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 |
|---|---|
| Blender MCP Server cwahlfeldt/blender-mcp A Model Context Protocol server that allows management and execution of Blender Python scripts, enabling users to create, edit and run scripts in a headless Blender environment through natural language interfaces. | |
| wiki-rag-mcp cwarre33/wiki-rag-mcp Exposes a markdown knowledge base to MCP clients so they can search pages, fetch individual documents, and ask grounded questions that come back with numbered citations or a refusal. Retrieval is graded before answering, with a single query | |
| AVA cwattsnogueira/mcp-server-draft Enables AI agents to create Gmail drafts safely using the Gmail API, without sending emails. | |
| SPNEGO MCP Proxy cwbr/spnego-mcp-proxy Enables MCP clients to securely connect to Kerberos-protected upstream MCP servers using the current macOS user's Kerberos ticket cache via SPNEGO authentication over a local HTTP proxy. | |
| Porkbun MCP Server cwdcwd/mcp-server-porkbun Enables domain and DNS management through Porkbun's API over a Streamable HTTP connector, validating the caller's API key pair upstream on every request so no credentials are stored in the deployment. Purchase and funding tools can be locke | |
| Odoo MCP Server cwdshaun/initial-odoo-mcp Full-featured MCP connector for Odoo ERP via XML-RPC, enabling natural language interaction with CRM, sales, inventory, and other Odoo modules. | |
| omnistate cwen0224/omnistate Enables AI agents and MCP clients to govern code changes through transactional begin/step/audit/finish workflows, enforce scope and anti-laziness guardrails, and obtain commit clearance tokens before Git commits. | |
| Knowledge Base MCP Server cwente25/knowledgebasemcp Enables AI assistants to manage a personal markdown-based knowledge base with natural language interactions. Supports creating, searching, updating, and organizing notes across categories like people, recipes, meetings, and procedures. | |
| photo-get-skill cwentor/photo-get-skill An MCP server that searches and downloads royalty-free images from Pixabay by keyword, with support for custom image size and safe search. | |
| SQL Server MCP cwilby/mcp-node-mssql A Model Context Protocol server that enables AI assistants (Cursor, Windsurf, Claude Code) to interact with Microsoft SQL Server databases by providing connectivity through environment-configurable connections. | |
| memstack-skills cwinvestments/memstack Enables Claude Code with 127 professional skills for deployment, security, databases, content, marketing, and more, activating automatically when needed. | |
| session-bridge-mcp cwj9195/session-bridge-mcp Enables cross-tool session reading and bidirectional incremental context synchronization for AI coding tools such as Codex, Claude Code, and VS Code Copilot, with exact caller identification and incremental transcript access. | |
| zentao-rest-v1-mcp cwj9195/zentao-rest-v1-mcp Enables interaction with ZenTao open-source instances to query and manage tasks, bugs, stories, test cases, and test runs, using REST v1 with legacy fallback for incompatible routes. | |
| Weather MCP Server cwk2025/weather_mcp_test A real-time weather query MCP server supporting 12 major Chinese cities, with tools to get weather, list cities, and server info. | |
| MCP Terminal Server cwmoore-ai/mcp-terminal-server A lightweight FastAPI server that allows remote execution of shell commands on Windows, with real-time output streaming and security features like API key authentication and rate limiting. | |
| TrustAtom MCP Server cwnapps/trustatom-mcp Provides cryptographic signing and verification for AI decisions to generate verifiable, Ed25519-signed receipts for compliance and auditing. It automatically maps AI actions to regulatory frameworks like HIPAA and SOX with high-performance | |
| icampus-mcp cwon-z/skku-icampus-mcp Enables AI assistants to read your own SKKU iCampus data, including tasks, assignments, announcements, lectures, attendance, and grades, through read-only MCP tools, with a refresh tool to request a new sync. | |
| pvwatts-mcp cwoodcox/pvwatts-mcp Enables solar energy potential assessment by converting parcel centroid and acreage into annual/monthly generation estimates using the NREL PVWatts v8 API, suitable for revenue modeling and infographic headlines. | |
| HG MCP Server cwt/hg-mcp Enables AI assistants to interact with Mercurial repositories, supporting version control operations like cloning, committing, branching, merging, and remote synchronization through natural language. | |
| shutil-mcp cwt/shutil-mcp Provides asynchronous file system operations (ls, cp, mv, etc.) with structured JSON output and optional jail restriction for AI agents. | |
| Tripletex MCP Server cwvedvik/tripletex-mcp Enables AI assistants to interact with the Tripletex accounting system via 56 tools and 18 skills for orders, invoices, bookkeeping, reports, projects, and travel expenses. | |
| DLP MCP Server cx-anand-nandeshwar/security-dlp-mcp Connects AI coding assistants to DLP One for real-time security scanning, vulnerability management, and AI-generated remediation directly inside your IDE or AI agent. | |
| Memória cx-guilherme-pinto/claude-memory-app Enables Claude Code to search, save, and relate local Markdown notes—lessons, do/don't rules, and task history—by project, ticket, epic, tags, or text, keeping everything on the user's own computer. | |
| prompt-workbench cx0806v/prompt-workbench Enables MCP-compatible AI clients to list or recommend scenarios, retrieve step-by-step questionnaires, and render polished prompts from user answers. | |
| Claude Fedora Bridge cx188/bridge-mcp-for-claude-users-on-fedora A local MCP server that gives Claude in the browser tools to interact with a Fedora machine, including file operations, system diagnostics, build tasks, and root actions via Polkit. | |
