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 |
|---|---|
| Pingfusi donghyukh23/pingfusi Enables AI coding agents to file tasks with real human reviewers who open published artifacts, leave pinned comments, and return approval verdicts so agents can iterate until accepted. | |
| FHIR MCP Server donghyukleclerc85/fhir-mcp-server Enables LLM-based agents and MCP-compatible clients to query and manipulate clinical data through natural-language prompts, including CRUD operations on medical resources, document ingestion, semantic search, and LOINC terminology lookup vi | |
| Frappe MCP donghyukleclerc85/mcp Enables Frappe Framework apps to act as Streamable HTTP MCP servers, exposing developer-registered tools to LLM clients. It provides decorators and request handling for registering tools and serving a single MCP endpoint. | |
| SandBase MCP Bridge donghyukmurphy26077/cli It enables AI clients to discover, inspect, and run over 2,000 AI models and APIs—including free data APIs and paid LLM, image, video, and audio models—through a local MCP connection with OAuth and rollback. | |
| Smart Coding MCP donghyukp0200/smart-coding-mcp Enables AI assistants to search local codebases semantically by meaning, automatically indexing code and returning relevant chunks even when terminology differs. It also supports package version lookup, workspace switching, reindexing, cach | |
| BigQuery MCP server donghyukvo/mcp-server-bigquery Enables LLMs to inspect database schemas and execute SQL queries against BigQuery. | |
| wanderlog-mcp donghyukvo/wanderlog-mcp Enables MCP-compatible agents to view, create, and edit Wanderlog trip itineraries through conversation, including places, notes, hotels, transit, checklists, expenses, guides, and shareable links. | |
| Ombre Brain donghyukwu3593/ombre-brain Enables Claude to keep persistent, cross-conversation emotional memories tagged along Russell's valence/arousal dimensions and stored as Obsidian-compatible Markdown buckets. Memories decay on a modified Ebbinghaus curve and automatically s | |
| Amadeus MCP Server donghyun-chae/mcp-amadeus Integrates with Amadeus Flight Offers Search API to provide flight search capabilities through natural language interfaces, enabling users to search for flight options between two locations with specific dates. | |
| MG6 MCP Server dongjoon-shin/mg6-mcp-server Next.js MCP server with Streamable HTTP, deployable to Vercel, providing tools for greeting, calculation, geocoding, weather, and image generation via HuggingFace tokens. | |
| KISPilot dongju923/kispilot Enables AI agents to query and trade Korean stocks through the Korea Investment & Securities Open API, covering quotes, investor flows, financials, rankings, indices, ETFs, account balances, charts and technical indicators, plus custom-stra | |
| dependency-compat-mcp dongju93/dependency-compat-mcp MCP server that evaluates compatibility between exact versions of packages and runtimes using official evidence, returning structured verdicts (supported/unsupported/unknown) with sources and limitations. | |
| ai-mail-mcp dongjunke/ai-mail-mcp A mail service that connects private domain email to MCP clients, enabling sending (with auto signature), receiving, and reading emails through natural language via stdio or SSE transport. | |
| krx-etf-mcp dongkyucho17/krx-etf-mcp An MCP server that lets AI assistants search, compare, and rank Korean ETFs by name, issuer, index, or category, with price return calculations and NAV premium analysis. | |
| SerialHub dongly/serialhub Enables AI agents to interact with serial devices via MCP tools, providing serial port discovery, connection, read/write, and status management, while sharing the same serial connection with a browser-based terminal. | |
| mcp-toolkit dongnb66/mcp-toolkit Enables any Model Context Protocol-compatible host (Claude Desktop, Cherry Studio, Cline, MCP Inspector) to call 8 plug-and-play tools over stdio: hotspot ranking, TC3 signing, text chunking, date calculation, read-only SQLite queries, webp | |
| Matter Web Controller dongnh/matter_webcontrol Enables control of Matter smart-home devices via REST and MCP APIs, supporting lights, sensors, and AC units with federation capabilities. | |
| Paymenter MCP Server dongocanh0501/paymenter-mcp Enables AI agents to autonomously govern cloud hosting infrastructure and billing workflows, including provisioning, invoices, wallet credits, support tickets, and catalog management through 35 tools with JSON:API response hydration. | |
| atlassian-mcp-server dongood/atlassian-mcp-server Enables AI agents to manage Jira issues and Confluence pages via natural language, including creating, updating, searching, and uploading file attachments using API token authentication. | |
| Tools MCP Server dongood/tools-mcp-server An MCP server that provides utility tools for markdown processing, including ADF-to-markdown conversion, table formatting, and table of contents management. | |
| MCP Docent Server dongprojectteam/mcp-docent-server An AI-powered server that analyzes uploaded images and automatically generates explanatory text (docent) for various images. | |
| LGTM MCP Server dongri/mcp-server-lgtm Enables fetching random LGTM (Looks Good To Me) images from the LGTM API for use in code reviews and developer communications. | |
| dsh-artifact-promotion-proof dongsheng123132/dsh-artifact-promotion-proof Enables offline, deterministic verification that one immutable artifact followed a declared build-to-production promotion chain, using only hash-based evidence and failing closed on incomplete or nonconformant gate records. | |
| dsh-audit-bundle dongsheng123132/dsh-audit-bundle MCP server for auditing DeepSeek Harness evidence. Enables inspection and verification of content-addressed audit manifests with fail-closed validation. | |
| dsh-build-hermeticity-proof dongsheng123132/dsh-build-hermeticity-proof Enables verifying that recorded build accesses stay within a declared closure by inspecting and verifying hash-only receipts, without executing builds or making network requests. | |
