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 |
|---|---|
| GenPark JWT Token Verifier & Claims Auditor alphaparkinc/genpark-jwt-token-verifier-and-claims-auditor-skill Pure-Python zero-dependency JWT claims auditor and payload inspector enforcing expiry, audience, and | |
| GenPark Levenshtein Fuzzy Tool Matcher alphaparkinc/genpark-levenshtein-fuzzy-tool-matcher-skill Fast Levenshtein distance and fuzzy similarity matcher autocorrecting hallucinated LLM tool calls | |
| GenPark LLM Token Bucket & Sliding Window Rate Limiter alphaparkinc/genpark-llm-token-bucket-sliding-window-rate-limiter-skill Adaptive multi-tier TPM/RPM rate limiter with smooth leaky bucket queuing and burst wait estimation | |
| GenPark LLM Token Cost Budget Tracker alphaparkinc/genpark-llm-token-cost-budget-tracker-skill Multi-model LLM token cost budget ledger and burn rate forecaster enforcing spending limits and earl | |
| GenPark LRU TTL Multi-Tier Cache alphaparkinc/genpark-lru-ttl-multi-tier-cache-skill In-memory LRU cache with per-key TTL expiration, deterministic eviction, and hit/miss/stale telemetr | |
| GenPark Markdown Mermaid Syntax Lint Healer alphaparkinc/genpark-markdown-mermaid-syntax-lint-healer-skill LLM output Mermaid diagram linting, unquoted bracket healing, and syntax normalization engine | |
| GenPark Markdown Table AST Normalizer alphaparkinc/genpark-markdown-table-ast-normalizer-skill AST-based Markdown table normalizer rebalancing columns, padding, and exporting clean RFC 4180 CSV a | |
| GenPark Merkle DAG State Verifier alphaparkinc/genpark-merkle-dag-state-verifier-skill Cryptographic Merkle tree verification engine for agent state transitions, tool call histories, and | |
| GenPark Multi-Agent Borda Voting Consensus alphaparkinc/genpark-multi-agent-borda-voting-consensus-skill Positional Borda Count voting and weighted multi-agent consensus engine resolving conflicting model | |
| GenPark Multi-Source OpenAPI Router Mesh alphaparkinc/genpark-multi-source-openapi-router-mesh-skill Aggregates multiple OpenAPI specifications into a unified virtual routing mesh with service namespac | |
| GenPark OpenAPI Spec to MCP Tool Synthesizer alphaparkinc/genpark-openapi-spec-to-mcp-tool-synthesizer-skill Inspect OpenAPI 3.0 specs and synthesize schema-compliant Model Context Protocol tool declarations w | |
| GenPark PII Redactor & Data Masker alphaparkinc/genpark-pii-redactor-and-data-masker-skill Regex and Luhn heuristic PII redaction and tokenization engine sanitizing sensitive emails, phones, | |
| GenPark Priority Event Scheduler Queue alphaparkinc/genpark-priority-event-scheduler-queue-skill Min-heap priority event scheduler and delayed task dispatcher for asynchronous multi-agent coordinat | |
| GenPark Prompt Drift Semantic Fingerprint alphaparkinc/genpark-prompt-drift-semantic-fingerprint-skill Prompt template drift and structural fingerprint sentinel detecting unauthorized prompt mutations an | |
| GenPark Prompt Injection Canary Leak Sentinel alphaparkinc/genpark-prompt-injection-canary-leak-sentinel-skill HMAC-signed zero-width invisible canary token generator and output response leak auditor | |
| GenPark RAG Semantic Boundary Chunker alphaparkinc/genpark-rag-semantic-boundary-chunker-skill Semantic boundary preserving text chunker maintaining markdown headers, code fences, and paragraphs | |
| GenPark Recursive JSON Schema Healer alphaparkinc/genpark-recursive-json-schema-healer-skill Recursive JSON schema validator and autonomous healer repairing type mismatches, missing defaults, a | |
| GenPark Red-Black Tree Index alphaparkinc/genpark-red-black-tree-index-skill Self-balancing Red-Black binary search tree engine for ordered indexing, range queries, and log-time | |
| GenPark Redact Unredact Session Vault alphaparkinc/genpark-redact-unredact-session-vault-skill Bidirectional in-memory sensitive vault and surrogate token masker protecting credentials in LLM pro | |
| GenPark Reservoir Sampling Stream Auditor alphaparkinc/genpark-reservoir-sampling-stream-auditor-skill O(k) space unbiased stream reservoir sampling and quantile estimation engine for LLM telemetry and h | |
| GenPark Safe Eval Expression AST Sandbox alphaparkinc/genpark-safe-eval-expression-ast-sandbox-skill Zero-dependency AST safe mathematical and boolean expression evaluator and validator | |
| GenPark Secure Secret Token Redactor alphaparkinc/genpark-secure-secret-token-redactor-skill High-speed regex and entropy-based scanner redacting API keys, JWT tokens, and credentials | |
