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 |
|---|---|
| genpark-yield-curve-nelson-siegel-interpolator-skill alpha-park/genpark-yield-curve-nelson-siegel-interpolator-skill Enables users to model and interpolate zero-coupon yield curves using Nelson-Siegel parameters, fitting level, slope, curvature, and decay components from spot-rate data. It supports quantitative finance workflows through a standard MCP int | |
| genpark-zero-query-inspiration-graph-matcher-skill alpha-park/genpark-zero-query-inspiration-graph-matcher-skill Enables agents to turn ambient visual wallpapers and lifestyle scenes into personalized retail product recommendations and one-tap shopping actions via MCP. | |
| OpenClaw GenPark Agent Forge alpha-park/openclaw-genpark-agent-forge Enables MCP-compatible clients such as Claude Desktop, Cursor, and Antigravity to invoke deterministic mathematical modeling and System 2 agent capabilities through a native STDIO JSON-RPC 2.0 server with zero external dependencies. | |
| OpenClaw GenPark Sentinel alpha-park/openclaw-genpark-sentinel Enables real-time sliding-window token velocity anomaly detection and adaptive rate-limiting through a native STDIO MCP server built entirely on the Python standard library. Exposes deterministic algorithmic checks that report anomalies and | |
| OpenClaw GenPark Vocalist alpha-park/openclaw-genpark-vocalist Enables agents to analyze audio through a pure standard-library acoustic time-domain autocorrelation pitch tracker and vocal stability estimator, exposing deterministic JSON results as MCP tools over STDIO JSON-RPC. | |
| personal-agent-skills alpha-park/personal-agent-skills Enables circadian-aware scheduling of cognitive work, ambient flow-state detection, and utility-gated interruption decisions so proactive personal-agent interventions respect focus and urgency. | |
| AI Knowledge Base MCP Server alpha-w0lf/ai-knowledge-base-public Provides read-only hybrid RAG search and discovery over a local-first AI knowledge corpus, enabling semantic and keyword search, browse, digest, and status tools. | |
| kimai-timelog-mcp alpha101code/kimai-timelog-mcp Enables MCP-capable clients to read and write Kimai timesheets using a personal API token, supporting natural language time logging, timers, and timesheet management. | |
| Loyalteez MCP Server alpha4-labs/loyalteez-mcp Model Context Protocol (MCP) server for Loyalteez, enabling AI assistants to design loyalty programs, create events, track rewards, and access comprehensive documentation. | |
| alphaassay/mcp Most trading signals are noise. AlphaAssay puts them on trial — deflated Sharpe, out-of-sample, leakage forensics — and returns signed pass/fail verdicts anyone can verify. Methodology audits, not investment advice. | |
| journey-log alphabilal/journey-log-mcp-server This MCP server integrates with Journey Log to automatically document development journeys, enabling AI assistants to create, update, and retrieve documents, capture conversations, and manage code snippets. | |
| layercake alphacornutum/layercake A local MCP server that connects AI agents to Adobe After Effects, enabling reliable project inspection, reasoning, and controlled mutations through structured tools and typed patches. | |
| well alphadataomega/well Provides a memory organ for agents, enabling them to feed content, recall grounded passages, and ask questions with honest abstention (ABSENT) via MCP tools over stdio. | |
| handoff-mcp alphaelements/handoff-mcp Provides persistent memory for AI coding agents across sessions by saving and loading session context like tasks, decisions, and blockers. | |
| mcp-server alphaiterations/mcp-server An MCP server that provides weather and web search tools, orchestrated by a LangGraph agent with OpenAI for natural language interaction. | |
| arcadey-mcp alphajew420/arcadey-sdk MCP server for managing games on coolgptgames.com, enabling agents like Claude to publish, update, and track games via the Arcadey API. | |
| concierge-mcp alphajew420/concierge-mcp MCP server for Concierge, enabling AI agents to manage Discord customer support operations including tickets, AI, knowledge base, analytics, and more via natural language. | |
| shack-mcp alphamonkey/shack-mcp An MCP server that lets an LLM operate an amateur radio shack: query live APRS traffic, predict satellite passes, schedule SDR captures, and monitor FT8/WSPR band activity. | |
| elim-mcp alphanen/elim-mcp An MCP server that gives coding agents a persistent, chained memory of debugging investigations, tracking what's been tried, ruled out, and solved across sessions and scopes. | |
| Penpot MCP Server alphanusa/public_penpot_mcp Enables LLM clients to query, transform, and create design data in design files through a plugin connection, supporting design-to-design, code-to-design, and design-to-code workflows. | |
