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 |
|---|---|
| Firefox DevTools MCP bam-devcrew/maxerviker-firefox-devtools-mcp Model Context Protocol server for automating Firefox via WebDriver BiDi, enabling page navigation, snapshots, input, network monitoring, and console debugging for AI agents in MCP clients. | |
| mcp-asterisk-socle bamba4700/mcp-asterisk-socle Provides a secure foundation for Asterisk PBX supervision via MCP, with role-based access control, JWT authentication, and mandatory human confirmation for control actions. | |
| gpt-mcp bambara123/gpt-mcp A local MCP server that enables Claude to generate images using the OpenAI API. | |
| mcp-skatteetaten bambinobino/mcp-skatteetaten Enables AI assistants to query Norwegian tax data, submit reports, look up population register information, and validate VAT returns through Skatteetaten APIs using Maskinporten authentication. | |
| Houdini MCP Server bamboovfx/houdini-mcp-codex Enables AI assistants to control SideFX Houdini 3D software, providing tools for scene management, node operations, rendering, and more through the Model Context Protocol. | |
| nextcloud-collectives-mcp bambutz/nextcloud-collectives-mcp A MCP server for accessing Nextcloud Collectives, allowing MCP clients to list, read, and edit collectives, their pages, and tags. | |
| Ghidra MCP Server bamimore-tomi/ghidra_mcp Enables LLMs to perform binary analysis using Ghidra in headless mode, extracting functions, pseudocode, structs, and enums from binaries for interactive reverse-engineering. | |
| BASH-CMS bamr87/bash-cms Enables governed LinkedIn company-page publishing from a VS Code extension's MCP server, with read-only tools for account info, post preview, and a draft tool for creating pending posts, plus an optional publish tool that is off by default | |
| BananaCrystal MCP Server bananacrystal/mcp-server-bananacrystal Provides AI agents with a wallet and autonomous payment capabilities using stablecoins, enabling seamless micropayments and financial operations with under 5-second settlement on Hedera. | |
| TrainingPeaks MCP Server banananovej-chuan/tp-mcp-server A Model Context Protocol server for TrainingPeaks with an analytics focus — enabling real-time querying of training data, performance trends, CTL/ATL/TSB analysis, and training load optimization through Claude Desktop. | |
| bambu-studio-mcp bananarama123/bambu-studio-mcp Enables plain-English slicing guidance, profile discovery and comparison, 3MF/STL inspection and optimization, headless slicing with cost/time metrics, GUI automation, and live printer/AMS monitoring and control for Bambu Lab 3D printers. | |
| foglift-mcp banant2/foglift MCP server for website SEO + GEO analysis. Scan any URL to get scores across 5 categories (SEO, GEO, Performance, Security, Accessibility) with actionable fix recommendations. Enables AI coding assistants to audit websites and implement fix | |
| Passport MCP Server banarasi/passport-mcp-server Enables natural-language interaction with the Passport ELM legal matter-management system, including creating, enriching, searching, and submitting matters, budgets, allocations, and entitlements, with deterministic business rules and audit | |
| Salesforce MCP Server banburger/salesfoce-mcp-server Enables Claude to query, create, update, and delete Salesforce records directly using SOQL and SOSL, with tools for metadata exploration and bulk operations. | |
| Claude Session Coordinator bancs-norway/claude_session_coordinator A flexible MCP server enabling multiple Claude AI sessions to coordinate work across machines through shared state management. | |
| Thenvoi MCP Server band-ai/band-mcp Provides seamless integration with the Thenvoi AI platform, enabling AI agents and users to manage agent identities, create and participate in chat rooms, send messages with mentions, post execution events, and manage conversation lifecycle | |
| Pendo Ontology MCP Server band-aid/pendo-ontology-mcp A semantic ontology layer for Pendo that enables users to define and manage business concepts, entity relationships, and measurement hints, grounding LLM queries in workspace-specific definitions. | |
| MCP API Gateway bandageok/mcp-api-gateway A unified local API gateway providing caching, rate limiting, and full Model Context Protocol compatibility for AI agent integration. It enables users to aggregate multiple API endpoints into a single gateway with built-in observability and | |
| Log Analytics MCP Server bandarudheeraj/log-analytics-mcp-server A Model Context Protocol server that enables AI agents to query Azure Log Analytics workspaces using KQL. | |
| TestFlight Feedback MCP Server bandarudheeraj/testflight-feedback-mcp Enables AI assistants to access TestFlight beta tester feedback, including screenshots, crash logs, and text comments from App Store Connect. It works across any platform without requiring Xcode, using official API keys and optional browser | |
| Personal AIVA MCP Bootstrap banddude/aiva-bootstrap A self-hosted MCP server that gives ChatGPT controlled access to a user's Oracle Cloud Ubuntu VM through tools for shell commands, file operations, and personal skills. | |
| ModAST-MCP banderzhm/modast-mcp Module-aware AST MCP server for C++20/23 projects using clangd for AST/LSP operations and a source-level module index, enabling module graph queries, references, diagnostics, and code formatting. | |
| MCP API Catalog Recommender bandham-manikanta/mcp-catalog-agent Enables semantic search over an OpenAPI catalog to find and recommend API endpoints based on natural language queries. | |
