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 |
|---|---|
| Filesystem MCP Server eeb16027/mcp_integration_project Provides secure filesystem operations, including reading, searching, and batch processing files, with directory monitoring to detect new files, designed for integration with MCP clients such as LangGraph agents. | |
| EIP MCP Server eecheonwu/essot-mcp-server Bridges local development environments with the Engineering Intelligence Platform (EIP), enabling AI coding agents to manage SSOT, generate implementation/test/security plans, and synchronize architectural knowledge. | |
| SpinQit MCP Tools eeeeeeeason/backup_mcp Enables AI models to invoke SpinQ's quantum computing hardware resources by creating and submitting quantum circuits (QASM) to the SpinQ cloud platform for execution and results retrieval. | |
| Amadeus Agent eegrcenem/amadeus-agent A proof-of-concept MCP server that allows LLM agents to query live flight booking information via Amadeus, including cheapest tickets, destinations, and airline routes. | |
| FiveM MCP Server eeharumt/fivem-mcp A TypeScript-based server that provides debugging and management capabilities for FiveM plugin development, allowing developers to control plugins, monitor server logs, and execute RCON commands. | |
| avalanche-mcp-server eelvanpsd/avalanche-mcp Enables AI agents and IDEs to search official Avalanche documentation, query live C-Chain/P-Chain/X-Chain and Data API data, and follow guided workflows for launching L1s, configuring precompiles, and building cross-chain applications. | |
| OpenSearch Dashboards MCP Server eemijuntunen/opensearch-dashboards-mcp-server-py An MCP server for managing OpenSearch Dashboards, enabling AI assistants to create, manage, and inspect dashboards, visualizations, saved objects, and plugin features. | |
| github-mcp-server eemredemirci/github-mcp-server Enables management of GitHub issues, milestones, projects, and labels for a single repository via MCP tools. | |
| LUT Lunch MCP eerihyppanen/lut-lunch-mcp Enables AI assistants to browse and search lunch menus across LUT University's Skinnarila campus restaurants, including vegan and allergen-aware filtering, with clear reasons when menus are unavailable. | |
| capcut-mcp eery1677-lab/capcut-mcp An MCP server that enables AI assistants to automate CapCut Pro video editing, including creating drafts, adding media, text, effects, and keyframes, with support for both local and remote connections. | |
| Dialpad MCP Server eesaai/eesa-plugin-dialpad Enables Eesa AI agents to interact with Dialpad cloud phone system via MCP tools, including user management, call logs, transcripts, and SMS sending, with multi-tenant support. | |
| Microsoft Graph MCP Server eesb99/msgraph-mcp Provides read-only access to Microsoft 365 services including SharePoint, OneDrive, Outlook, Teams, and Calendar through the Microsoft Graph API, enabling users to search, browse, and retrieve content across their M365 suite. | |
| office365-mcp-server eesb99/office365-mcp-server Provides 45 tools for managing Office 365 via Microsoft Graph API, enabling email, calendar, file, contact, Teams, and task operations through natural language in Claude Code CLI. | |
| Optimization MCP eesb99/optimization-mcp Provides nine specialized production-ready solvers for advanced resource allocation, network flow, and multi-objective optimization with native Monte Carlo integration. It enables users to perform constraint-based decision-making and perfor | |
| rlm-mcp eesb99/rlm-mcp MCP server that enables verified code execution with LLM reasoning using Recursive Language Models (RLM). It supports tasks like code generation, data analysis, and complex task decomposition. | |
| advanced-calculator-mcp eeshan-anand/advanced-calculator-mcp An advanced calculator MCP server that provides a wide range of mathematical operations over streamable HTTP, enabling users to perform complex calculations via natural language with any MCP client. | |
| expense-tracker-postgres-mcp eeshan-anand/expense-tracker-postgres-mcp Persistent expense tracker backed by Neon Postgres with SQL tools for adding, editing, deleting, and analyzing expenses via natural language. | |
| test-emp-database-mcp eeshan-anand/test-emp-database-mcp An employee-analytics MCP server backed by SQLite that provides hand-written SQL queries for common analytics tasks like salary ranking and department statistics. It self-seeds sample data, enabling immediate testing of GROUP BY, window fun | |
| test-emp-database-mcp eeshan-anand/test-employee-database-mcp An employee-analytics MCP server backed by SQLite with pre-seeded sample data, providing tools for common SQL analytics such as top N earners, department averages, window functions, and subqueries. | |
| E-commerce MCP Server eeshapatel12/commerce-mcp Enables management of e-commerce operations including products, customers, and orders with full CRUD capabilities, plus data analysis features like sales summaries, top products/customers reports, and inventory tracking. | |
| whatsapp-mcp-plus eeshsaxena/whatsapp-mcp-plus A secure, zero-setup WhatsApp MCP server that lets AI assistants read, search, summarize, and (with user confirmation) act on personal WhatsApp chats via a safety-focused toolset, built as a maintained successor to the abandoned whatsapp-mc | |
| HoudiniMCP eetumartola/houdini-mcp Connects Claude AI to Houdini via the Model Context Protocol, enabling prompt-assisted 3D modeling, scene manipulation, and rendering within Houdini. | |
| Tattoo Feed eezymacc/mcp-loop-build-demo An MCP server that lets an LLM client browse and curate posts from a hand-picked list of Instagram tattoo artists via Instagram's Business Discovery API. | |
| Tattoo Feed eezymacc/tattoo-pal Enables browsing and curating posts from Instagram tattoo artists via Business Discovery API, with features like inspiration feed, bookmarking, and preference tracking, optimized for ChatGPT integration. | |
