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 |
|---|---|
| n8n-MCP acrt-eval/n8n-mcp-72-cr7 Provides AI assistants with structured access to n8n node documentation, properties, operations, and AI tool metadata so they can understand and build n8n workflows; optional n8n API credentials also enable workflow management. | |
| n8n-MCP acrt-eval/n8n-mcp-72-cr9 Provides AI assistants with structured access to n8n node documentation, properties, operations, and validation tools so they can build and troubleshoot workflows; with API credentials, it can also create, update, and execute workflows. | |
| Ouroboros acrt-eval/ouroboros-234-cr1 Enables AI coding agents to conduct Socratic interviews, crystallize answers into immutable specifications, execute staged development, and run automated evaluation and evolutionary loops until convergence. | |
| Ouroboros acrt-eval/ouroboros-234-cr10 Enables AI coding agents to run a specification-first workflow through MCP tools: Socratic interview, immutable seed specification, execution, staged evaluation, and evolutionary loops. This helps turn vague ideas into verified, working cod | |
| Ouroboros acrt-eval/ouroboros-234-cr5 Enables AI coding agents to run a specification-first workflow with Socratic interviews, immutable seed specs, staged evaluation gates, and persistent evolutionary loops across multiple runtimes. | |
| Ouroboros acrt-eval/ouroboros-234-cr7 Enables AI coding agents to run a specification-first workflow through MCP tools: Socratic interviews, immutable seed specifications, execution, staged evaluation, evolutionary loops, and PM/PRD generation. | |
| x402tools MCP Server acrylicfiddle/x402tools-mcp Provides AI agents with 10 pay-per-call utility tools (QR generation, DNS lookup, OCR, etc.) using USDC on Base via the x402 protocol, with agent's private key never leaving the agent. | |
| beebjit-mcp acscpt/beebjit-mcp Lets an AI application instantiate, connect to, drive, capture output from, and interrogate a real BBC Micro emulator. | |
| AEM Block Collection MCP Server acsgenui/mcp-block-collection Enables access to AEM block metadata by reading structured information from blocks.json files. Provides a simple tool to list available blocks with their descriptions, file paths, and counts. | |
| mcp-orchestrator-framework acsgenui/mcp-orchestrator-framework A configurable MCP server that enables creating custom analysis tools through JSON configuration, with built-in frameworks for error handling, self-evaluation, security guardrails, and output artifacts. | |
| Cisco Secure Access MCP Server acsmith1337/cisco-secure-access-mcp Enables AI agents to investigate threats, pull reports, manage security policies, and administer deployment infrastructure through the Cisco Secure Access REST API. | |
| @actalumen/mcp-server actalumen/mcp-server Enables AI agents to upload, verify, and chat about documents for compliance (e.g., SOC2, GDPR) with PII redacted server-side. | |
| workhorse-ai-mcp actari/actari-mcp Provides an append-only SQLite journal for orchestrator/worker AI workflows, enabling delegation, reporting, verification, and tracking of tasks with built-in search and optional cloud sync. | |
| GTNH MCP actforever/gtnh-mcp Enables authenticated AstrBot group chats to perform GTNH server operations such as player queries, announcements, world saves, whitelist management, backup listing, and admin-confirmed restores with rollback support. | |
| MCProbe actions-marketplace-validations/alitiknazoglu_mcprobe A stdio MCP server that audits other MCP servers by linting their tool schemas and calling tools with malformed inputs to produce a 0–100 conformance score and Markdown report. | |
| Maxion actions-marketplace-validations/aruuhii2yo_maxion-mcp Enables AI agents to run with autonomous thermal/energy pacing, real-time threat interception, and AES-256-GCM encrypted state vaulting entirely in-process under 50 microseconds. | |
| n8n-mcp actions-marketplace-validations/automatelab-tech_n8n-mcp An MCP server for n8n that gives AI agents tools for generating workflows, linting, diagnosing failed executions, and driving live n8n instances. | |
| release-intel-mcp actions-marketplace-validations/barissozudogru_release-intel-mcp Enables building structured release evidence by comparing two Git refs and correlating commits, merged pull requests, linked issues, labels, changed files, and contributors. | |
| mcp-heimdall actions-marketplace-validations/caglarbozkurt_mcp-heimdall Enables agents to vet MCP servers and agent configurations before trusting them, using local static analysis to detect injection, dangerous capabilities, exfiltration paths, and CVEs, with policy-based gating for CI. | |
| ci-guard-mcp actions-marketplace-validations/carelessdept_ci-guard-mcp Enables MCP clients to run local, read-only audits that detect risky GitHub workflows, undocumented environment variables, possible credentials, and conflicting dependency configuration before merging. | |
| skill-audit-mcp actions-marketplace-validations/eltociear_mcp-security-audit Enables static security scanning of MCP servers, AI agent skills, and plugins by detecting attack patterns across severity levels and producing SARIF output for GitHub Code Scanning. | |
| Elliot actions-marketplace-validations/emanuelecell4_elliot-mcp Enables AI agents and developers to independently verify code and documentation claims against the repository, producing evidence-backed audit reports and pull-request checks. | |
| mcp-authprobe actions-marketplace-validations/enigmacker_mcp-authprobe Enables active, authorized security testing of remote MCP servers' OAuth authorization flows, reporting results as JSON, SARIF, and Markdown. It runs checks for refresh token rotation, redirect URI strictness, PKCE enforcement, token audien | |
| MCP Rigor actions-marketplace-validations/fusiononeplatform_mcprigor Enables natural-language testing of MCP servers—covering tools, resources, prompts, contracts, and transports—without writing test code, with deterministic validation and CI integration. | |
