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 |
|---|---|
| Remote MCP Server on Cloudflare berndgill/remote-mcp-server Enables remote MCP server deployment on Cloudflare Workers with OAuth login, supporting tool calling via SSE from clients like MCP Inspector or Claude Desktop. | |
| HubSpot MCP Server berndk57348/mcp-hubspot Enables AI assistants to interact with HubSpot CRM data, including contacts, companies, engagement, conversations, and semantic search over previously retrieved data, with vector storage and caching to overcome API limitations and improve r | |
| flameox berndkaya0853/flameox Enables coding agents to turn explicit artifact paths or commands into bounded, locally captured runtime evidence such as profiles, traces, and benchmarks, with typed provenance, coverage, and limitations recorded. It requires no workspace | |
| data-gov-il-mcp berndnam/data-gov-il-mcp Enables MCP-compatible clients to discover, search, and query Israeli Government Open Data from data.gov.il, covering datasets, resources, organizations, tags, and tabular datastore records. It also provides curated prompts and resources fo | |
| LeetCode MCP Server berndtakeda771/leetcode-mcp-server Enables automated access to LeetCode problems, solutions, contests, and public data across leetcode.com and leetcode.cn, with optional authentication for user-specific features like submissions, notes, and progress. | |
| Bernerspace bernerspace/bernerspace A unified MCP server that provides OAuth-enabled integrations for multiple services through a single deployment. Currently supports Slack with 47 tools, with plans to expand to Gmail, Google Calendar, Notion, and 100+ other integrations. | |
| Architect-to-Product (A2P) bernhardjackiewicz/architect-to-product An MCP server that adds engineering discipline to AI-assisted development, enforcing evidence-gated TDD, security review, backup strategy, and deployment generation to turn AI-generated code into production-ready software. | |
| Loxone MCP Server bernhardrode/loxone-mcp-server Connects AI assistants to Loxone smart home systems for controlling devices, managing scenes, and monitoring real-time states through natural language. Supports lights, blinds, climate control, and automation with secure PIN-protected comma | |
| Cloudflare Playwright MCP berniecpa/playwright-mcp-example Enables AI assistants to control a browser through Playwright on Cloudflare Workers, allowing web automation tasks like navigation, typing, clicking, and taking screenshots through natural language commands. | |
| brain-trust bernierllc/brain-trust-mcp Enables AI agents to ask questions and review planning documents by connecting to OpenAI's GPT-4. Provides context-aware question answering and multi-level plan analysis with structured feedback including strengths, weaknesses, and suggesti | |
| taste-mcp bernieweb3/taste-skill-mcp MCP server that indexes and serves design skills, guides, and patterns from the taste-skill library, enabling structured retrieval and workflow prompts for design, redesign, and image generation. | |
| ichi-mcp bernik-bot/ichi-mcp Enables AI assistants to read the free public ICHI API via MCP stdio, retrieving the current Internet Cyber Health Index, recent critical alerts, and source health with structured JSON results and graceful error reporting. | |
| FCEFyN MCP bernoulli2005/fcefyn-mcp Enables an MCP-compatible assistant to log in with UNC single sign-on and explore the FCEFyN virtual classroom, listing enrolled courses, retrieving course indexes and materials, and reading or searching pages, activities, and PDFs. It work | |
| mcp-knowledge-server berns722/mcp-knowledge-server Exposes a version-controlled knowledge base as MCP tools so agents can read merged identity/state summaries and next recommended actions at runtime, plus run deterministic schema validation and cross-reference link checks. This lets agents | |
| clingen-link berntpopp/clingen-link Enables querying ClinGen curated evidence for gene-disease validity, dosage, actionability, and variant pathogenicity via MCP tools. | |
| gencc-link berntpopp/gencc-link MCP server that provides tools to query harmonized gene-disease validity data from the Gene Curation Coalition, supporting consensus and conflict detection for gene-disease assertions. | |
| hgnc-link berntpopp/hgnc-link Grounds gene-nomenclature work in the HUGO Gene Nomenclature Committee (HGNC) dataset, enabling resolution of gene symbols and IDs to canonical HGNC identifiers, plus cross-references and batch operations. | |
| hpo-link berntpopp/hpo-link MCP server that provides tools for querying the Human Phenotype Ontology (HPO) including term lookup, hierarchy exploration, cross-ontology mappings, and gene-phenotype-disease associations, all grounded in a local SQLite database for fast | |
| metadome-link berntpopp/metadome-link Enables querying of per-residue missense tolerance, Pfam domain annotations, and variant counts for human transcripts by wrapping the MetaDome web service. Provides MCP tools for resolving transcripts, requesting tolerance landscapes, and i | |
| mgi-link berntpopp/mgi-link An MCP server that provides mouse genetics data from Mouse Genome Informatics (MGI), enabling LLM agents to query markers, mutations, alleles, phenotypes, and disease models. | |
| orphanet-link berntpopp/orphanet-link An MCP server that enables querying rare-disease data from Orphanet, including disease nomenclature, cross-references, classifications, gene associations, HPO phenotypes, epidemiology, and natural history. | |
| uniprot-link berntpopp/uniprot-link An MCP server that grounds protein research in the UniProt SPARQL endpoint, providing tools for querying proteins, sequences, variants, diseases, and more via intent-named tools and raw SPARQL. | |
| Cloud Sandbox MCP bernydotjar/cloud-sandbox-mcp-v2 Provides ChatGPT with a persistent, VM-like Linux engineering workstation inside Docker, with root access, development tools, and a private nested Docker daemon. | |
| litellm-admin-mcp berriai/liteadmin-mcp Enables agents to administer a LiteLLM gateway by creating and managing keys, model deployments, teams, budgets, and spending through MCP. | |
