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 |
|---|---|
| ProtonBound dazzle-blip/code-protonbound A security-first MCP server that provides AI agents with a scoped, read-and-draft-only view into Proton Mail via Proton Bridge, ensuring no emails can be sent and access is restricted to configured workspaces. | |
| ProtonScope dazzle-blip/code-protonscope A lightweight MCP server providing AI agents a scoped, read-and-draft-only view into Proton Mail via Proton Bridge, with code-enforced restrictions preventing external access or sending. | |
| RAG Regression Gate db-inlee/rag-regression-gate-mcp MCP server that diagnoses RAG pipeline regression by detecting which failure modes (e.g., retrieval miss, hallucination) significantly regressed, not just score drops, using statistical methods to avoid false alarms. | |
| UE-MCP db-lyon/ue-mcp Gives AI assistants deep read/write access to the Unreal Editor through 21 category tools covering 525+ actions, plus a YAML flow engine for multi-step workflows. | |
| Databricks MCP Server Template db-mattmolony/databricks-mcp-template Enables AI assistants like Claude to interact with Databricks workspaces through secure OAuth authentication. Supports custom prompts, tools for workspace management, and SQL query execution via a deployable MCP server on Databricks Apps. | |
| Custom MCP Server on Databricks Apps db-mattmolony/mcp-mmolony-waf Enables deployment and hosting of custom MCP servers on Databricks Apps platform. Provides a template and deployment methods for creating scalable MCP servers with Databricks authentication. | |
| mcp-change-risk db-mcp-tools/mcp-change-risk Enables assessing database change risk, estimating impact, generating rollback plans, prechecking change windows, and orchestrating dry-run, canary, apply, and rollback with approval gates and auditable state transitions. | |
| mcp-data-semantics db-mcp-tools/mcp-data-semantics Enables teams to structure metric definitions, compare semantic differences, detect JOIN fanout and drift, reconcile mismatched numbers layer by layer, and persist metric contracts as YAML. | |
| mcp-dbwatch db-mcp-tools/mcp-dbwatch Enables on-call database diagnostics: it classifies load pressure, traces root causes with hypothesis-evidence-confidence, detects blocking and lock chains, scores health across a dimension tree, and renders deliverable incident reports. Wo | |
| mcp-migration-diff db-mcp-tools/mcp-migration-diff Enables cross-database and domestic-database migration analysis by checking type mappings, dialect gaps, NULL and charset/collation semantics, object parity, SQL translation, consistency verification with checksums and sampling, effort esti | |
| mcp-profile-hub db-mcp-tools/mcp-profile-hub Enables MCP clients to register and inspect database instance profiles, record observations and audits, compute scalar and quantile baselines, manage technical-debt findings and incident timelines, link related instances, and import/export | |
| SQL Review db-mcp-tools/mcp-sql-review Enables static, database-free SQL health checks that return rule-based findings and verdicts, propose executable fixes, and verify rewrites are equivalent while comparing execution plans and suggesting indexes. Supports batch/file/git-diff | |
| Databricks MCP Server Template db-nethra/mcp-you.com-demo Enables AI assistants like Claude to interact with Databricks workspaces through secure OAuth authentication. Supports custom prompts, tools for workspace management, and seamless deployment to Databricks Apps. | |
| You.com MCP Server db-nethra/mcp-youdotcom Enables AI assistants to search the web, get news, perform research, and retrieve AI-powered answers with citations using the You.com API. | |
| db3-atlassian-mcp db3net/db3-atlassian-mcp Lightweight MCP server for Jira, Confluence, and Bitbucket — read, create, and update from your AI IDE. | |
| Notability AI Bridge dbalchunas2-pixel/notability-ai-bridge Enables AI assistants to search, read, and query handwritten notes backed up as PDFs on Google Drive via MCP, with OAuth authentication, multi-user support, and usage metering. | |
| termcp dbalchunas2-pixel/termcp Gives MCP-compatible AI agents a full local terminal over stdio, enabling shell command execution, file reads and writes, content search, background processes, and stateful tmux sessions with variable capture, auditing, and a configurable c | |
| agent-browser-extension dbalders/agent-browser-extension Enables MCP-compatible agents and HTTP clients to discover, claim, and control Chrome tabs through an authenticated local bridge, including snapshots, actions, approvals, task ownership, screenshots, frames, diagnostics, and cleanup. | |
| Weather MCP Server dbalencar/openai-chatbot-weather-mcp A Model Context Protocol server that interfaces with OpenWeatherMap API to provide real-time weather information and forecasts for cities worldwide. | |
| Jamf Pro MCP Server dbankscard/jamf-mcp-server Enables AI assistants to interact with Jamf Pro for comprehensive Apple device management, including device inventory, policy deployment, configuration profiles, script execution, and compliance reporting. | |
| SkuVault MCP Server dbankscard/skuvault-mcp-server Enables interaction with the SkuVault inventory management system API for product management, inventory control, warehouse operations, and analytics through natural language. | |
| CBAPI.dev MCP Server dbansana/cbapi-mcp Enables AI agents to search products across affiliate networks, compare commissions, find arbitrage opportunities, and get auto-injected affiliate links via MCP. | |
| PocketBase MCP Server dbarbieri96701/pocketbase-mcp Enables advanced database operations, schema and collection management, record CRUD, user authentication, and backups through the Model Context Protocol. | |
| GAM MCP Server dbarks/mcp-gam Enables Google Workspace administration through the GAM CLI, allowing Claude to manage users, groups, and organizational units via natural language. | |
| VEX AIM MCP dbbudd/vex-aim-mcp Enables AI assistants to drive and control a VEX AIM coding robot over Wi-Fi, using its camera, lights, screen, speaker and kicker to navigate, detect objects, and play soccer. Also serves a live browser control panel for driving, team setu | |
| imagethis dbbuilder-org/imagethis One-step AI image generation for Claude Code, allowing users to generate images from natural language prompts with support for multiple backends like Replicate and OpenAI. | |
| px-pipe-mcp dbbuilder-org/pipethis Renders large text blobs as dense PNG image pages via pxpipe, enabling vision models to read content at ~3x token efficiency with a single inline image block. | |
| web-gpt-agent-core dbc-hbin/web-gpt-agent Connects ChatGPT Web to a local development environment, enabling file reads and patches, shell execution, plan updates, and isolated worktree coordination through permissioned MCP tools. | |
| TogoMCP dbcls/togomcp An MCP server that gives AI assistants access to biological and biomedical RDF databases via SPARQL at the RDF Portal, as well as selected REST APIs (NCBI E-utilities, UniProt, ChEMBL, PDB, Reactome, Rhea, MeSH, and more). | |
| DBCode dbcodeio/public DBCode is a Visual Studio Code extension that allows you to manage many databases, including PostgreSQL, MySQL, SQL Server, DuckDB, Redis, MongoDB, and more.
