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 |
|---|---|
| antigravity-claude-mcp arjunthilak05/antigravity-claude-mcp Allows Claude Code to request an independent code review from Google Antigravity (Gemini, Claude, or GPT-OSS) via the Antigravity CLI, providing a second opinion on plans or diffs. | |
| antigravity-claude-mcp arjunthilakeros/antigravity-claude-mcp Enables Claude Code to request independent code reviews and second opinions from other AI models (like Gemini, GPT-OSS) via the Antigravity CLI, directly from the chat. | |
| toli arjunvlama/toli Self-hosted daemon connecting Claude Code, Codex, and other coding agents across machines via MCP + A2A: delegate tasks, ask questions, share results, and wake sessions. | |
| controlplane-mcp arjunyerevan95-dot/controlplane-mcp Enables adopting an existing project into a durable, repo-backed coordination pattern, providing role-scoped context and state management for long-horizon agentic work. | |
| mcp-dora ark-forge/mcp-dora DORA compliance scanner MCP server that scans projects for regulatory gaps, classifies entities, generates reports, and optionally produces ICT registers and incident templates with cryptographic certification. | |
| EMMA MCP ark9164-create/blaylock-emma-mcp A custom MCP server that enables Claude to access and query municipal bond data from the MSRB's EMMA website, which lacks a public API. It provides 18 tools for searching bonds, downloading official statements, and extracting financial data | |
| Agentic Memory arkaaiadmin/agentic-memory MCP server for persistent, cross-session, local-first memory for AI agents, storing memories as Markdown files with SQLite indexing for hybrid search. | |
| AEM DEV MCP Server arkadiusz-rosiak/aem-dev-mcp Enables AI agents to manage Adobe Experience Manager instances, including OSGi bundle and component operations, configuration CRUD, health monitoring, log analysis, and Groovy script execution. | |
| Gmail MCP Server arkaigrowth/gmail-mcp-server Multi-account Gmail integration for AI assistants via the Model Context Protocol (MCP). | |
| Stargraph arkaigrowth/stargraph Enables evidence-first analytics over GitHub starred repositories, including search, similarity comparison, explanation, and clustering via MCP tools. | |
| waiting-on arkaigrowth/waiting-on Provides an MCP server that tracks open loops (pending decisions or replies) across email, agent sessions, and other channels, enabling agents to query what is waiting on whom. | |
| metabase-mcp-server arkanji/metabase-mcp-server Enables AI agents to read-onlyly access Metabase instances, query databases using MBQL or SQL, explore schemas, run saved questions, and export data. | |
| model-context-protocol arkapatra31/model-context-protocol MCP server enabling real-time weather queries via Tavily API and internet usage data by country via MongoDB. | |
| Groww MCP arkapravasinha/groww-mcp-server Enable seamless integration of Groww platform data and tools with language models to enhance financial decision-making and automation. Provide access to Groww-specific resources, execute financial operations, and utilize predefined prompts | |
| WikiFact arkased/wikifact Enables AI agents to search a self-maintaining knowledge wiki for facts with confidence scores, and to submit evidence-backed correction or update requests that a worker validates, merges, and writes back with full history. Agents both read | |
| AppMCP arkay92/appmcp Embeds a secure, curated MCP server inside Python applications, exposing explicit tools, resources, and prompts with dependency injection, security policies, and in-memory testing. | |
| Arke Institute MCP Server arke-institute/arke-mcp-server Enables semantic search across the Arke Institute's extensive archive of NARA records and presidential libraries using natural language queries. Provides access to millions of historical documents, photographs, and records with OCR'd conten | |
| Attio MCP Server arkel-ai/attio-mcp-server Provides tools to interact with the Attio API, enabling management of resources in an Attio workspace. | |
| Model Context Protocol Server arkeodev/search-engine-with-rag-and-mcp Provides a standardized protocol for tool invocation, enabling an AI system to search the web, retrieve information, and provide relevant answers through integration with LangChain, RAG, and Ollama. | |
| TogoMCP arkinjo/togo-mcp Executes SPARQL queries against biological and biomedical RDF databases from the RDF Portal, with additional REST API integrations for bioinformatics resources. | |
| SiYuan MCP Server arkkwang/siyuan-mcp Enables interaction with SiYuan Note through its API for comprehensive note management. Supports searching, creating, editing documents, managing notebooks, and daily notes operations through natural language commands. | |
| feedkit arknill/feedkit Enables users to search a curated RSS/Atom catalog, subscribe to and collect feeds, and query collected articles through natural-language tools. | |
| snapgrab arknill/snapgrab Enables capturing URL screenshots with page metadata and Claude Vision token estimates, comparing desktop versus mobile (or arbitrary) viewports, and extracting metadata such as titles, Open Graph tags, favicons, and HTTP status without tak | |
| coordination_bus/mcp_server.py arko-sanyal/loci-coordination-bus Enables MCP-capable coding agents to coordinate via authenticated task creation, claiming, messaging, and review approval over a secure local event log. | |
| susan arkone-ai/susan MCP server that provides cross-session awareness for Claude Code, tracking active sessions, file conflicts, and shared todos to enable agent coordination without blocking tool calls. | |
| Neuro MCP V2 arks-06/neuro_mcp_v2 Supercharges Claude Desktop with persistent semantic memory, sandboxed file I/O, live web search, and local emotional intelligence using a local ChromaDB and Hugging Face model. | |
