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 |
|---|---|
| agentguard agentguard-run/agentguard-mcp Enables local spend caps and Ed25519-signed provenance receipts for AI agent tool calls, allowing any MCP host to gate model usage and independently verify signed decisions without sending prompts or content. | |
| recon-crypto-mcp agenthill/vaultpilot-mcp Self-custodial crypto portfolio and DeFi MCP server. Read balances and positions (Aave, Compound, Morpho, Uniswap V3, Lido, EigenLayer) across Ethereum, Arbitrum, Polygon, and Base, and prepare transactions for approval on a Ledger via Wall | |
| dealdesk-mcp agenthouse-org/dealdesk-plugin Enables AI hosts like Claude, ChatGPT, Cursor, Codex, and Copilot to connect to DealDesk for working with cards, quotes, CPQ portfolio, directory, and export. | |
| agent-observability-mcp agentia1984-cmd/agent-observability-mcp MCP server for AI agent observability, providing trace and span logging, search, latency/tokens/cost metrics, and anomaly detection using an in-memory buffer. | |
| fr-compliance-mcp agentia1984-cmd/fr-compliance-mcp French compliance and KYC MCP server offering VAT validation (VIES), BODACC legal announcements, and company risk scoring using open data. | |
| conformite-ia-mcp agentia1984-cmd/mcp-conformite-ia Provides an AI agent with regulatory compliance tools for the French/European market based on the AI Act and GDPR, including system classification, obligation listing, deadline schedules, legal reference lookup, and GDPR crosschecks. | |
| MCP Immobilier France (DVF) agentia1984-cmd/mcp-immobilier-dvf Provides AI agents with real-time access to French real estate transaction data, price per square meter, and property estimates using official open DVF data, with no API key required. | |
| mcp-marches-publics agentia1984-cmd/mcp-marches-publics Provides tools to search and retrieve French public procurement data (tenders, awarded contracts) and company information from official open APIs. | |
| risques_territoire_mcp agentia1984-cmd/mcp-risques-territoire Assess natural and technological risks for French addresses or communes using open APIs (Géorisques, Base Adresse Nationale). | |
| Agentic Actions for Laravel agentic-actions/demo Enables MCP clients to read, summarize, create, update, and delete tasks on a team task board according to the caller's tenant and role. It also supports running the same board operations exposed to forms, JSON routes, Artisan, and the copi | |
| bfl-flux-mcp agentic-ai-forge/bfl-flux-mcp Minimal Python MCP server for Black Forest Labs Flux image generation API, providing tools for text-to-image, editing, expansion, variations, and credit checking. | |
| OCR.space MCP Server agentic-ai-forge/ocr-space-mcp MCP server for OCR.space API to extract text from images and PDFs, with tools for file, URL, automatic oversized handling, and language support. | |
| memora agentic-box/memora Persistent memory with knowledge graph visualization, semantic/hybrid search, importance scoring, and cloud sync (S3/R2) for cross-session context management. | |
| Agentic Chat Rooms (ACR) MCP Server agentic-chat-rooms-protocol/acr-chatgpt-plugin It enables OpenAI models to create and join secure deliberation rooms, post messages, verify Ed25519 W3C DIDs, reach 67% Byzantine-fault-tolerant consensus, manage Atlas 2.0 goal DAGs with rollback, and escalate high-risk actions through fa | |
| ACR Meta-MCP Forward Proxy agentic-chat-rooms-protocol/acr-meta-mcp Enables deploying a secure MCP gateway that proxies, sandboxes, and policy-governs third-party MCP servers, with credential vaulting and audited tool access across stdio, SSE, and Streamable HTTP. | |
| ACP Governance MCP Server agentic-control-plane/acp-mcp-server Governs AI agent tool calls by checking them against Agentic Control Plane policies, returning allow/deny/ask decisions with audit logging and identity attribution for MCP clients like Claude and ChatGPT. Exposes acp_check and acp_status to | |
| DME MCP Server agentic-data-ops/dme-mcp-server Exposes DME storage O&M actions as MCP V1 tools, enabling management of storage modules such as SAN, NAS, and storage via natural language. It provides per-module MCP endpoints and a root server to enumerate available tools. | |