DBCode offers the option to run an MCP server, providing access to those database | |
| SSAS MCP Server dbdave/mssas_mcp_server A read-only MCP server for querying SQL Server Analysis Services (multidimensional cubes via MDX and tabular models via DAX) using Windows Integrated Security. | |
| rugguard-mcp dbe006/rugguard-mcp MCP server for RugGuard, enabling AI agents to perform pre-trade rug checks on tokens, with paid tools for token scanning and pre-trade verification, and a free metrics resource. | |
| QTask dbeasty/qtask Task and project management MCP server with OAuth for Claude Desktop, Cursor bridge, semantic search, staged write approval | |
| mcp-ssh dbeidachazi/mcp-ssh Enables AI agents to establish and manage persistent SSH sessions, supporting smart command execution, async tasks, multi-host, sudo, and file operations through SFTP. | |
| pg-mcp dbelokursky/pg-explorer-mcp Gives agents read-only access to PostgreSQL databases, enabling them to inspect schemas, sample rows, compare stands, view query plans, and run read-only SQL through a single entry point. | |
| Anansi MCP Server dbennett19103/anansi Exposes 17 scraping tools over stdio or SSE so an LLM agent can drive fetching, extraction, screenshotting, and full crawls of hostile, bot-protected sites through conversation. | |
| enterprise-mcp dbett4/hermes-enterprise-deployment-lab An MCP server exposing scoped, read-only enterprise operations tools with fail-closed credential handling. It returns opaque approval IDs for mutations and requires a separate operator approval command to release one-time capabilities. | |
| regulated-reporting-mcp dbett4/regulated-reporting-mcp MCP server for regulated financial reporting on Workiva, enabling agents to search, read, and write to Workiva workbooks with policy-gated mutations, readback verification, and immutable receipts. Supports both a compact 3-tool facade and a | |
| Plaud MCP Server dbf100/plaud-mcp Enables AI assistants to access Plaud Note recordings, providing direct access to speaker-diarized transcripts and AI-generated meeting summaries. Users can search, list, and retrieve recording details directly within MCP-compatible clients | |
| outlook-mcp dbfournier33/outlook-mcp An MCP server that gives AI agents structured access to a Microsoft Outlook mailbox through the Microsoft Graph API, with a deliberate constraint: agents can read and draft emails, but only humans can send. | |
| agent-librarian dbhardwaj99/librarian Enables coding agents to search and read curated project memory before exploring code, and to record durable findings as append-only events for later Librarian auditing. | |
| io.github.dbhat93/grounded dbhat93/grounded Enables AI assistants to answer high-trust sales questions with cited, vetted facts or explicit refusals, grounded in a local knowledge base. | |
| mcplex dbhavery/mcplex An MCP server that bridges local Ollama models and ChromaDB vector memory to MCP clients like Claude Code. It enables local text generation, vision-based image analysis, and semantic memory storage without requiring external API keys. | |
| SDD Orchestrator dbianco/sdd-orchestrator Routes each coding task to the best-fitting spec-driven-development framework with explainable rules, then enforces deterministic lifecycle gate checks between phases so progress can't skip required artifacts or evidence. Assembles per-phas | |
| AI PC Assistant MCP Server dbiswal3942-ctrl/chhotu_sa_mcp_mvp Enables AI assistants to safely perform actions on your computer including file system management, command execution, clipboard access, application launching, and local search with license-based monetization built in. | |
| agent-obsidian-mcp dbko/agent-obsidian-mcp Local MCP servers for the Agent-Obsidian workflow, providing vault file I/O, todo management, and arXiv paper fetching with zero-dependency single-file Node.js scripts. | |
| tmux-bridge-mcp dblanchard5035/tmux-bridge-mcp Enables AI coding agents running in separate tmux panes to read each other's output, send messages, and inject keystrokes, so multiple agents can coordinate workflows, hand off tasks, and review each other's work without manual copy-pasting | |
| Postgres MCP Pro dblinick/postgres-mcp-pro-streamable An MCP server for PostgreSQL with index tuning, explain plans, health checks, and safe SQL execution. | |
| PTY MCP Server dblmca/pty-mcp Enables AI assistants to manage interactive pseudo-terminal (PTY) sessions for programs requiring full terminal emulation like vim, ssh, and interactive REPLs. It provides tools to spawn sessions, send input with escape sequences, and read | |
| apple-reminders-mcp dbmcco/apple-reminders-mcp Enables Claude to manage Apple Reminders on macOS, including creating, reading, updating, deleting, and searching reminders across multiple lists with due dates, priorities, and notes. |
42,951–43,000 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.