| scrcpy-agent ef-code/android-agent-mcp Local MCP server for observing and controlling an authorized Android device over USB using ADB and scrcpy, providing screen capture, UI automation, app inspection, logcat, and evidence recording. | |
| boxes-mcp ef-code/boxes-mcp Enables managing GNOME Boxes virtual machines through libvirt/virsh, including lifecycle operations, snapshots, screenshots, and capability-gated keyboard, mouse, clipboard, and drag-and-drop interactions. | |
| EFLOWCODE Image MCP ef-flowcode/eflowcode-image-mcp MCP server for generating and editing images using EFLOWCODE's Responses API. Supports text-to-image, image editing, batch editing, and multi-reference synthesis for MCP clients like Codex and Claude. | |
| Linear MCP Server efabien/linear-mcp-server Enables interaction with Linear workspace through the Model Context Protocol, supporting issue management, project cycles, teams, and global search. | |
| MCP Server efazahmed/csee-4119-project-1-mcp-server Enables MCP-compatible clients to discover and execute tools — current date/time formatting, weekday lookup, a progress-reporting timer, and expression calculation — over Streamable HTTP using JSON-RPC 2.0. Supports real-time SSE notificati | |
| safe-mcp-bridge-v2 efe-arv/safe-mcp-bridge-v2 A fail-closed policy boundary that translates local stdio MCP clients to authenticated Streamable HTTP servers, enforcing allowlists or read-only modes and redacting credentials from audit trails. | |
| MCP MySQL Server efeabio/mcp-mysql-server A robust MCP server for interacting with MySQL databases through AI agents, providing tools for schema analysis, query execution, and dynamic connection management with read-only security. | |
| MCP Redis Server efeabio/mcp-redis-server MCP server for Redis interaction with dynamic connection setup and management. | |
| catena-x402-mcp-demo efedurmaz16/x402-mcp-demo An MCP server whose tool invocations are metered and charged over x402, plus a paying-proxy reference client that lets any standard MCP client use the paid tool without knowing x402 exists. | |
| etherlink-mcp-server efekucuk/etherlink-mcp-server Enables interaction with the Etherlink blockchain, including balance checks, transactions, smart contract interactions, and token operations. | |
| Kortx MCP Server effatico/kortx-mcp A lightweight MCP server that provides coding copilots with access to GPT-5, Perplexity Sonar, and GPT Image models, offering tools for planning, debugging, research, and image generation. | |
| openclaw-mcp effectorhq/openclaw-mcp Bridges SKILL.md format to the Model Context Protocol, making effector skills available as MCP tools for agents like Claude, Cursor, and Windsurf. | |
| plausible-mcp effektiv-spenden-jetzt/plausible-mcp Enables teams to query Plausible Analytics from Claude using Google sign-in, with org-wide access managed through allowlisted domains or emails and no per-person API keys. | |
| Architecture Drift MCP efficjump/architecture-drift-mcp Compare evidence-linked documentation claims with facts observed in the current source tree. | |
| DoneProof MCP efficjump/doneproof-mcp Converts implementation objectives into explicit acceptance criteria and a traceable evidence matrix with hash-linked ledger, enabling deterministic completion assessment. | |
| HiMCP efficjump/hi-mcp Compiles OpenAPI 3.x documents and HTTP manifests into verified MCP tools, serving only operator-approved HTTP operations over Model Context Protocol stdio. | |
| Local Dev Doctor MCP efficjump/local-dev-doctor-mcp Local Dev Doctor turns an unfamiliar development checkout into an evidence-backed diagnosis. It discovers how the project is meant to run, checks safe prerequisites, and executes only the exact probe that a user approves. | |
| MCP QA Lab efficjump/mcp-qa-lab Evidence-driven quality testing for Model Context Protocol servers. It connects as a real client, captures the complete model-facing contract, identifies agent-usability risks, measures context cost, and executes only explicitly approved ta | |
| Preference Memory MCP efficjump/preference-memory-mcp A local, provider-neutral MCP server that turns user corrections into scoped, reviewable, and safely retrievable preference memory. | |
| Repro Capsule MCP efficjump/repro-capsule-mcp Enables creating portable, reviewable bug reproduction capsules from bug reports with safe, bounded execution and redacted evidence. | |
| Ensembl MCP Server effieklimi/ensembl-mcp-server A Model Context Protocol server providing LLMs with access to the Ensembl genomics database, enabling AI assistants to query gene information, sequences, variants, and other genomic data across multiple species. | |
| forgekit-radix-mcp effinrich/forgekit-radix-mcp Exposes Radix Primitives' parts, props, and accessibility contracts to AI coding agents, ensuring correct and accessible component usage. | |
| mcpserver effizienzagent/mcpserver Turns a Frappe site into a remote MCP server that AI clients such as Claude can sign in to with OAuth and use curated, task-level tools registered by installed apps. Every call runs as the signed-in user with that user's permissions, with s | |
| Freshservice MCP server effytech/freshservice_mcp MCP server created for Freshservice, allowing AI models to interact with Freshservice modules | |
| Senu efg-technologies/senu Enables MCP clients to list and retrieve project data over stdio through read-only tools, including optional name search and exact project ID lookup. | |
| Agileday MCP Server eficode/mcp-agileday Connects Agileday's competence and employee data with LLMs, enabling natural language queries to find experts by skill and retrieve employee competence profiles directly from your chat interface. |
47,151–47,200 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.