keyword searches, date range filtering, recent browsing activity, and usage statistics across all platforms. | |
| Copy-Paste MCP ananddtyagi/copy-paste-mcp A Model Context Protocol server that provides a tool for extracting specific line ranges from text content while preserving exact formatting and newlines. | |
| Remote MCP Server anandkumarpatel/remote-mcp-server A Cloudflare Workers-based implementation of Model Context Protocol (MCP) server that enables AI assistants like Claude to access external tools and capabilities through a standardized interface with OAuth authentication. | |
| Remote MCP Server Authless anandkumarpatel/remote-mcp-server-authless A serverless Model Context Protocol implementation on Cloudflare Workers that enables AI tools without requiring authentication, allowing connection from AI Playground or Claude Desktop. |
28,401–28,450 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.