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 |
|---|---|
| Local Repo Automation MCP ersonumech/mcp Enables inspecting local Git repositories and automating delivery tasks such as status checks, diffs, commits, pull requests, and deployments using git and GitHub CLI. | |
| Erstan Agent Tools Beta erstanai/erstan-agent-tools-beta Enables building, optimizing, reviewing, and running AI agents and skills, plus managing authorized work items, in Erstan's QA environment via OAuth-authenticated MCP. | |
| time-toolkit erstcl/time-toolkit Enables interaction with Time Messenger and Mattermost-compatible servers via their REST API, supporting reading, writing, and event streaming with configurable write policies for safety. | |
| chainlead ert1981/chainlead Enables agents to create and run Web3 B2B lead-discovery campaigns, list qualified leads, retrieve opportunity briefs, and inspect offers and budgets via MCP tools. | |
| arena-mcp ertekinno/arena-mcp Enables AI agents to interact with Are.na for creative research and knowledge curation, including searching, browsing, creating, and managing channels, blocks, comments, and connections. | |
| LinkedIn MCP Assistant ertiqah/linkedin-mcp-runner LinkedIn MCP Assistant | |
| Tradingview Chart MCP ertugrul59/tradingview-chart-mcp MCP server that captures TradingView chart images via Selenium — supports any ticker/interval with browser pooling for concurrent performance | |
| Unravel MCP eruditecoder108/unravel-mcp A deterministic AST evidence engine that forces AI agents to debug using verified execution facts instead of pattern-matching symptoms, enabling hallucination-free debugging for MCP-compatible agents. | |
| icloud-mail-calendar-contacts-mcp eruveo/icloud-mail-calendar-contacts-mcp Enables access to iCloud mail, calendars, and contacts over MCP through IMAP/SMTP, CalDAV, and CardDAV, with configurable read/write and deletion permissions. | |
| ops-mcp-server erveepp/mcp-server Enables natural language management of landing pages and ad campaigns, with dry-run confirm and audit for write operations. | |
| BugForge ervikasti/bugforge AI-powered QA defect reporting MCP server that generates Jira-ready defect reports with business context, reproduction steps, and priority from test scenarios and error details. | |
| my-remote-mcp-py ervin-zhang/my-remote-mcp-py A remote MCP Server demo using FastMCP and Streamable HTTP, offering tools (add, now, fetch_url_title, long_task with progress), resources, prompts, and autocomplete for remote client connections. | |
| gws-mcp ervinpopescu/gws-mcp Enables AI agents and LLMs to directly access Google Workspace APIs such as Drive, Docs, Sheets, Gmail, and Calendar by executing gws CLI commands through MCP tools. | |
| tushare-mcp-server erwanjun/tushare-mcp-server Provides AI assistants with access to Chinese financial market data via the Tushare Pro API, covering stocks, indices, funds, futures, options, bonds, forex, and macroeconomic indicators. | |
| irpp-mcp erwanpaccard/irpp-mcp A Python MCP server that calculates French income tax using the official DGFiP source code compiled locally. It enables accurate tax simulations for 2023 income based on real French tax forms without network calls. | |
| railway-sandbox-mcp erwinkn/railway-sandbox-mcp Enables ChatGPT to create, manage, and execute commands in ephemeral isolated Linux sandboxes on Railway, with file operations and checkpointing. | |
| Ibid eryc123y/ibid-mcp Enables AI agents to search scholarly literature across Semantic Scholar, OpenAlex, arXiv, OpenReview, and CORE through one compact, rate-limit-aware interface, merging and de-duplicating results into a single list. | |
| zvex erzat1986/zvex Enables AI video dubbing by letting users submit video URLs for dubbing into Russian, English, or Spanish while preserving original speakers' voices through voice cloning, plus job status and cost estimation tools. | |
| mcp-app-server erzhiqianyi/mcp-app-server Enables existing apps to expose their users and data to external AI agents via MCP with OAuth 2.1 authentication and scoped tools. | |
| code-review-graph es-3581100/code-review-graph Enables AI coding assistants to query a persistent local code graph for targeted context, blast-radius analysis, and incremental updates, so they read only relevant files during reviews and large-repo workflows. | |
| system-one-mcp es11225599/systemone-mcp Enables MCP clients to evaluate typed choice, score, and noul questions and list available models on configured backends such as Ollama nimble/tev/clef, TypeSafe jev, Kev, or Laya via two stdio tools. | |
| Turf-MCP es3154/turf-mcp Provides comprehensive geospatial analysis capabilities through Turf.js, enabling spatial measurements, geometric operations, coordinate transformations, and geographic data processing. Supports over 100 geospatial functions including dista | |
| cc-tap es617/cc-tap An MCP server that bridges Claude Desktop and Claude Code by letting Desktop read and interact with Claude Code Remote Control sessions, enabling cross-agent coordination. | |
| claude-sessions-mcp es6kr/claude-code-sessions Browse, search, rename, split, and clean up Claude Code sessions via MCP, Web UI, or VSCode extension. | |
| claude-session-manager es6kr/claude-session-manager-mcp Claude Code Session Manager | |
| claude-sessions-mcp es6kr/claude-sessions-mcp MCP server for managing Claude Code conversation sessions | |
| mcp-first-server esaban17/mcp-first-server Provides an add tool for summing two numbers and a greeting://{name} resource that returns a personalized greeting over stdio. | |