| Ghostlight banditburai/ghostlight A QA verification MCP server that prevents AI hallucination by using adversarial verification with screenshots and subagents for accessibility, visual regression, and UI verification. | |
| Hunt-Droid Mobile MCP banditpradyun/hunt-droid-mobile-mcp An MCP server that enables AI agents to drive real Android apps, capture API traffic, and test mobile-native attack surfaces, similar to Playwright for mobile. | |
| Bandwidth MCP Server bandwidth/mcp-server Official MCP server for interacting with Bandwidth APIs (messaging, voice, number lookup, etc.) via AI agents. Supports configurable tool filtering and multiple deployment modes. | |
| approval-guardian baneado98/approval-guardian Analyzes a wallet's active ERC-20 token approvals and provides prioritized risk assessment along with revoke calldata. | |
| brandguard baneado98/brandguard Scans npm, PyPI, and GitHub for typosquatting and brand impersonation, risk-scores findings, and drafts takedown notices. | |
| calldata-guardian baneado98/calldata-guardian Decodes Ethereum calldata and returns a safety verdict with plain-English explanations of what the transaction does, flagging dangerous actions like unlimited approvals or gasless permits. | |
| chain-data baneado98/chain-data Enables AI agents to fetch live multi-chain portfolio, token info, gas prices, and token prices across Ethereum, Base, Polygon, Arbitrum, and Optimism with a single call. No API key required. | |
| ChainID Guard baneado98/chainid-guard MCP server that gates premium features behind a combined x402 (USDC per call) and Stripe API key paywall, ensuring only paying users access deep functionality while free tier runs locally. | |
| contract-auditor baneado98/contract-auditor Quick-scan a smart contract for rug, honeypot, or centralization risk before sending funds. It combines verified source, live on-chain state, and heuristic Solidity analysis to return a SAFE/CAUTION/HIGH-RISK verdict. | |
| CORS Doctor MCP Server baneado98/cors-doctor Enables CORS diagnostics with a free local tier and a premium server-side tier gated by payment. | |
| dmarc-doctor baneado98/dmarc-doctor A template MCP server with a built-in paywall gate, enabling free local execution and paid premium server-side execution via Stripe or x402. | |
| dnsdoctor baneado98/dnsdoctor An MCP server that checks SPF, DKIM, DMARC, and MX records for a domain, returning a health verdict and specific DNS fixes to improve email deliverability. | |
| email-verify baneado98/email-verify Enables real-time email verification via MCP tools, checking syntax, MX, disposable domains, and optional SMTP probe to determine deliverability with a VALID/RISKY/INVALID verdict. | |
| Header Doctor baneado98/header-doctor A template for MCP servers that enforces a paywall gate, offering free local execution and monetizing premium features via Stripe or x402 payments. | |
| ip-doctor baneado98/ip-doctor MCP server for live IP and domain reputation checks via DNS lookups, providing abuse scores and network type without requiring an API key. | |
| JWT Doctor baneado98/jwt-doctor Template for creating MCP servers with a server-side paywall gate, enabling free local usage and premium hosted tier with Stripe and x402 payment lanes. | |
| jwt-doctor-mcp baneado98/jwt-doctor-mcp Enables AI agents to audit JSON Web Tokens (JWTs) and other token formats for security vulnerabilities, including HMAC secret cracking, live JWKS verification, and CVE fingerprinting. | |
| license-guardian baneado98/license-guardian Audits npm dependencies for license compatibility, catching copyleft and source-available traps before shipping. | |
| lockfile-guardian baneado98/lockfile-guardian Audits your package-lock.json for supply-chain attacks before install. Cross-checks every resolved entry against the live npm registry to detect integrity mismatches, new install scripts, and other malicious signals. | |
| Mempool Doctor baneado98/mempool-doctor Enables blockchain mempool analysis with a free tier for basic queries and a premium tier for deep analysis, gated by a server-side paywall. | |
| npm-guardian baneado98/npm-guardian Audits npm packages for supply-chain attacks (typosquatting, malicious install scripts, credential exfiltration) before installation, returning a SAFE/SUSPICIOUS/DANGEROUS verdict. | |
| OpenAPI Doctor baneado98/openapi-doctor A template for building MCP servers with a built-in paywall gate that offers free local execution and premium server-side execution via Stripe and x402 payment lanes. | |
| rug-check baneado98/rug-check On-chain rug-pull & honeypot risk screen for ERC-20 tokens, providing a SAFE / CAUTION / HIGH-RISK verdict based on live public RPC reads. | |
| secret-scanner baneado98/secret-scanner Enables scanning diffs or code blobs for leaked secrets, returning a verdict with severity and masked findings, all processed locally with no data sent externally. | |
| solidity-sentinel baneado98/solidity-sentinel Enables static security audit of Solidity smart contracts by analyzing source code or deployed bytecode for vulnerabilities, providing risk scores and detailed findings. | |
| ssl-doctor baneado98/ssl-doctor Enables live TLS/SSL certificate health checks for any hostname, providing expiry, hostname match, trust verdict, and a health score. Supports both free and paid deep tiers with protocol/cipher analysis. | |
| web-doctor baneado98/web-doctor Enables live website health checks including TLS, HTTPS, and security headers, returning an A-F grade with specific fixes. |
32,851–32,900 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.