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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| run-sql-connectorx gigamori/mcp-run-sql-connectorx Executes SQL queries via ConnectorX and streams results to CSV or Parquet files, supporting multiple databases and optional token counting for CSV output. | |
| Securedact MCP giganteshji/securedact-mcp Local-first privacy MCP server for sensitive AI workflows | |
| Giggy Speech MCP giggy-ai/giggy-mcp Giggy speech tools for AI agents: discover voices and generate text-to-speech. | |
| io.github.gigshow/decker gigshow/decker-ai Deterministic market-state engine for trading agents — state, gate, coordinates, with receipts. | |
| Bareun — Korean NLP & Spell/Grammar Checking gih2yun/bareun-mcp Korean NLP MCP server: morphological analysis, tokenization, spell & grammar checking (Bareun) | |
| io.gildara/mcp-server gildara-io/mcp-server Operating contracts for AI agents. Structured instructions compiled into system prompts. | |
| io.github.gilesdawe/tokei-agent gilesdawe/tokei-agent Control your Tokei (tokei.io) pre-launch and waitlist campaigns from AI agents and the command line. | |
| Giljo HQ giljoai/giljo-hq Context engineering for AI coding agents: product context, project missions, and 360 memory. | |
| io.github.GillMacedo/chargescout gillmacedo/chargescout Find subscriptions, price increases and double charges in a bank statement CSV, on your machine. | |
| io.github.GillMacedo/lapsewatch gillmacedo/lapsewatch Find customers who stopped buying, and the revenue at risk, from an orders CSV on your machine. | |
| io.github.GillMacedo/latepayers gillmacedo/latepayers AR aging from an invoice CSV: who owes what, how late, and who to chase first, on your machine. | |
| io.github.GillMacedo/runwaystock gillmacedo/runwaystock Find what to reorder, stockout dates and dead stock from sales and stock CSVs, on your machine. | |
| io.github.GillMacedo/samecontact gillmacedo/samecontact Find duplicate customers and contacts in CSV exports. Your data stays on your machine. | |
| io.github.GillMacedo/slowplan gillmacedo/slowplan Find why a PostgreSQL query is slow from its EXPLAIN output, without a database connection. | |
| io.github.GillMacedo/stalemodel gillmacedo/stalemodel Catch outdated AI model names, and look up current models, prices and limits. | |
| io.github.GillMacedo/stuckgo gillmacedo/stuckgo Find what a stuck Go program is waiting on from a goroutine dump, with no connection to it. | |
| io.github.GillMacedo/tiedout gillmacedo/tiedout Match bank statements to invoices from local CSV files. Your data stays on your machine. | |
| Maya MCP gimbalgoats/gg_mayamcp Control Autodesk Maya scenes with 71 typed tools for modeling, animation, shading, and more. | |
| Gingerguide: European city walking tours gingerguide/gingerguide Read-only European city sights: search, nearby, walking routes and itineraries in 6 languages. | |
| GingerLive gingerlive-io/gingerlive-mcp GingerLive livestream ad formats, network reach stats, campaign case studies, and streamer program. | |
| Analook — Competitor Intelligence gingiris-1031/competitor-analysis-tool Competitor intelligence for AI agents — SEO, traffic, social, Product Hunt, pricing, AI insights. | |
| Gingugu gingugu/gingugu Persistent long-term memory for AI coding assistants. Local SQLite, no cloud - 16 MCP tools to store, search, relate, and consolidate typed memories with a confidence lifecycle, hybrid BM25 + semantic search, namespaces, a knowledge graph, | |
| ATS Jobs Gateway (Workday, Greenhouse, Lever, Ashby) ginugokz/ats-zero-browser-gateway Job postings from Workday, Greenhouse, Lever and Ashby, with added, updated and removed jobs. | |
| GrowBlocks Dev Kit gioluan/growblocks-devkit Build, play-test with screenshots, and ship three.js browser games on GrowBlocks. | |
| gateonai-mcp-server giorgio44/gateonai-mcp-server Search 2,756+ verified AI tools, generate step-by-step AI workflows, compare tools head-to-head, and find GDPR-compliant or EU-hosted AI solutions — powered by GateOnAI, Europe's AI Workflow Intelligence Platform. | |