| teams-assistant-mcp agentic-delivery/teams-assistant-mcp Lets a Claude Code agent read and post in a fixed allowlist of Microsoft Teams group chats using an ordinary user account, with tools for messaging, replying, editing, deleting, and polling. | |
| whatsapp-assistant-mcp agentic-delivery/whatsapp-assistant-mcp Enables a Claude Code agent to read messages from and send messages to a pre-approved allowlist of WhatsApp chats via a stdio MCP server. | |
| OpenShift SRE Copilot agentic-devops/mcp-sre-tools AI-powered MCP server for enterprise OpenShift/Kubernetes cluster management, providing diagnostic tools, RAG knowledge retrieval, and autonomous remediation recommendations. | |
| agentic-fy agentic-fy/agentic-fy Enables AI agents to drive spec-driven development workflows from the IDE by exposing tools for exploring, proposing, applying, verifying, archiving, listing, showing, validating, status, and context operations. | |
| Vantage Telemetry MCP Server agentic-magic-innovators/vantage-telemetry-mcp MCP server that captures and exposes usage, cost, productivity, and activity metrics for local-first software engineering teams, including LLM token usage, cloud cost savings, and developer activity tracking. | |
| Real Estate MCP Server agentic-ops/real-estate-mcp A comprehensive Model Context Protocol server for real estate data management that provides tools and resources for property listings, agent management, market analysis, client relationships, and area intelligence. | |
| Aurey Wallet MCP agentic-pantheon/aurey-mcp Self-hosted MCP server enabling AI agents to manage EVM wallets, check balances, swap tokens, and securely execute transactions via 1Claw Intents without exposing private keys. | |
| Icon MCP Server agentic-ph/icon-mcp Provides unified search across multiple icon libraries with fuzzy search, caching, and comprehensive filtering for easy icon discovery and retrieval via the Model Context Protocol. | |
| Finance Agent MCP Server agenticai-ind/finance-agent MCP server for personal finance management and investment tracking with real-time market data, expense tracking, portfolio management, and AI financial advisor capabilities. | |
| AgenticBI agenticbihq/agenticbi-mcp-server Connect your business data to any MCP client. AgenticBI agents find the right data, join across systems, run queries, build dashboards, generate reports, and automate analytics workflows. No SQL required. | |
| @agenticbits/claude-plugin agenticbits/claude-plugin Adds a live git branch status bar to the Claude interface for monitoring multiple repositories simultaneously. It provides tools for managing repository tracking and visibility through natural language commands. | |
| AgenticBooks MCP Server agenticbooks/agenticbooks-mcp Financial data infrastructure for AI agents. Connect to a startup's books to read live P&L and bank balances, review and reclassify transactions, manage the chart of accounts, and connect banking sources. | |
| StyleTrace agenticbridge/style-trace Analyzes website references, images, screenshots, and HTML snippets to produce a design brief with style constraints, and reviews generated HTML against those constraints. | |
| TwinCAT Validator MCP Server agenticcontrolio/twincat-validator-mcp An MCP server for validating, auto-fixing, and scaffolding TwinCAT 3 XML files using deterministic code quality tools and IEC 61131-3 OOP checks. It enables AI assistants to perform structural validation, apply safe fixes, and generate cano | |
| deckrun-free agenticdecks/deckrun-mcp-server Generates PDF slide decks from Markdown using any MCP-compatible AI client. Free, no authentication, max 10 slides, output URL valid 90 days. | |
| CC Explorer MCP Server agenticledger/clientmcp_ccexplorer_mcpserver Enables AI assistants to query the Canton Network blockchain explorer through the CC Explorer Pro API. It provides tools for accessing ledger updates, governance votes, validator information, and network consensus data. | |
| Lighthouse Explorer MCP Server agenticledger/clientmcp_lighthouse_mcpserver Provides tools for AI assistants to query the Canton Network for data on contracts, governance, validators, and party transactions through the Lighthouse Explorer API. It enables seamless interaction with blockchain statistics, price histor | |