| GenPark SemVer Dependency Resolver Agent alphaparkinc/genpark-semver-dependency-resolver-agent-skill Semantic Versioning 2.0.0 range matcher and dependency tree resolver for multi-agent toolkits and pl | |
| GenPark Sliding Log Rate Limiter alphaparkinc/genpark-sliding-log-rate-limiter-skill Microsecond-precision sliding window log rate limiter preventing boundary burst exploitation | |
| GenPark Sliding Window Rate Anomaly Detector alphaparkinc/genpark-sliding-window-rate-anomaly-detector-skill Real-time streaming sliding-window anomaly and burst detector using z-score and EWMA for spikes | |
| GenPark SQL Injection AST Taint Analyzer alphaparkinc/genpark-sql-injection-ast-taint-analyzer-skill Dynamic SQL AST taint tracking and static vulnerability auditor detecting tautology injections | |
| GenPark Streaming NDJSON & JSONL Schema Validator alphaparkinc/genpark-streaming-ndjson-jsonl-schema-validator-skill Ultra-low-latency incremental line validator with chunk boundary reassembly and schema auditing | |
| GenPark Structured Data Mask Reconstruction Guard alphaparkinc/genpark-structured-data-mask-reconstruction-guard-skill Deterministic reversible tabular and JSON record anonymizer and de-identification guard with HMAC | |
| GenPark Token Bucket Traffic Shaper alphaparkinc/genpark-token-bucket-traffic-shaper-skill Token bucket traffic shaper with smooth replenishment and burst capacity for LLM tool call throttlin | |
| GenPark Tool Call Latency Profiler Metrics alphaparkinc/genpark-tool-call-latency-profiler-metrics-skill High-resolution MCP tool call latency profiler and P50/P90/P95/P99 telemetry metrics collector | |
| GenPark Tri-State Circuit Breaker Router alphaparkinc/genpark-tri-state-circuit-breaker-router-skill Tri-state circuit breaker router managing LLM provider failure cascades, sliding error windows, and | |
| GenPark Trie Prefix Keyword Matcher alphaparkinc/genpark-trie-prefix-keyword-matcher-skill High-performance in-memory Trie and multi-keyword search engine for prompt routing and entity extrac | |
| GenPark Two-Phase Commit Coordinator alphaparkinc/genpark-two-phase-commit-coordinator-skill Distributed Two-Phase Commit (2PC) transaction coordinator for atomic multi-agent state mutations wi | |
| GenPark Vector Embedding Cache Deduplication Sentinel alphaparkinc/genpark-vector-embedding-cache-deduplication-sentinel-skill High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation | |
| GenPark Weighted Round Robin Balancer alphaparkinc/genpark-weighted-round-robin-balancer-skill Nginx-style smooth weighted round-robin load balancer with dynamic weight adjustment for multi-LLM r | |
| CONTRI alphasafal/contri Is this GitHub issue free to take, is the project alive, will maintainers reply? Read-only. | |
| FactStamp alpineaisih/factstamp Verify a company, figure or citation before you rely on it. Card or crypto; signed receipt. | |
| Chalet-Montagne.com alpium/chalet-montagne-mcp Search French mountain holiday rentals and contact owners directly — commission-free. | |
| EvolutionDB Long-Term Memory alptekin/evolutiondb Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB. | |
| Konstruct alright-alright/konstruct Knowledge graph for AI agents. Query concepts, walk edges, get advisories. | |
| Persis alright-alright/persis Biological memory for AI agents. Pattern learning, decay, clustering, 8-drive behavior. | |
| Alshhbaa Copperware — نحاسيات الشهباء alshhbaa/alshhbaa-agent-kit Luxury chandeliers and lighting catalog MCP server for shop.alshhbaa.com | |
| Alter Onboarding alteraidev/alter-vault Guide developers from setup through a verified, policy-aware, audited Alter API call. | |
| Altss Public Profiles altssdata/public-client Search and read bounded published Altss profile summaries with canonical citations. No private data. | |
| io.github.altyaper/changologs-mcp altyaper/changologs-mcp Create, search, and list Changologs logs and tasks | |
| Clair alumeet/clair Sell-side agent for retail: one typed waitlist transaction plus read-only machine manifests. | |
| mail-index alunsoldantarctica/mail-index Local-first, read-only MCP server for recall over your Gmail: search, contacts, threads, digests. | |
| io.github.AlvaroRamirezCastillo/greeting-mcp-server alvaroramirezcastillo/greeting-mcp-server An MCP server greeting | |
| QY Evolution Engine alvinxiao2/qianyuan-protocol 13 tools for agents: pitfalls, results, tasks, capability. Anonymous reads; writes need signing. | |
| Reverse Engine Anything Plus alyhnte/reaplus Conduit live-debug core (30 frozen tools) + Rea static RE domains over MCP stdio/HTTP. |
20,251–20,300 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.