| io.github.giovanemartins/localstack giovanemartins/localstack-mcp-server MCP server for LocalStack AWS services, enabling AI agents to interact with local AWS infra. | |
| io.github.GiovannaFilippini/gazzetta-mcp giovannafilippini/gazzetta-mcp Free, local MCP server to consult and search the Italian Gazzetta Ufficiale. Unofficial. | |
| io.github.girik-chadha/interviewer-mcp girik-chadha/interviewer-mcp Full technical interview prep: company briefing, concepts, code deep-dive, mock interviews. | |
| rostrum girishkvs/rostrum Clean up talk recordings: find redos, retakes and dead air, review every cut, render and verify. | |
| SpecPilot girishr/specpilot Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent | |
| io.github.girmmy/google-tasks girmmy/google-tasks-mcp-server Read/write Google Tasks: create, update, complete, delete, move tasks and lists, with due dates. | |
| Giskard Memory giskard09/giskard-memory Pay-per-use semantic memory for AI agents. SHA256 commitment, Ed25519 sig, Lightning. | |
| MySQL MCP gistrec/mcp-mysql-client MCP server for one MySQL database: schema, read-only queries and guarded writes. | |
| io.github.gitajhd/amanchain gitajhd/amanchain AmanChain: quantum-resistant x402 payments. Remote MCP, 50 paid services. USDC on Base or AMAN. | |
| io.github.gitajhd/amanchain-mcp gitajhd/amanchain-mcp 59 pay-per-call AI services as MCP tools with automatic x402 USDC-on-Base payment. | |
| Twin Me Up gitdakky/twin-me-up A personal work twin for every AI agent: your confirmed guidance and explicit grants, enforced. | |
| Calculator MCP Server githejie/mcp-server-calculator A Model Context Protocol server that enables LLMs to perform precise numerical calculations by evaluating mathematical expressions. | |
| GitHits githits-com/githits-cli Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples. | |
| Lotor githubscum/lotor A local receipt and approval gate for AI agent sessions. The agent can act, but it cannot sign. | |
| GitLumen MCP gitlumen-team/gitlumen-mcp Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals. | |
| io.github.gitmem-dev/gitmem gitmem-dev/gitmem Persistent institutional memory for AI coding agents. Memory that compounds. | |
| ntfy-me-mcp gitmotion/ntfy-me-mcp A streamlined MCP server that enables AI assistants to send real-time notifications to your devices through the ntfy service, allowing you to receive alerts when tasks complete or important events occur. | |
| Gitopia MCP Server gitopia/gitopia-mcp-server Decentralized Git with on-chain governance, bounties, and DAOs. Tools for repos, issues, PRs, labels, releases, bounties, and DAO proposals.
Auto-wallet on first use, trust tiers, and approval mode for human-in-the-loop. | |
| io.github.gitscrum-core/mcp-server gitscrum-core/mcp-server MCP server for GitScrum — manage tasks, sprints, time tracking, and client workflows via AI | |
| AOTrust Notarization & Evidence Server gitserge-crypto/aotrust-skills Cryptographic proof of existence for AI agents. x402 on Base or Solana, NEAR anchored. Free tier. | |
| Mermaid MCP Server gittyburstein/mermaid-mcp-server Enables agents to analyze codebases (local or GitHub) and automatically generate Mermaid diagrams rendered as PNG images via Kroki, providing visual understanding of project structure and flow through file discovery, reading, and diagram ge | |
| io.github.gitwormq/datasieve gitwormq/datasieve-mcp On-chain watches, web-page monitors, dead-man switches, cron, and agent coordination, paid via x402. | |
| io.github.giuliobmb/exam-sheet giuliobmb/exam-sheet-mcp Generate a timed exam on any topic and take it in an interactive exam sheet with live grading. | |
| RE-call MCP Memory Server giulioder/re-call Agent memory on your own Postgres that flags superseded facts and abstains instead of guessing. | |
| Doc Manager giuliohome-org/doc-manager Zero-knowledge document vault backed by Azure Blob Storage with built-in MCP server. Client-side AES-256-GCM encryption, five tools (list, get, search, create, update), and OAuth-gated access for Claude. |
8,351–8,400 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.