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 |
|---|---|
| CashBFF MCP dakshbeep/cashbff-mcp CashBFF is a personal-finance MCP server for Claude. Connect your bank through Plaid and ask Claude about your real money in chat. | |
| folder_stats dakshhgondaliyaa/mcp-folder-stats Provides a tool to count files and folders in a directory, supporting both recursive and non-recursive counts. | |
| Nova dakshhhhh-ops/nova Enables Alexa+ care circles to catch medication mistakes before they happen by checking pill labels, coordinating reminders and escalations, and surfacing evidence-backed health insights. It also integrates Ring doorbell events to support o | |
| PDFDashboardWithMCP dakshp26/pdfdashboardwithmcp Enables MCP clients to list indexed PDF document collections and perform semantic search queries on them using locally extracted text and embeddings. | |
| Odoo.sh MCP Server dalahmasdev/odoo-sh-mcp-server SSH-based Model Context Protocol server for Odoo.sh - Build custom apps with AI assistance using Git workflow tools. | |
| gumroad-publish-mcp dalai2/gumroad-publish-mcp Enables creating and publishing Gumroad products end to end, including uploading files, setting covers and thumbnails, writing landing pages, and managing catalogue and sales through MCP tools. | |
| content-ops-studio dalalala-art/content-ops-studio Provides a bounded set of MCP tools for orchestrating research, content planning, visual production, approval gates, and immutable delivery of image-post projects. | |
| sonsuchup-mcp dalboki/sonsuchup-mcp MCP server for Sonsuchup web tool that allows AI assistants to manage mystery cases, including people, alibis, timelines, and records via natural language. | |
| OpenVoice Studio MCP Server dalcio/openvoice-studio Enables Claude to discover available engines and voices, generate narration from text, monitor generation jobs, download finished audio, and run voice evaluations, all against a local on-device service. | |
| Blogger MCP Server dalcontak/blogger-mcp-server Enables AI models to interact with Google Blogger blogs, manage posts, labels, and retrieve blog information via API key or OAuth2. | |
| SEO MCP Tools dalebertrand/seo-mcp-tools Provides tools to extract the first or all sitemap URLs from a website's robots.txt file. | |
| sourcegraph-mcp dalebrubaker/sourcegraph-mcp MCP server for searching code via SourceGraph's GraphQL API, enabling fast symbol and text search across local or cloud SourceGraph instances. | |
| Volleyball MCP Server dalejan/volleyball_mcp Enables querying volleyball match, team, and tournament data from VolleyballWorld API through SQL queries on a SQLite database. | |
| job-tracker dalemagrath/mcp-job-tracker Enables managing a job search through natural language: tracking applications, discovery leads, interview prep, and resume generation. Connects to Claude via MCP to read and update local Excel files and documents. | |
| zephyr-dc-mcp dalemarchand/zephyr-dc-mcp Enables LLMs to manage test cases, cycles, and executions in Jira Data Center via Zephyr Scale. | |
| verbashield-mcp dalexsys/verbashield-mcp AI text detection, humanization, and quota management for Russian & multilingual text. Official MCP server for VerbaShield AI. | |
| BMAD MCP Server dali1789/bmad-mcp-server Provides intelligent agent routing with 5 specialized AI agents (analyst, architect, dev, pm, qa) through OpenRouter integration. Enables unified project structure across all IDEs with global registry management and automated BMAD methodolo | |
| Mcp Server Sqlite Fast dali5599/mcp-server-sqlite-fast Enables AI agents to explore and query SQLite databases through secure read/write SQL execution, schema introspection of tables, columns, keys and indexes, and EXPLAIN execution-plan analysis for indexing guidance. It runs on Node's native | |
| mcp-snippetbox dalibordurisrw/mcp-snippetbox Enables users to add, retrieve, update, delete, and list notes through five MCP tools, with persistent storage configured by a file path. It also provides atomic saves and clear tool descriptions for client integration. | |
| AcuMiglio MCP GitHub Agent dalilamiglio/acumiglio-mcp MCP server that lets AI agents interact with GitHub using natural language, supporting operations like creating repositories, issues, and commits. | |
| ZWCAD-MCP dalingo81/zwcad-mcp Enables AI clients to drive ZWCAD drawing, modification, query, and plotting via natural language. | |
| n8n Community Nodes MCP Server dalisys/n8n-community-nodes-mcp This MCP server enables users to search and access documentation for community-developed n8n nodes and official built-in nodes. It provides token-optimized responses for discovering n8n packages and documentation directly through AI assista | |
| Yatishara Studio MCP dallas-ferdinand/yatishara-studio-mcp Connects AI assistants such as Cursor, ChatGPT, and Claude to Yatishara Studio, enabling secure access and interaction with the studio's capabilities through natural language. | |
| Accessibility MCP Server dallask/a11y-mcp-srv Provides conversational, actionable accessibility testing for AI agents, including auditing, prioritization, and code-level fixes. | |
| remote-mcp-server-authless dallask/remote-mcp-server-authless Deploys a remote MCP server on Cloudflare Workers without authentication, allowing custom tool integration and connection to AI clients like Claude Desktop. | |
| proxmox-ai dallaswk/proxmox-ai MCP server that lets an AI agent manage Proxmox VE in natural language, with policy-driven security, read-only mode, two-step confirmations, and audit logging. | |