| pdf-inspector agenticledger/pdf-inspector-mcp-http Classifies PDFs (text-based vs scanned vs image vs mixed), extracts text, and converts to clean Markdown over Streamable HTTP MCP. Supports remote PDFs via URL or base64, with optional page restriction and OCR fallback detection. | |
| Ridgeline Finance OS MCP agenticledger/ridgeline-finance-os A Model Context Protocol server exposing the freight accrual pipeline as reusable tools, enabling agents to execute, monitor, sign off, and improve accrual runs. | |
| MCP Server agentico-dev/mcp-server MCP Server provides a simpler API to interact with the Model Context Protocol by allowing users to define custom tools and services to streamline workflows and processes. | |
| agenticpay agenticpay-dev/agenticpay agenticpay lets MCP server developers monetize tools via per-call USDC micropayments on Solana, using the x402 protocol. Each tool declares a price; agents pay via signed Solana transactions; settlement happens on-chain in ~1.5–2 seconds. | |
| Code MCP Server agentics-ai/code-mcp An experimental MCP server that enables AI assistants to interact with VS Code workspaces through file operations, code execution, and Git management. It also provides tools for Docker integration, project scaffolding, and secure command ex | |
| AgenticSettle Verify agenticsettleio/agenticsettle-mcp Free VOP (Verified Output Protocol) verification for AI agent outputs — score any output 0-100 and get a PASS/PARTIAL/FAIL verdict. No account, no escrow, no financial transaction of any kind. | |
| agentic-store-mcp agenticstore/agentic-store-mcp A collection of self-hosted, open-source tools that enable AI agents to perform web searching, content crawling, and code analysis tasks like linting and security scanning. It provides power-user capabilities for MCP-compatible clients with | |
| Agentic Vault MCP Server agenticvault/agentic-vault Exposes an EVM wallet to AI agents via MCP, using AWS KMS for HSM-backed signing and a deny-by-default policy engine for secure DeFi transaction approvals. | |
| Expert Registry MCP Server agentience/expert-registry-mcp A high-performance MCP server for expert discovery, registration, and context injection, enabling AI-powered expert selection through semantic search and relationship modeling with vector and graph database integration. | |
| react-design-systems-mcp agentience/react-design-systems-mcp Provides component information, usage guidelines, and code generation for AWS Cloudscape Design System in React, with search and pattern library capabilities. | |
| Tribal Knowledge Service agentience/tribal_mcp_server An MCP server implementation that helps Claude remember and learn from programming errors by storing, retrieving, and finding similar errors with full context. | |
| Cursor Proxmox MCP agentify-sh/cursor-proxmox-mcp A Python-based Model Context Protocol server that enables managing Proxmox virtualization platform through Cursor IDE, supporting complete VM lifecycle management including creation, power control, and deletion. | |
| agentify-desktop agentify-sh/desktop MCP server that enables AI tools to control local browser sessions for ChatGPT, Claude, and other AI services, supporting querying, navigation, file uploads, and artifact management. | |
| qrcode-pub-mcp agentiloop/qrcode-pub-mcp Enables users to generate QR code images for text or links, convert public web pages to Markdown, fetch page metadata, and host small files through a hosted MCP endpoint, with paid tools settled via x402 and no API key. | |
| AgentTemp MCP agentinbox-in/agentinbox-mcp Enables AI agents to create temporary email inboxes and wait for OTPs, magic links, or password reset emails via AgentTemp's API, useful for automation and verification workflows. | |
| agentindexworld agentindexworld/agentindex-mcp-server 26651 agents scanned 48137 SHA-256 blocks in an immutable chain 1169 Bitcoin anchors submitted 788 confirmed on-chain 49.7 $TRUST tokens earned by 5 agents 0 tokens bought — all earned through behavior |
24,451–24,500 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.