| kener-mcp alphaomegateam/kener-mcp Enables AI agents to read monitors and incidents and to create, update, and resolve incidents on Kener v4 status pages, with read-only tools marked safe and write operations available when permitted. | |
| flask-hello-world alphaparkinc/flask-hello-world Enables agents to call deterministic microservice operations through a native FastMCP JSON-RPC interface, including URL prefix routing, HMAC-SHA256 JWT claims authentication, and P99 latency SLA auditing. | |
| genpark-actuator-thermal-torque-throttle-sentinel-skill alphaparkinc/genpark-actuator-thermal-torque-throttle-sentinel-skill Enables real-time monitoring of robotic joint actuator thermal and torque loads, triggering preventative throttling and safety supervision for DJI/RoboMaster actuators through MCP. | |
| genpark-adaptive-token-rate-limiter-skill alphaparkinc/genpark-adaptive-token-rate-limiter-skill Enables autonomous agents to apply adaptive token bucket concurrency limits and backoff scheduling to avoid HTTP 429 errors. It provides deterministic rate-limiting permits and structured telemetry through MCP-compatible clients. | |
| Adaptive Retry Circuit Breaker Skill alphaparkinc/genpark-agent-adaptive-retry-circuit-breaker-skill Enables autonomous agents and multi-agent pipelines to protect external API calls with stateful circuit breaking, adaptive exponential backoff with jitter, and fail-fast behavior. It exposes tools to check execution permission, report succe | |
| genpark-agent-bash-command-sandbox-guard-skill alphaparkinc/genpark-agent-bash-command-sandbox-guard-skill Enables MCP-compatible agents to execute bash and subprocess commands through a zero-dependency sandbox guard that blocks destructive system mutations, path traversals, reverse shells, and other unsafe execution patterns. | |
| genpark-agent-budget-token-spend-circuit-breaker-skill alphaparkinc/genpark-agent-budget-token-spend-circuit-breaker-skill Enables autonomous agents to enforce financial guardrails by tracking real-time token burn and cost velocity, automatically throttling or freezing execution when budgets are exceeded. It also blocks destructive shell commands, prompt inject | |
| genpark-agent-checkpoint-state-persistence-restorer-skill alphaparkinc/genpark-agent-checkpoint-state-persistence-restorer-skill Enables AI agents to persist and restore checkpoint state, supporting crash recovery and replay for LangGraph-based workflows. | |
| genpark-agent-codebase-ast-dependency-slicer-skill alphaparkinc/genpark-agent-codebase-ast-dependency-slicer-skill Enables coding agents to parse multi-file AST dependency graphs and extract minimum context symbol call-trees through MCP. | |
| Conflict Resolution Merger Skill alphaparkinc/genpark-agent-conflict-resolution-merger-skill Enables multiple autonomous agents to reconcile concurrent edits to shared text, markdown, and source files using 3-way merging, with conflict detection and structured markers for automated re-arbitration. | |
| genpark-agent-context-dynamic-compressor-skill alphaparkinc/genpark-agent-context-dynamic-compressor-skill Enables AI agents and MCP-compliant clients to dynamically shrink long-horizon context windows, pruning verbose tool outputs, HTML boilerplate, and semantic redundancy by roughly 40-70% without frontier LLM round-trips. Runs deterministical | |
| Continuous Context Session Compactor alphaparkinc/genpark-agent-continuous-context-session-compactor-skill Enables long-horizon autonomous agents to avoid context-window exhaustion by enforcing configurable token budgets and distilling older conversation turns into concise sliding summaries. | |
| GenPark Agent Cryptographic Audit Trail Merkle Sealer alphaparkinc/genpark-agent-cryptographic-audit-trail-merkle-sealer-skill Enables agents to generate tamper-evident SHA-256 Merkle audit trails, produce logarithmic inclusion proofs, and verify integrity through a STDIO MCP interface. | |
| genpark-agent-deadlock-liveloss-loop-detector-skill alphaparkinc/genpark-agent-deadlock-liveloss-loop-detector-skill Enables detection of autonomous agent infinite tool loops, planning deadlocks, and liveloss cycles via trajectory state entropy analysis. Also provides safety guardrails for prompt injection, destructive commands, budget overruns, and data | |
| Deep Research Fact-Checker MCP Server alphaparkinc/genpark-agent-deep-research-fact-checker-skill Enables autonomous agents to cross-reference factual claims against multiple source documents, detect ungrounded statements, and compute normalized confidence scores. It supports multi-source corroboration and claim verification through a s | |