| blender-MCP berrio/blender-mcp Enables safe, repeatable preparation of game characters in Blender through high-level MCP tools for validation, import, normalization, action renaming, and GLB export, with dry-run by default and loopback-only security. | |
| inkscape-mcp berrio/inkscape-mcp Enables headless and secure control of Inkscape for creating, inspecting, and resizing SVG documents, and exporting to PNG, PDF, and SVG with validation of size, pages, structure, and hashes. | |
| powerbi-orchestrator-mcp berriosb/powerbi-orchestrator-mcp Enables AI agents to work end-to-end with Power BI and Fabric through 26 high-level tools that orchestrate specialized engines for semantic modeling, report authoring, cloud operations, validation, and visualization UX. | |
| verse-diagnostics-mcp berry-13/verse-diagnostics-mcp Parses UEFN Verse build diagnostics from UnrealEditorFortnite.log and exposes structured error data to MCP clients. | |
| BerryRAG berrydev-ai/berry-rag A local vector database RAG system that integrates with Playwright MCP for web scraping, enabling users to build searchable knowledge bases from web content with multiple embedding providers and Claude-optimized context formatting. | |
| deepseek-mcp berrydev-ai/deepseek-mcp Local MCP server that provides DeepSeek-powered code review, file analysis, and consultation tools for coding agents, enabling read-only analysis with minimal token overhead. | |
| JSON MCP Server berrydev-ai/json-mcp-server Provides powerful JSON manipulation tools through Model Context Protocol, enabling complex queries, schema generation, and validation with jq notation and native Node.js operations. | |
| MCP Server Template berryj85/mcp-server A production-ready template for building Model Context Protocol servers using TypeScript and Bun runtime, including schema validation, structured logging, and retry utilities. | |
| Radarr and Sonarr MCP Server berrykuipers/mcp_services_radarr_sonarr A Python-based Model Context Protocol server that allows AI assistants like Claude to access and query your movie and TV show collection via Radarr and Sonarr APIs. | |
| antigravity berryuiki/agy_mcp_codex Enables OpenAI Codex to delegate tasks to Google Antigravity CLI, running them headlessly and polling for results. | |
| Kaggle Dataset Analyst bert305/kaggle_mcp Enables exploratory data analysis and machine learning on CSV datasets with tools for profiling, missing values, correlation, plotting, model training, and prediction. | |
| Pet Grooming Analytics MCP bert305/pet_grooming_mcp A read-only MCP server that connects to a pet-grooming database, exposing secure analytics tools for customers, pets, appointments, services, and payments. | |
| shewhart-mcp bertanucar/shewhart-mcp Enables AI agents to perform statistical process control calculations using validated, deterministic tools such as control charts, capability analysis, and tolerance intervals. | |
| KatCoder MySQL MCP Server berthojoris/katcoder-mysql-mcp A secure MySQL Model Context Protocol server that enables AI agents to interact with MySQL databases through standardized operations. Features comprehensive security with SQL injection prevention, connection pooling, and configurable tool a | |
| Memory Server berthojoris/memory-server-mcp Provides persistent memory management with SQLite, enabling storage and retrieval of conversational context with metadata via MCP tools and REST API. | |
| SQLite MCP Server berthojoris/sqlite-mcp Enables secure and controlled access to SQLite databases through the Model Context Protocol. Provides comprehensive database operations with granular permissions, SQL injection protection, and audit logging for safe database interactions. | |
| Groot DataKG MCP Server bertinm/groot-data-kg-mcp MCP server for enabling data extraction and context retrieval for agents, storing information in a knowledge graph using Amazon Neptune or FalkorDB. | |
| Google Ads MCP Server bertramdev/googleadsmcp A comprehensive Google Ads MCP server providing ~47 tools for full read/write access to Google Ads accounts, including campaign management, ad creation, keyword management, and reporting. | |
| CVE-Search MCP Server bertrand311/cve-search_mcp Enables users to browse vendors and products, retrieve CVEs by ID, fetch the latest updated CVEs with CAPEC/CWE/CPE expansions, and inspect database update information via the CVE-Search API. | |
| MySQL MCP Server bertshim/simple_mysql_mcp Enables interaction with MySQL databases through MCP tools for querying table structures, searching data across single or multiple tables, and managing database information. Built with FastMCP framework for secure database operations using | |
| Simple Task MCP Server bertshim/simple_task_mcp A straightforward task management system enabling sequential task tracking, completion, and progress management through simple function calls or natural language commands. | |
| mcp-lsp-v1 beruang/lsp-mcp An MCP stdio server that wraps language servers to expose read-oriented code-intelligence tools (hover, definition, references, diagnostics, etc.) for coding agents, supporting TypeScript/JavaScript and Python. | |
| Gmail MCP Server bescka/fac_mcp Enables AI assistants to read unread Gmail emails and create draft replies, with optional NASA APOD integration. | |
| Newline MCP besscoleridge/newline Provides utilities for formatting multi-line shell commands with backslashes for safe pasting and reading system clipboard content. | |
| BESSER-MCP-Server besser-pearl/besser-mcp-server MCP server for BESSER low-code platform enabling AI assistants to create, manipulate, and generate code from domain models through natural language. Supports model creation, deletion, and multi-language code generation (SQL, Python, Java, e | |
| ats-jobs-mcp best-apis/ats-jobs-mcp Gives AI agents a daily-refreshed index of 350k+ open jobs scraped from 12,000+ company career sites on Greenhouse, Lever, Ashby, SmartRecruiters, Recruitee and Personio. Enables keyword, country, remote, seniority and recency job searches, |
33,801–33,850 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.