| SuperMCP arksentinel/super-blender-mcp Enables Blender automation via MCP with 107 tools for complex mesh modeling, PBR texturing, UV mapping, rigging, animation, lighting, rendering, and a pre-export curing pipeline for Godot 4.x/Redot GLB export. | |
| Docker MCP Server arktechnwa/docker-mcp Enables AI assistants to interact with Docker containers through safe, permission-controlled access to inspect, manage, and diagnose containers, images, and compose services with built-in timeouts and AI-powered analysis. | |
| Federated Search arktechnwa/federated-search A federation MCP server that sits in front of multiple memory backends and presents a unified search surface to AI agents, allowing a single query to search across knowledge graphs, session history, and web search. | |
| GitHub Actions MCP arktechnwa/github-actions-mcp Connects AI assistants to GitHub Actions workflows to monitor CI/CD pipelines, view run logs, diagnose failures, and optionally trigger or manage workflows with granular permission controls. | |
| j5ed-knowledge-graph arktechnwa/j5ed-knowledge-graph A knowledge graph MCP server providing persistent, structured memory for AI assistants with multi-agent isolation, tiered search, and index navigation. | |
| pfClaude arktechnwa/pfsense-mcp Enables bidirectional control and monitoring of pfSense firewalls through Claude, with full API access for configuration and diagnostics, plus autonomous emergency response capabilities when network connectivity is lost. | |
| PostgreSQL MCP Server arktechnwa/postgres-mcp Provides AI assistants with safe, controlled access to PostgreSQL databases with read-only defaults, granular permissions, query safety features, and schema introspection capabilities. | |
| Prometheus MCP Server arktechnwa/prometheus-mcp Enables AI assistants to query Prometheus metrics, monitor alerts, and analyze system health through read-only access to your Prometheus server with built-in query safety and optional AI-powered metric analysis. | |
| systemd-mcp arktechnwa/systemd-mcp Provides AI assistants with safe, read-only access to Linux systemd services, including status monitoring, log querying, and dependency analysis, with optional granular permissions for service management actions. | |
| @arkty/redash-mcp arkty/redash-mcp Enables executing SQL queries, exploring database schemas, and exporting results from Redash via MCP, with ad-hoc queries and write protection. | |
| Native_MCP arkvex/native_mcp An extensible Model Context Protocol server that enables AI assistants like Claude to generate React Native components and perform development tasks through a standardized interface. | |
| Anchor MCP arkya-ai/anchor-mcp Provides persistent, local-first long-term memory for LLMs using Voronoi-partitioned vector storage and local embeddings. It enables users to store, recall, and automatically retrieve project context and preferences entirely on their own ma | |
| Ember MCP arkya-ai/ember-mcp A local-first persistent memory server that uses Voronoi partitioning and temporal intelligence to provide LLMs with long-term context across different sessions and clients. It features automatic drift detection to prevent hallucinations by | |
| Book Store MCP arlansantos/bookstore-mcp Enables users to search and explore a bookstore catalog including books, authors, categories, stock, prices, and recommendations through natural language. | |
| Economía Venezuela MCP arlexperalta/economia-mcp Provides real-time Venezuelan economic data, including official and parallel exchange rates, inflation statistics, and basic goods basket prices. It enables AI assistants to query historical economic trends and current market indicators via | |
| mcp-lab arlian/mcp-lab A hands-on lab for learning the Model Context Protocol (MCP) in TypeScript, providing example tools, resources, and prompts. | |
| centered-agent-memory arlinamid/centered-agent-memory Enables AI agents to search and retrieve past coding-tool conversations across Claude Code, Claude Desktop, Codex, and Cursor through a local, read-only index. | |
| htmltool arlyon/htmltools Bun runner for HTML-first local tools that exposes them as MCP servers with typed browser RPC, async streams, and MCP 2.0 Streamable HTTP, including MCP Apps UI support. | |
| retained arm00pv/retained Enables MCP clients to persist, search, retrieve, and verify append-only memory records, with every write acknowledged only after append, fsync, byte-exact read-back, and hash-chain validation. It also surfaces truncation and index drift so | |
| dk-mcp arm1323/dk-mcp Enables read-only access to DraftKings DFS lobby data, including slates, contests, salaries, and roster rules, via MCP. | |
| reforger arma-reforger-competitive/arma-reforger-tools-mcp Enables Claude to read Arma Reforger wiki pages by title and, as development continues, search the Enfusion script API and locate/read the game’s own files to support modding work. | |
| thndr-mcp armaaar/thndr-mcp An unofficial MCP server that lets assistants query a Thndr brokerage account and market data — portfolio, positions, orders, realized returns, price snapshots and history, order books, screeners, financials, news, dividends — and manage wa | |
| GeoSight MCP Server armaasinghn/geosight-mcp Production-ready satellite imagery analysis server that enables natural language queries for Earth observation data, including land cover classification, vegetation monitoring, water detection, change detection, and automated environmental | |
| Quantum Computation MCP Server armaasinghn/quantumcompute_mcp Enables natural language quantum computing by converting English queries to quantum circuits via OpenAI and executing them on IBM Quantum backends or simulators. |
30,451–30,500 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.