| Crease dallenpyrah/creasekit Enables coding agents to read snapshots of inspected UI elements and attached notes, allowing visual feedback and context to be shared through MCP. | |
| Moory dalmaktube-creator/dv-moory A self-hosted MCP bridge that enables Notion AI to interact with approved Git repositories and curated GitHub APIs, supporting guarded code changes, pull requests, issues, Actions, logs, releases, secret scanning, and audit logging. | |
| omniventure-agent-tools dalnaspdal/omniventure-agent-tools Sub-15ms edge intelligence tools for Claude Desktop, Cursor, and LLM agent loops. Provides sub-millisecond LLM JSON repair, web-to-markdown token compression (cuts context tokens up to 90%), PII redaction, and RFC 5322 B2B email deliverabil | |
| codex-chatgpt-bridge dalomeve/codex-chatgpt-bridge Local MCP bridge enabling ChatGPT web to access approved local files and execute tasks via local Codex. | |
| mcp-dalpralab dalpralab/mcp-dalpralab Enables AI assistants to query DalPraLab's SEO/GEO consulting services, prices, case studies, availability, and submit audit requests directly from MCP clients. | |
| Useful-mcps daltonnyx/userful-mcps List of small useful mcp servers including:
* docx\_replace: replace tag in word document
* yt-dlp: extract chaper and subtitles base on chapter
* mermaid: generate and render image using mermaidchart.com API | |
| Sharebox MCP Server dalvivishal/custommcpserver Enables AI clients to manage projects, cases, and file uploads while maintaining an immutable audit trail for all write operations. | |
| youbank-mcp dalydoo/youbank-mcp Enables AI agents to query a personal knowledge vault with hybrid search, entity relationships, user highlights, and vault statistics over a Supabase/Postgres schema. | |
| atlas-przetargow-mcp-py dam2452/atlas-przetargow-mcp-py Enables searching and analyzing Polish public procurement tenders from BZP and TED, including filtering, tender details and timelines, offers and contract values, buyer/contractor profiles, CPV code lookup, and regional statistics, with opt | |
| crossref-mcp dam2452/crossref-mcp Enables searching and retrieving scholarly metadata from Crossref's public REST API, including works, journals, funders, and members, without requiring an API key. | |
| llmstudio-mcp dam2452/llmstudio-mcp MCP server that connects LLM agents to a local LM Studio instance, enabling model management, OpenAI-compatible chat completions, text completions, and embeddings through a set of tools. | |
| pubmed-mcp dam2452/pubmed-mcp MCP server for accessing NCBI PubMed/PMC databases, enabling search, retrieval of summaries and full records, citation export, and ID conversion through various APIs. | |
| semanticscholar-mcp dam2452/semanticscholar-mcp Provides access to the Semantic Scholar Academic Graph API, enabling search and retrieval of papers, authors, citations, and related academic data. | |
| unpaywall-mcp dam2452/unpaywall-mcp Enables looking up free-to-read versions of scholarly papers by DOI and searching article titles for Open Access matches via the Unpaywall API. | |
| vastai-mcp dam2452/vastai-mcp MCP server that wraps the Vast.ai REST API to enable LLM agents to search GPU marketplace, rent machines, manage instance lifecycle, run commands, and inspect billing. | |
| Novamira damadorpl/warsztat-wordcamp-wroclaw-2026 Enables AI assistants and agents to communicate directly with a WordPress environment, executing PHP code and WP-CLI commands, inspecting and editing theme and plugin files in a sandbox, and managing posts, content, and Gutenberg blocks in | |
| PureData-MCP damagethundercat/puredata-mcp Control and live-patch Pure Data from AI agents via the Model Context Protocol. | |
| MCP WebResearch damameet14/mcp-webresearch An AI-ready MCP server that performs intelligent web searches using SearxNG and Playwright, with one-step Docker setup. | |
| Openlaw MCP damankaur-dev/openlaw-mcp OpenLawMCP is an open-source legal AI research tool built to make AI-assisted legal research more reliable.
A major problem with using AI for legal research is that it can give confident answers without showing whether the answer is ground | |
| openai-image-mcp damao-bot-army/openai-image-mcp Enables Claude to generate and edit images through the OpenAI Images API, storing full-size results in R2 and returning public URLs, IDs, token usage, model details, and optional JPEG previews. | |
| x-reply-guard-mcp damao-bot-army/x-reply-guard-mcp Enables Grok Bot and other MCP clients to retrieve X mentions and posts, create drafts, and publish approved posts or replies with server-side prompt-injection defenses, reply whitelisting, deduplication, and rate limits. | |
| MCP JobPilot Africa damasoumana1/mcp-jobpilot-africa- Enables AI agents to discover African tech internships and early-career jobs, match candidate profiles, analyze skill gaps, track applications, and generate interview questions and preparation checklists. | |
| Artsy Analytics MCP Server damassi/mcp-artsy-analytics A Model Context Protocol server that provides Artsy partner analytics tools for Claude Desktop, allowing users to query gallery metrics, sales data, audience insights, and content performance through natural language. | |
| claude-code-session-mcp dambinhtu-nhuy/claude-code-session-mcp MCP server that provides read-only analysis of Claude Code session transcripts, enabling queries about project activity, session details, and tool usage. |
41,751–41,800 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.