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 |
|---|---|
| Anyfetch aliasmode/anyfetch Web search and web fetch with no API keys. Reads the sites that refuse AI agents. | |
| OuterSpace Apizr alien6-studio/outerspace-apizr Python capability compiler: read-only analysis, experiment history/comparison and exposure planning. | |
| Epsilon alienbase-xyz/epsilonrobinhood Non-custodial limit, stop-loss and DCA trading on Epsilon (Robinhood Chain) for AI agents | |
| ResiliReplay aliengineering-byte/resilireplay Run bounded, deterministic MCP reliability tests and generate executable regressions. | |
| io.github.Alightttt/chesswithclaw alightttt/chesswithclaw Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar. | |
| io.github.aligndottech/cli aligndottech/align-cli Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP. | |
| Mapflyover alihassan1437/mapflyover-mcp Create 3D map flyover videos with an AI agent: script, narration, captions and animated scenes. | |
| SA Business Calendar alimora83/sa-business-calendar-mcp South African business days, public holidays and SARS EMP201/VAT201 deadlines. | |
| Quantlix public content alimuhammadofficial/quantlix-agents Search and read published Quantlix services, company information and insights. | |
| Agent Readiness alipajand/agent-readiness-action Deterministic, read-only audits of repo readiness for AI coding agents and of agent context files. | |
| io.github.alipishbin77/aether alipishbin77/github-connector-test Marketplace where AI agents hire other agents, paid per call in USDC. Plus LLM inference. | |
| PressIt alireza99/pressit Compress, resize and convert images (JPG, PNG, WebP, GIF) locally. No API key, no uploads. | |
| app.allagents/directory allagents-app/allagents Find AI agents (A2A, MCP, API) with tested badges: search, read cards, relay messages, list agents. | |
| Boat House allenzhangyiteng/boathouse-cloud Deploy and share small apps with team login, persistent data, versioned updates and domains. | |
| Git Why alliecatowo/git-why Finds the Git commits that explain why code is the way it is: semantic and full-text history search. | |
| Swamp allisonbit/bug-protocol An open habitat where security agents register themselves, work in public, and rerun each other. | |
| Capital Markets Agents: MCP+A2A allooloo/cm-kg KYP Agentic Trading: listed-issuer records served in-country, and AIO-10060 orderability outcomes. | |
| Alloy alloy-systems/work-with-alloy AI workspace — shared knowledge, skills, and tools for AI agents | |
| ai.usealloy/alloy alloyrobotics/alloy-web Connect Claude, Cursor, Codex, and other AI tools to your robotics mission data. | |
| es.ofixio/professionals allterraindeveloper/ofixio-mcp Find skilled tradespeople in Spain — fontaneros, electricistas, pintores, cerrajeros. | |
| Acorn Harness almond-bot/acorn-plugins Configure, price and order custom XT30, XT30(2+2) and XT30 + JST GH wire harnesses. | |
| LogoAPI.sh alonharpaz/logo-api Company logos by domain as SVG or PNG URLs. Free, no API key. Search brands, get favicons. | |
| Helvabase — Governed response dossiers alopez3006/helvabase-mcp Connect your AI assistant to governed tender and RFP dossiers: sources, versions, decisions. | |
| GoodWatch alp82/goodwatch-monorepo Find movies and TV shows, track watches, and get suggestions based on your taste. | |
| PhysioArt client booking alparlorincz/physioart Book, list, and cancel appointments for the signed-in client. | |
| GenPark Adaptive Batch Request Debouncer alphaparkinc/genpark-adaptive-batch-request-debouncer-skill Adaptive sliding window query debouncing and micro-batch coalescing engine optimizing LLM throughput | |
| GenPark Adaptive Exponential Backoff with Jitter Retry alphaparkinc/genpark-adaptive-exponential-backoff-jitter-retry-skill Full jitter exponential backoff retry scheduling and half-open circuit breaker for LLM APIs | |
| GenPark Agent State Snapshot & Time-Travel Skill alphaparkinc/genpark-agent-state-snapshot-time-travel-skill Agent conversation state snapshotting and time-travel rollback engine pruning divergent hallucinatio | |
| GenPark Aho-Corasick Multi-Pattern Matcher alphaparkinc/genpark-aho-corasick-multi-pattern-matcher-skill High-throughput Aho-Corasick automaton for simultaneous multi-keyword dictionary matching and conten | |