| mcp-pin actions-marketplace-validations/gautamtalksdev_mcp-pin A read-only MCP server that lets an agent check whether a public MCP server's tool definitions have changed, and whether any locally pinned server has a change waiting for review. It also returns the exact setup steps for protecting servers | |
| mcpcost actions-marketplace-validations/ondraulehla_mcpcost Enables agents to look up and search servers from the official MCP registry, probe any server live for availability, protocol, auth, tools and context-token cost, and retrieve registry-wide statistics. Also supplies a CLI and GitHub Action | |
| pkg-health-mcp actions-marketplace-validations/orcsnren_pkg-health-mcp Enables AI agents and developers to score npm packages, PyPI packages, and GitHub repositories for maintenance health, producing A–F grades, per-signal details, and plain-language risk lists before adoption. It supports checking individual | |
| shutup-mcp actions-marketplace-validations/schchit_shutup-mcp Acts as a proxy between an MCP client and one or more MCP servers, aggregating upstream tool definitions and exposing only the top-k tools that best match the current task intent. It enables users to shrink large tool catalogs via hybrid re | |
| mcp-deprecate actions-marketplace-validations/shurugiken_mcp-deprecate MCP server that scans source code for MCP protocol features deprecated or removed by the 2026-07-28 release candidate, offering tools to inspect spec compatibility and generate migration checklists. | |
| mcp-tenant-isolation actions-marketplace-validations/subodhkc_mcp-tenant-isolation Static analysis scanner for multi-tenant SaaS and MCP server code that catches cross-tenant data leakage with 57 deterministic rules, including an MCP server for Claude Desktop and Cursor integration. | |
| mcpgrade actions-marketplace-validations/tengbyte_mcpgrade Enables agents to grade other MCP servers for LLM usability, covering descriptions, schema design, naming, token cost, and consistency, while also explaining grading rules. | |
| mcpgrade actions-marketplace-validations/tenglidev_mcpgrade Runs as an MCP server that lets an agent grade other MCP servers for agent usability, explain grading rules, and list available rules. It enables automated assessment of tool descriptions, schemas, naming, token cost, consistency, and optio | |
| mcp-security-toolkit actions-marketplace-validations/x0base_mcp-security-toolkit Provides security audit primitives for MCP servers, agent tool schemas, and system prompts, along with pentest utilities like JWT inspection and HTTP diffing. | |
| ats-mcp actiontestscript/ats-mcp Test automation across web, mobile, desktop, API, and SAP GUI via ActionTestScript. 30 tools covering the Playwright MCP surface plus native multi-platform reach. | |
| Teamwork MCP activ8-ai/teamwork-mcp An MCP server that connects to the Teamwork API, providing tools to manage projects, tasks, companies, people, time entries, and reports, with built-in competitive intelligence capabilities. | |
| TTS MCP Server activebook/tts-mcp-server Provides Text-to-Speech (TTS) functionality using Google TTS API, enabling audio generation, voice listing, and style templates via MCP. | |
| Postmark MCP Server activecampaign/postmark-mcp An MCP server implementation that enables sending emails via Postmark email services with features for sending plain text/HTML emails, using templates, tracking delivery statistics, and listing available templates. | |
| mcp-google-sheets activepieces/activepieces Google sheets. | |
| Master Brain MCP Hub activi-ai/master-brain-mcp-hub A central knowledge hub that connects AI tools to a unified 'Master Brain' with automated memory capabilities. It utilizes intelligent analysis to automatically capture and store key decisions, fixes, and learnings across various developmen | |
| LabScout actogram/scholar-mcp Enables AI assistants to search public sources for labs, papers, grants, clinical trials, and patents on a research topic, returning ranked labs with explanations, researcher profiles, and geographic data. | |
| Standup Voice actualjudgepresident/standup-voice Enables building a daily standup from real GitHub activity and spoken notes, exposing tools to fetch a voice-ready summary, capture tasks, bugs and blockers, list and complete items, and file deduplicated GitHub issues. Output is voice-firs | |
| AcuityScan MCP Server acuityscan/mcp Enables AI clients to run comprehensive website scans for security, accessibility, performance, and SEO using the AcuityScan API. | |
| n8n Forum MCP acunningham-ship-it/n8n-forum-mcp Enables AI agents to search and read solved threads from the n8n community forum for vetted solutions. | |
| acuris-agent-guard acuris-gmbh/acuris-agent-guard MCP server that verifies storefront merchants before AI agents make payments, checking if the merchant is a real legal entity bound to the domain, and returning a PROCEED, ABORT, or REVIEW decision to prevent payment to clones or fraudulent | |
| mcp-stub acus9345/mcp-stub Enables testing AI agents against a scripted mock MCP endpoint where each tool call returns a chosen response, fails, hangs or drops the connection, and where assertions verify which tools were called, how often, in what order and with what | |
| publish-pilot-mcp acus9345/publish-pilot-mcp Enables Claude to take a project from an empty folder to a published GitHub repository and npm, PyPI, or crates.io package. It automates preflight checks, scaffolding, quality checks, publishing, trusted-publishing setup, tagging, and relea | |
| mcp-tenki acxelerator/mcp-tenki Get weather of Japan | |
| repository-runtime acydusx/repository-runtime Enables AI agents to search, read, and traverse a local knowledge base of Markdown files using full-text search and relationship graph, reducing token usage. | |
| Swift Test MCP Server acyment/swifttest-mcp-server Enables running Swift package tests through the swift test command in specified directories. Provides a secure way for MCP clients to execute Swift tests without requiring full shell access. | |
| agent-eval-mcp ad-github1/enterprise-ai-agent-evaluation-platform An MCP-style stdio server for evaluating AI agent outputs, enabling CI-friendly quality gates, regression comparisons, and canary promotion decisions. |
23,501–23,550 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.