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 |
|---|---|
| ReelClaw Create, produce, and publish UGC-style short-form video reels at scale. Full pipeline: source UGC reaction hooks from DanSUGC, analyze app demos with Gemini... | |
| LLM Monitor Monitor and report usage, costs, quotas, and rate limits for LLM providers, plus manage clawmeter setup and daemon status securely. | |
| LobsterLAN Communicate with other OpenClaw agents on your local network. Use when you need to ask another agent a question (sync), delegate a task (async), or check if... | |
| OfficeClaw Connect to personal Microsoft accounts via Microsoft Graph API to manage email, calendar events, and tasks. Use this skill when the user needs to read/write Outlook mail, manage calendar appointments, or handle Microsoft To Do tasks. | |
| gcal-oauth-bridge Interact with the Calendar Bridge — a self-hosted Node.js service that provides a persistent REST API for Google Calendar events. Handles OAuth token auto-re... | |
| Perpetua OAuth proxy for calling external APIs (Oura, Google Calendar, etc.) via Perpetua.sh hosted API using a single API key. Use when fetching Oura data, Google Ca... | |
| mcdonalds-mcp-order-lite Place McDonald's China delivery orders through the official MCP server at https://mcp.mcd.cn using a Bearer MCP token over Streamable HTTP / JSON-RPC. Use wh... | |
| opensoulmd Search, summon, and possess your agent with SOUL.md personality files from the OpenSOUL.md registry | |
| CI Flake Triage Detect flaky tests from JUnit XML retries and emit a triage report with top unstable cases. | |
| Dockerfile Hardening Audit Statically audit Dockerfiles for common container hardening risks (root user, unpinned/latest base images, missing healthchecks, and risky build patterns). | |
| Env Alias Audit Audit .env alias groups for missing required config, conflicting values, and canonical-key drift before deploy. | |
| GitHub Actions Actor Reliability Audit Audit GitHub Actions run reliability by actor to surface high-risk contributors and flaky automation owners. | |
| GitHub Actions Artifact Budget Audit Audit GitHub Actions artifact storage usage from JSON exports so bloated artifacts are flagged before they inflate CI cost. | |
| GitHub Actions Branch Drift Audit Detect branch-level GitHub Actions reliability drift by comparing failure and runtime deltas against a mainline baseline. | |
| GitHub Actions Cache Hardening Audit Audit GitHub Actions workflow cache usage for poisoning, keying, and secret-path risks. | |
| GitHub Actions Cancel Waste Audit Audit cancelled and timed-out GitHub Actions runs from JSON exports to surface wasted CI minutes and noisy workflows. | |
| GitHub Actions Commit Health Audit Audit GitHub Actions reliability by commit SHA to surface risky commits causing repeated workflow failures across branches. | |
| GitHub Actions Conclusion Volatility Audit Audit GitHub Actions workflow conclusion volatility to surface unstable pipelines before they become chronic failures. | |
| GitHub Actions Deploy Risk Audit Audit deployment workflow risk from GitHub Actions runs by scoring failure rate, unresolved failure streaks, and time since last successful deploy. | |
| GitHub Actions Duplicate Run Audit Detect duplicate GitHub Actions run bursts by workflow/branch/commit and quantify wasted rerun minutes. | |
| GitHub Actions Failure Hour Audit Audit GitHub Actions failure timing by day/hour to surface recurring outage windows and staffing hotspots. | |
| GitHub Actions Failure Matrix Summarize GitHub Actions matrix job failures across runs so you can spot unstable OS/runtime axes fast. | |
| GitHub Actions Failure Owner Audit Audit failing GitHub Actions runs by actor ownership to expose who/workflow combinations generate the most CI noise and wasted minutes. | |
| GitHub Actions Failure Phase Audit Group GitHub Actions failures by pipeline phase (setup/build/test/lint/deploy/security) with minute impact to prioritize fixes. | |
| GitHub Actions Failure Spike Audit Detect sudden GitHub Actions failure-rate spikes by workflow group using recent-vs-baseline run windows. | |