| GenPark AST Diff Semantic PR Summarizer alphaparkinc/genpark-ast-diff-semantic-pr-summarizer-skill Synthesize semantic AST delta trees across git diffs and classify breaking signature changes | |
| GenPark Bloom Filter URL Dedup Crawler alphaparkinc/genpark-bloom-filter-url-dedup-crawler-skill In-memory Bloom filter for URL and document hash deduplication preventing redundant web crawler inge | |
| GenPark Circuit Breaker Fault Sentinel alphaparkinc/genpark-circuit-breaker-fault-sentinel-skill Three-state circuit breaker with failure rate tripping and automatic half-open probe recovery | |
| GenPark Concurrency Semaphore Guard alphaparkinc/genpark-concurrency-semaphore-guard-skill In-memory concurrency leaky-bucket and fair semaphore guard protecting downstream LLM APIs from rate | |
| GenPark Consistent Hash Ring Router alphaparkinc/genpark-consistent-hash-ring-router-skill Consistent hashing ring with virtual nodes for distributed LLM cache routing and agent partitioning | |
| GenPark Context Window Token Pruner alphaparkinc/genpark-context-window-token-pruner-skill Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar | |
| GenPark Cron Jitter Scheduler Agent alphaparkinc/genpark-cron-jitter-scheduler-agent-skill Crontab syntax parser and distributed jittered task scheduler preventing thundering herds in autonom | |
| GenPark Distributed Deadlock Wait-For-Graph Detector alphaparkinc/genpark-distributed-deadlock-wait-for-graph-detector-skill Real-time Tarjan SCC cycle detection on lock Wait-For-Graphs with victim transaction arbitrator | |
| GenPark Distributed ID Snowflake Generator alphaparkinc/genpark-distributed-id-snowflake-generator-skill 64-bit Twitter Snowflake-compatible distributed unique ID generator with clock backwards drift prote | |
| GenPark Distributed Lease Lock Coordinator alphaparkinc/genpark-distributed-lease-lock-coordinator-skill In-memory distributed lease lock with monotonically increasing fencing tokens preventing multi-agent | |
| GenPark Entropy Hallucination Detector alphaparkinc/genpark-entropy-hallucination-detector-skill Token entropy and n-gram perplexity analyzer auditing LLM outputs for degenerate repetition loops an | |
| GenPark Exponential Backoff Jitter Retry alphaparkinc/genpark-exponential-backoff-jitter-retry-skill Enterprise retry engine with full jitter, decorrelated jitter, and truncated exponential backoff for | |
| GenPark Few-Shot MMR Diversity Selector alphaparkinc/genpark-few-shot-mmr-diversity-selector-skill Maximal Marginal Relevance (MMR) exemplar selector optimizing semantic relevance and diversity for L | |
| GenPark Git Commit Conventional Semantic Linter alphaparkinc/genpark-git-commit-conventional-semantic-linter-skill Conventional Commits 1.0.0 semantic linter and changelog grouping engine parsing breaking changes an | |
| GenPark Git Semantic Cherry-Pick Conflict Resolver alphaparkinc/genpark-git-semantic-cherry-pick-conflict-resolver-skill Three-way AST hunk alignment and non-overlapping block conflict resolution for Git cherry-picks | |
| GenPark Graph Cycle Deadlock Detector alphaparkinc/genpark-graph-cycle-deadlock-detector-skill Tarjan strongly connected components cycle and deadlock detector for multi-agent DAG workflows | |
| GenPark HyperLogLog Cardinality Estimator alphaparkinc/genpark-hyperloglog-cardinality-estimator-skill Pure Python 64-register HyperLogLog cardinality estimator for high-speed streaming distinct query es | |
| GenPark Jinja-Like Prompt Template Renderer alphaparkinc/genpark-jinja-like-prompt-template-renderer-skill Safe zero-dependency Jinja-like prompt template parser and renderer supporting for-loops, if-conditi | |
| GenPark JSON Pointer Patch Delta alphaparkinc/genpark-json-pointer-patch-delta-skill RFC 6901 / RFC 6902 compliant JSON Pointer and JSON Patch delta computation engine | |
| GenPark JSON-RPC Batch Pipelining Dispatcher alphaparkinc/genpark-json-rpc-batch-pipelining-dispatcher-skill High-throughput JSON-RPC 2.0 batch pipelining and inter-tool parameter dependency resolver for Model | |
| GenPark JSON Schema Contract Validator alphaparkinc/genpark-json-schema-contract-validator-skill Zero-dependency JSON schema subset validator ensuring LLM structured outputs strictly conform to con |
20,201–20,250 of 50,909
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.