| memory_plus cx2002302-lang/memory_plus Provides persistent, searchable structured memory management for AI agents, with keyword matching, bidirectional Zettelkasten sync, and six MCP tools. | |
| commercial-creator cxbxmxcx/commercial-creator Enables AI agents to produce video commercials from product descriptions via a multi-stage pipeline with human-in-the-loop approval gates and explicit spend authorization. | |
| BrowserPilot cxcboss/browserpilot Enables AI assistants to control a Chrome browser through natural language, supporting navigation, interaction, tab management, and data extraction. | |
| mcp-ccnu-lib cxdpowered/mcp-ccnu-lib 封装华中师范大学图书馆空间预约系统（包括登录、查座位、预约、取消、暂离等操作）为一组MCP工具，供LLM调用执行。 | |
| git-panel cxfhackers/codex-git-panel Enables Codex users to review workspace and staged files, preview diffs, stage or unstage changes, generate AI-written Chinese Conventional Commit messages from staged diffs, and switch, merge, update, and push branches from a local panel. | |
| Gemini Media MCP cxoagi/gemini-media-mcp MCP server for generating images and videos using Google Gemini and VEO models, with support for multiple AI models and credential modes. | |
| meican-mcp cxorz/meican-mcp 美餐MCP服务器，支持查询餐次、餐厅、菜单和订单，以及下单和取消订单操作。 | |
| Name.com MCP Server cxs85/namecom-mcp Enables management of domains and DNS records through the Name.com REST API. Users can search for available domains, check bulk availability, and configure DNS records or nameservers using natural language. | |
| Neo4j MCP cxt9/neo4j-mcp Enables LLMs to interact with Neo4j graph databases using natural language to execute Cypher queries and introspect database schemas. It supports both read and write operations for local, Docker, and cloud-based instances like Neo4j Aura. | |
| wavekit-mcp cxzzzz/wavekit-mcp An MCP server that provides AI assistants with a persistent, sandboxed Python environment for waveform analysis, enabling loading and manipulation of VCD/FST/FSDB files and temporal pattern matching. | |
| tech-doc-mcp cy-wwyy/tech_doc_mcp Provides local technical documentation with hybrid search (semantic + BM25) for AI agents, ensuring access to up-to-date framework docs. | |
| Eclipse Aperture MCP cyan-eclipse-technologies-llc/cyan-eclipse-aperture-mcp Enables building one approved package into native Instagram Feed, Carousel, Story, and Reel variants, with capability probing, owner-approved native previews, and a hash-chained receipt ledger. Publishing and analytics are routed only throu | |
| Cyan Eclipse Apply MCP cyan-eclipse-technologies-llc/cyan-eclipse-apply-mcp The auto-apply tool that shows its work — policy-scoped autonomy, review-first, receipts for every action. | |
| Eclipse Beacon MCP cyan-eclipse-technologies-llc/cyan-eclipse-beacon-mcp Enables users to build a local insurance policy graph with per-field provenance and monitor upcoming policy deadlines through read-only ingestion, listing, radar, and gap-analysis tools backed by hash-chained receipts. | |
| Eclipse Benchkit cyan-eclipse-technologies-llc/cyan-eclipse-benchkit-mcp Enables vendors to run a declared check battery against their own MCP server, emit sealed Assay-format scorecards with evidence hashes and environment fingerprints, and have a local verifier re-run a random sample to issue counter-signed ve | |
| Cyan Eclipse Book MCP cyan-eclipse-technologies-llc/cyan-eclipse-book-mcp Market data + venue access layer — not an exchange: one book, one fee truth, one ledger of record. | |
| Cyan Eclipse Cluster MCP cyan-eclipse-technologies-llc/cyan-eclipse-cluster-mcp Signed images, governed runtimes — the gate runs first: no verified signature and provenance, no deploy. | |
| Cyan Eclipse Colophon MCP cyan-eclipse-technologies-llc/cyan-eclipse-colophon-mcp Catalog of record for books: signed titles, rights, prices & royalties, checked everywhere they appear. | |
| Cyan Eclipse Compass MCP cyan-eclipse-technologies-llc/cyan-eclipse-compass-mcp The Thumbtack adapter: one approved Task Brief becomes a native Thumbtack request, and a hire runs under mandate. | |
| Eclipse Constellation MCP cyan-eclipse-technologies-llc/cyan-eclipse-constellation-mcp Enables agents to evaluate lifecycle actions against fleet policy (quotas, allowlists, TTLs, snapshot preconditions, approval gating), run read-only probes on declared targets, capture fleet snapshots, and inspect a hash-chained receipt led | |
| Cyan Eclipse Covenant MCP cyan-eclipse-technologies-llc/cyan-eclipse-covenant-mcp Consent-bound lead work for real-estate agents — provenance on every lead, a Gate on every send. | |
| Eclipse Dispatch MCP cyan-eclipse-technologies-llc/cyan-eclipse-dispatch-mcp Enables drafting once, reviewing per-platform previews and adaptation diffs, approving by content hash, and syndicating approved content to beehiiv/Ghost drafts and Substack paste packs. It also provides provenance-labeled cross-platform an | |
| Cyan Eclipse Forecast MCP cyan-eclipse-technologies-llc/cyan-eclipse-forecast-mcp The Polymarket adapter: the venue's prices, with their criteria and liquidity attached. | |
| Eclipse Genesis cyan-eclipse-technologies-llc/cyan-eclipse-genesis-mcp Enables sealing an agent's creator, model, config hash, and declared purpose scope into a signed, hash-chained birth certificate at registration, and later verifying that certificate offline against presented action records. Supports detect | |
| Eclipse Gig Core MCP cyan-eclipse-technologies-llc/cyan-eclipse-gig-core-mcp Enables owner-approved task brief creation, all-in quote normalization, mandate-based hire eligibility checks, scope-by-scope completion verification, and record-bound review drafting for gig marketplaces, with append-only receipts. |
41,251–41,300 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.