| dsh-credential-retirement-proof dongsheng123132/dsh-credential-retirement-proof Enables offline, deterministic verification of credential retirement settlements from explicit receipts, proving that rotations activated new credentials, rejected old ones, and closed without exposing secrets. | |
| dsh-duty-separation-proof dongsheng123132/dsh-duty-separation-proof Enables offline verification that a supplied DSH workflow adhered to declared duty-separation constraints, producing a redacted, content-addressed JSON verdict. | |
| dsh-license-obligation-proof dongsheng123132/dsh-license-obligation-proof Enables deterministic verification that all required license compliance artifacts have been delivered for a release decision, using hashes and obligation codes without exposing license bodies or scanning packages. | |
| dsh-loader-settlement-proof dongsheng123132/dsh-loader-settlement-proof Enables verification of content-addressed settlement receipts for DSH Loader activation, injection closure, and tool schema settlement. | |
| dsh-narrative-ledger dongsheng123132/dsh-narrative-ledger MCP server for verifying narrative consistency and querying story-state facts in DeepSeek Harness, exposing read-only ledger tools for canonical evidence and continuity checks. | |
| dsh-schema-migration-proof dongsheng123132/dsh-schema-migration-proof Lets users inspect and verify content-addressed schema migration evidence offline, checking idempotence, reversible rollback, required invariants, and explicit lossy-field disclosure without executing migrations or accessing data. | |
| dsh-tool-surface-proof dongsheng123132/dsh-tool-surface-proof Enables verification of deployment-scoped model-visible DSH tool surface conformance by checking recorded tool identities and schemas against approved locks, reporting only drift categories and hashes. | |
| dsh-vulnerability-remediation-proof dongsheng123132/dsh-vulnerability-remediation-proof Offers proof-only tools to inspect and verify remediation closure receipts, deterministically confirming asset coverage, fixed artifact deployment, rescanning, deadline compliance, and zero-residual closure without executing scans or touchi | |
| MoneySwitch MCP Server dongsheng123132/moneyswitch Enables AI agents to make payments over x402-priced HTTP APIs using USDC on Monad testnet, with policy enforcement, budgets, and approval workflows, without exposing private keys. | |
| task-passport dongsheng123132/task-passport Provides a task passport system for handoff across AI harnesses, enabling users to list, open, create, and checkpoint tasks with stable IDs and verified state. | |
| Mnemic dongtang3/mnemic Local-first memory kernel for coding agents that provides a shared, auditable, graph-backed long-term memory layer with features like write preview, temporal recall, and provenance explanations. | |
| Autotest AI MCP Server dongtrieuit/autotest-ai-mcp Enables AI agents to manage Autotest AI projects, screens, test cases, and test runs through natural language commands. | |
| building-register-mcp dongwook-chan/building-register-mcp Queries South Korean building register data (e.g., floor area, parking, seismic design) via a single unified tool, converting API responses to Korean field names for easy AI understanding. | |
| rtms-mcp dongwook-chan/rtms-mcp Queries Korean apartment sale transaction data (RTMS) by region code and contract date. Optimized for token efficiency with compressed JSON and Korean field names. | |
| slurm-mcp dongwookim-ml/slurm-mcp An MCP server that gives AI coding assistants direct access to Slurm HPC clusters for job submission, file management, and shell access. | |
| Outlook MCP dongwoosuk/aec-outlook-mcp Enables semantic search and AI-powered analysis of Outlook emails using RAG-based natural language queries and Vision AI for architectural documents, with specialized support for AEC workflows. | |
| Grasshopper MCP dongwoosuk/rhino-grasshopper-mcp Enables AI-powered computational design in Rhino/Grasshopper with ML-based automatic layout optimization, component clustering, performance prediction, and real-time code execution in running Rhino instances. | |
| zemax-mcp dongzhaohe321418-lab/zemax-mcp Safety-first MCP server enabling AI assistants to drive Zemax OpticStudio sequential-mode optical design workflows, including a mock backend for validation. | |
| SolidWorks MCP Server dongzijie1/solidworks-mcp Connects Claude Code to SolidWorks via MCP protocol, enabling natural language control for creating 3D models. | |
| kscc-mcp-server donhz666/kscc-mcp Wraps the kscc CLI as a stdio MCP server, enabling MCP clients to delegate coding tasks via headless prompt execution and session continuation. | |
| memory-mcp donk338/memory-mcp Persistent long-term memory for MCP clients. Store and recall semantic facts, episodic events, and task state with vector-based relevance search. Write what matters, retrieve what's needed — memory that persists across sessions and agents, | |
| MCPBridge donkronk17/mcpbridge Enables BCH agents to be exposed via MCP/A2A protocols for discovery and task delegation, and allows delegation to external A2A agents. | |
| fast-browser-mcp donleqt/fast-browser-mcp Adds persistent QA state to browser automation, enabling AI agents to maintain session-scoped artifacts and generate reports across multiple steps. | |
| mcp-context-window donliggett/mcp-context-sliding Provides an external context buffer so a local model can maintain session memory across long tasks and search and page through large documents without loading them whole into its limited context window. | |
| mcp-filesystem donliggett/mcp-file-system Provides a hardened filesystem interface that lets a local model read and write files only within user-specified directories, with symlink protection and atomic operations. |
45,501–45,550 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.