| Document AST Parser & Compiler Skill alphaparkinc/genpark-agent-document-ast-parser-compiler-skill Enables autonomous agents to parse markdown documents into structured AST nodes—including headings, lists, tables, callouts, and code blocks—and serialize modified AST back into clean canonical markdown via MCP tools. | |
| genpark-agent-dynamic-few-shot-example-selector-skill alphaparkinc/genpark-agent-dynamic-few-shot-example-selector-skill Enables AI agents and MCP clients to dynamically select few-shot in-context examples using semantic token overlap, cosine similarity, and MMR diversity ranking to optimize prompts deterministically without external dependencies. | |
| genpark-agent-dynamic-persona-style-adapter-skill alphaparkinc/genpark-agent-dynamic-persona-style-adapter-skill Enables AI agents to dynamically adjust their communication formality, brevity, tone, and technical depth based on channel context, the user's cognitive load, and sentiment feedback. It runs as a zero-dependency MCP server that generates co | |
| genpark-agent-execution-tree-rollback-checkpointer-skill alphaparkinc/genpark-agent-execution-tree-rollback-checkpointer-skill Enables long-running autonomous agents to snapshot environment and context states, evaluate the viability of competing reasoning branches, and roll back to an earlier checkpoint when an exploration path fails without restarting from scratch | |
| Executive Brief & KPI Dashboard Synthesizer Skill alphaparkinc/genpark-agent-executive-brief-dashboard-skill Enables autonomous agents to convert raw telemetry, system metrics, and departmental status updates into executive decision briefs, KPI watchpoint summaries, strategic signal extraction, and automated mitigation recommendations. | |
| genpark-agent-exfiltration-canary-leak-detector-skill alphaparkinc/genpark-agent-exfiltration-canary-leak-detector-skill Enables real-time injection fuzzing and canary-based exfiltration detection over untrusted prompts, RAG context, and agent actions, with entropy analysis, outbound channel interception, least-privilege sandboxing, and cryptographic audit pr | |
| genpark-agent-hallucination-fact-verifier-skill alphaparkinc/genpark-agent-hallucination-fact-verifier-skill Enables autonomous agents and MCP clients to decompose text into atomic claims and verify them against reference knowledge, detecting ungrounded claims, numerical contradictions, and hallucinated entities. | |
| genpark-agent-hierarchical-episodic-memory-skill alphaparkinc/genpark-agent-hierarchical-episodic-memory-skill Enables agents to maintain multi-tier memory across working scratchpad, dialogue buffer, and episodic stores with recency decay. Supports hybrid BM25/vector retrieval, rank fusion, graph expansion, and context reordering for optimized MCP-b | |
| genpark-agent-human-in-the-loop-approval-gate-skill alphaparkinc/genpark-agent-human-in-the-loop-approval-gate-skill Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds. | |
| genpark-agent-hybrid-memory-retriever-skill alphaparkinc/genpark-agent-hybrid-memory-retriever-skill Enables AI agents and MCP-compatible clients to perform hybrid episodic long-term memory retrieval by combining BM25 keyword search, semantic n-gram cosine similarity, and recency decay ranking over stored memories. | |
| genpark-agent-json-schema-auto-repair-skill alphaparkinc/genpark-agent-json-schema-auto-repair-skill Enables MCP-compatible agents and IDEs to deterministically extract JSON and auto-repair malformed schemas, including truncated braces, markdown wrappers, and invalid types, without LLM round-trips. | |
| genpark-agent-long-hhorizon-context-compactor-skill alphaparkinc/genpark-agent-long-horizon-context-compactor-skill Enables long-horizon conversational memory compaction and episodic anchor extraction for AI agents, providing deterministic memory management through a zero-dependency MCP server. | |
| GenParkAgentMCPToolPermissionLeastPrivilegeAuditor alphaparkinc/genpark-agent-mcp-tool-permission-least-privilege-auditor-skill Enables agents and operators to audit MCP tool permissions for least privilege, score blast radius, detect privilege-escalation chains, verify capability matrices, and produce cryptographic audit proofs with injection fuzzing and exfiltrati | |
| Meeting Minutes & Action Extractor alphaparkinc/genpark-agent-meeting-minutes-action-extractor-skill Enables autonomous agents to parse meeting transcripts into structured minutes with consensus decisions, assigned action items, owners, deadlines, and follow-up agendas via an MCP tool. | |
| Agent Mesh State Blackboard Deconfliction Engine alphaparkinc/genpark-agent-mesh-state-blackboard-deconfliction-skill Enables multi-agent systems to share and coordinate a common state space over MCP, detecting concurrent mutation race conditions, synchronizing state through vector clocks, and resolving conflicting decisions via consensus arbitration. Also |
27,251–27,300 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.