| mcp-mysql-database esaban17/mcp-mysql-database Enables Claude to work with local MySQL databases through natural language, including creating databases and tables, performing CRUD operations, switching between configured connections, and executing safe read-only or write SQL. | |
| qgis-mcp esaban17/qgis-mcp Enables controlling QGIS to generate thematic maps over a project polygon, automatically styling and clipping layers, creating print layouts, and exporting them as PDF, PNG, JPG, or TIF. It also supports headless operation and map series wi | |
| MCP Streamable HTTP Example esaghapour/mcp-streamable-http-master1 Demonstrates building an MCP server with Python, exposing tools like web search (Tavily) and basic utilities over streamable HTTP for AI assistants like Cursor. | |
| Hotels MCP Server esakrissa/hotels_mcp_server A Model Context Protocol (MCP) server that allows LLMs to search for hotels and destinations using the Booking.com API. | |
| MCP Documentation Server esakrissa/mcp-doc A customized MCP server that enables integration between LLM applications and documentation sources, providing AI-assisted access to LangGraph and Model Context Protocol documentation. | |
| code-map-mcp esalling23/code-map Enables agents to generate a JSON sitemap of how a path through a TypeScript/JavaScript codebase runs, capturing the summary, areas, every step with its file, lines, description, calls and data, and the links between services. The resulting | |
| gemini-research-mcp esanii/gemini-research-mcp An MCP server that adds real-time web research to Claude Desktop using Gemini 2.5 Flash with native Google Search grounding. | |
| RepoRecall esannkv/reporecall Provides persistent, local-first memory for coding agents with Markdown as the source of truth, exposed via CLI, loopback API, MCP, and Codex hooks for context retrieval and durable writes. | |
| mcp-mautic esanum/mcp-mautic Comprehensive MCP server for the Mautic marketing automation API, providing 203 tools for managing contacts, campaigns, emails, segments, and more. | |
| mcp-gate esarijal/mcp-gate Enables Claude to access and manage multiple Buffer accounts through a single OAuth-protected connector, including listing accounts, channels, and posts and creating, editing, or deleting posts across accounts. | |
| MSSQL-MCP esasiyun17/mssql-mcp Security-first, read-only MCP server for Microsoft SQL Server, enabling safe natural-language querying of databases. | |
| pg-logical-mcp esauro/pg-logical-mcp Diagnoses and manages PostgreSQL logical replication including slot WAL retention, walsender lag, stuck subscriptions, and provides gated remediation tools for safe AI-driven operations. | |
| samskriti-project escalate17/samskriti-shared-layer A local MCP server that enables multiple AI coding tools to share structured project state (decisions, tasks, bugs) so they coordinate without re-explaining. | |
| Accessible Visit MCP escape-velocity-by-sh-sw/barrier_free_trip-public Enables users with mobility impairments to assess tourist destination accessibility by providing integrated information on barrier-free facilities, weather conditions, nearby wheelchair charging stations, and festival-based congestion risk | |
| chrome-agent-bridge escapewu/chrome-agent-bridge MCP server for agent interaction with user-approved Google Chrome tabs, enabling tab listing/control, navigation, clicking, filling, snapshots, and screenshots via a local authenticated bridge. | |
| Pokémon MCP Server escasann/mcp_pokemon Enables interaction with live Pokémon data through PokeAPI, providing comprehensive Pokémon information, battle calculations, moveset validation, and team analysis. Supports searching Pokémon and moves, calculating stats, checking type effe | |
| Humanitarian Negotiation MCP Server escenariosparalatransformacion/humanitarian-mcp Enables humanitarian negotiators to analyze complex situations using proven methodologies like Island of Agreement, Iceberg analysis, and stakeholder mapping. Provides structured frameworks for establishing common ground, understanding deep | |
| Excel MCP Server eschaq/excel-mcp-server Enables Claude to open, filter, search, summarize, and write local .xlsx, .xlsm, .xls, and .csv spreadsheets through ten tools, all running locally with no Microsoft Office installed. Access is sandboxed to folders you allow, with an option | |
| beyond-mcp eschatus/beyond-mcp Enables D&D Beyond integrations through MCP by reading character sheets, monster statblocks, and campaign rosters, plus streaming live game-log dice rolls with optional write tools for HP and conditions. | |
| telegram-mcp escolhaperfeitani/telegram-mcp-claude Connects AI assistants to a Telegram bot so the model can message the user, send files, ask questions and wait for button answers, and read or search chats, groups and forum topics. It also lets the assistant reply as the user in connected | |
| netmiko-mcp escrimaglia/netmiko-sot_mcp Provides read-only SSH access to network devices (routers, switches, firewalls) with command allow/deny policies, nt-templates output parsing, and an audit trail, enabling an AI agent to query device state securely. | |
| auranet-omni-engine esdecy/auranet-omni-engine Omni-channel x402-gated MCP Oracle providing structured data across 12 verticals monetized via Base USDC micropayments. | |
| local-events-mcp esdraelon/date-night-event-list-mcp A small MCP server that scrapes and returns semantic event data from configured sources, supporting tools to list sources, validate scrapers, and retrieve events by time period or date. |
48,601–48,650 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.