| GitHub Actions Failure Streak Audit Detect consecutive GitHub Actions failure streaks by repo/workflow/branch to prioritize unstable pipelines. | |
| GitHub Actions Incident Timeline Audit Cluster failed GitHub Actions runs into incident windows by repo to expose outage duration, impact scope, and escalation severity. | |
| GitHub Actions Mainline Health Audit Audit GitHub Actions mainline branch reliability by scoring failure rate, consecutive failures, and stale-success risk for critical workflows. | |
| GitHub Actions Manual Trigger Audit Audit manual GitHub Actions trigger dependence by workflow/event to flag automation gaps and intervention risk. | |
| GitHub Actions Merge Queue Health Audit Audit GitHub merge queue workflow health with failure-rate, queue-latency, and stale-success risk scoring. | |
| GitHub Actions OIDC Hardening Audit Audit GitHub Actions cloud auth workflows for OIDC hardening gaps like missing id-token write permissions, static cloud secrets, and floating auth action refs. | |
| GitHub Actions Permission Scope Audit Audit GitHub Actions workflow permission scope drift to enforce least-privilege token access. | |
| GitHub Actions PR Gate Health Audit Audit pull-request and merge-queue GitHub Actions reliability by scoring failure rate, queue latency, and stale-success risk for merge gates. | |
| GitHub Actions Queue Latency Audit Audit GitHub Actions queue wait hotspots from run/job JSON so CI bottlenecks are visible before they stall merges. | |
| GitHub Actions Recovery Latency Audit Measure GitHub Actions failure recovery latency and unresolved incident age by workflow group. | |
| GitHub Actions Rerun Effectiveness Audit Audit GitHub Actions rerun dependency and success-after-rerun effectiveness to highlight workflows wasting CI time. | |
| GitHub Actions Rerun Waste Audit Quantify wasted GitHub Actions minutes caused by reruns so flaky workflows can be fixed with data. | |
| GitHub Actions Retry Recovery Audit Audit GitHub Actions runs for fail-then-success retry recovery patterns to quantify flaky rerun waste. | |
| GitHub Actions Run Gap Audit Detect GitHub Actions workflow groups that stopped running on their normal cadence using median run intervals and current inactivity gap. | |
| GitHub Actions Runtime Regression Audit Compare baseline vs current GitHub Actions run exports to catch workflow/job runtime regressions before CI costs and lead time spike. | |
| GitHub Actions Secret Exposure Audit Audit GitHub Actions workflow files for secret exposure risks like pull_request_target secret usage, secret echo commands, and unpinned action secret passing. | |
| GitHub Actions Self-Hosted Risk Audit Audit GitHub Actions workflows that use self-hosted runners for untrusted trigger and credential-hardening risks. | |
| GitHub Actions SHA Rerun Debt Audit Audit rerun debt by commit SHA to find commits that repeatedly burn CI minutes across workflows. | |
| GitHub Actions Step Flake Audit Detect flaky GitHub Actions job steps by finding mixed success/failure conclusions across runs. | |
| GitHub Actions Stuck Run Audit Detect stale queued/in-progress GitHub Actions runs before they quietly block delivery. | |
| GitHub Actions Timeout Risk Audit Audit GitHub Actions job runtime risk against timeout thresholds so near-timeout jobs get fixed before they fail CI. | |
| GitHub Actions Trigger Health Audit Audit GitHub Actions run health by trigger event and workflow so flaky or noisy automation sources are easy to prioritize. | |
| GitHub Actions Workflow Hardening Audit Audit GitHub Actions workflow files for hardening gaps (missing timeouts/permissions/concurrency and floating action refs). | |
| JUnit Failure Fingerprint Cluster JUnit failures into stable fingerprints so CI triage focuses on root causes, not noisy one-off logs. | |
| Prisma Migrate Guard Preflight Prisma migration state before deploy; fails fast on drift, failed migrations, missing DB URLs, or unapplied migration files. |
23,901–23,950 of 108,824
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.