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 |
|---|---|
| canvas-session-mcp corcvusrambochen/canvas-session-mcp Connects Claude, Cursor, Codex and other AI assistants to Canvas LMS through a normal browser sign-in (SSO and MFA included) instead of an access token, letting them read courses, assignments, rubrics, announcements, discussions, grades, ca | |
| cordata-catalog-mcp cordata-tech/catalog-mcp Enables users to query a governed data catalog for dataset ownership, contracts, columns, classifications, LF-tag validity, and whether tag-based grants reach a dataset or its columns, without returning any data rows. | |
| Japan Area Code MCP Server cordea/japan-areacode-mcp Provides access to Japanese statistical standard area codes (標準地域コード) from official government data, enabling users to list and search area codes by prefecture or municipality name. | |
| barcoding-mcp cordfuse/barcoding-mcp Enables encoding 100+ barcode symbologies and decoding common 1D/2D formats, plus terminal QR codes. | |
| sftp-mcp cordfuse/sftp-mcp Provides a browsable, mutable SFTP filesystem for AI agents, supporting file operations like listing, uploading, downloading, moving, and deleting. | |
| Claude Telemetry MCP cordlesssteve/claude-telemetry-mcp Provides comprehensive telemetry and usage analytics for Claude Code sessions, including token usage tracking, cost monitoring, and tool usage patterns. Enables users to monitor their Claude usage with detailed metrics, warnings, and trend | |
| Conversation Search MCP Server cordlesssteve/conversation-search-mcp Enables comprehensive search and analysis of Claude Code conversation history using full-text search, optional semantic vector search, and conversation management tools. Provides fast SQLite-based indexing with role-based filtering, project | |
| Document Organizer MCP Server cordlesssteve/file-converter-mcp Enables systematic document organization with PDF-to-Markdown conversion, intelligent categorization, and automated workflow management. Supports project documentation standards and provides complete end-to-end document processing pipelines | |
| Token Analyzer MCP cordlesssteve/token-analyzer-mcp Provides intelligent analysis of token usage patterns and optimization recommendations to improve efficiency and reduce costs in Claude Code sessions. Offers real-time analysis, cost metrics, and actionable insights for better context windo | |
| Webby MCP Server cordlesssteve/webby-mcp Provides comprehensive website validation across performance, accessibility, SEO, and security dimensions using multiple testing services including WebPageTest, Google PageSpeed Insights, Axe DevTools, Mozilla Observatory, and SSL Labs. Ena | |
| Cordum_io cordum-io/cordum The Control Plane for Autonomous AI
Enforce policy before execution, require human approvals where risk demands it, and keep a full audit trail — from first action to final result. | |
| Ravex-mcp-server core-edge-legacy/ravex-mcp-server Exposes the Ravex Partner API to MCP-compatible AI agents, with secure bearer-token authentication, idempotent write operations, and webhook-based reconciliation for async processing. | |
| knowledge core-euler/rag-mcp Enables MCP-capable clients to search a folder of Markdown notes with hybrid full-text and embedding retrieval, plus read, write, append, and reindex operations that keep a single shared SQLite index in sync with the files. | |
| Cheap Research core-fidelity/cheap-research A bounded evidence review engine that ingests documents, extracts evidence for a given claim, detects contradictions, and produces auditable evidence packets without hallucinations or open-web research. | |
| biocontext core-lab-research/biocontext Enables AI agents to resolve and cross-reference biological entities such as genes, proteins, and aliases across authoritative databases like HGNC, NCBI Entrez, and UniProt, with confidence scores and source citations. | |
| Marlo MCP core-marlo/marlo-mcp Enables interaction with Marlo's maritime finance and operations platform, providing access to vessel management, voyage tracking, financial data, banking transactions, loans, compliance reporting, and operational analytics for shipping bus | |
| 5g-ddos-mcp core-ncsrd/5g-ddos-mcp Model Context Protocol server for real-time 5G DDoS detection and response. | |
| Context Continuation MCP Server core3-coder/context-continue-mcp Provides intelligent context management for AI development sessions, allowing users to track token usage, manage conversation context, and seamlessly restore context when reaching token limits. | |
| coreason_mcp_registry coreason-ai/coreason-mcp-registry Enables discovering and managing MCP servers through a registry, supporting listing, searching, and configuration. | |
| coreason_multi_agent_debate coreason-ai/coreason-multi-agent-debate Dynamic multi-agent debate MCP server for structured argumentation and reasoning among AI agents. | |
| mcp-soundfx coreepoch/mcp-soundfx An MCP server that runs Stability AI's Stable Audio Open 1.0 locally on NVIDIA GPUs, enabling AI agents to generate broadcast-quality 44.1 kHz stereo WAV sound effects from text prompts fully offline with no API costs. | |
| claude-collaborator coreeye/claude-collaborator-learning-mcp Enables multi-AI collaboration with Claude and GLM for C# codebases, providing auto-learning, persistent memory, and creative brainstorming to assist development. | |
| Coreflux MQTT MCP Server corefluxcommunity/coreflux-cursor-plugin Enables agents to drive a Coreflux broker end to end over MQTT: running broker commands, publishing and subscribing to live topics, linting and deploying LoT/.lotnb files in order, uploading and exporting projects, tracing actions, and sear | |
| Coreflux MCP Server corefluxcommunity/coreflux-mqtt-mcp-server Connects Claude and other MCP-compatible AI assistants to a Coreflux MQTT broker, enabling them to discover and execute Coreflux commands for managing models, actions, rules, and routes through natural language. | |
| mcp-auth-template coreframelabs/mcp-auth-template A secure remote MCP server template implementing OAuth 2.1, client ID metadata documents, and constant-time credential verification for safe AI tool interactions. | |
| Antigravity GLM MCP coreline-ai/antigravity_glm_mcp A bridge between Gemini and GLM-4.5 models that provides 25 tools for automating complex coding tasks, file management, and system operations. It features a security-hardened architecture with sandboxing, persistent memory, and automatic fi | |
| Alexandria corentingi/alexandria Enables AI agents to search, read, ingest, annotate, and manage a self-hosted knowledge base of archived links, Git repositories, documents, and notes over MCP. | |
| shouldideploytoday-mcp corentinleberre/shouldideploytoday-mcp MCP server that checks if today is a good day to deploy using the shouldideploy.today API, with timezone support. | |
| Loupe MCP coreprocess/loupe-mcp Enables AI agents to turn PDFs, scans, photos, Office files, and HTML into readable text through signed-URL uploads and batch jobs, using fast page-level OCR or accurate vision-reconciled transcription. Jobs run independently, support page- | |
| Periscope MCP coreprocess/periscope-mcp Gives AI agents strictly read-only query access to PostgreSQL, Oracle, Cosmos DB, Blob Storage, Log Analytics, and Redis, returning each query as a paged or downloadable result set in Parquet or NDJSON rather than inline rows. | |
| Coreshub MCP Server coreshub/mcp-server-coreshub Enables interaction with the CoreHub cloud platform to manage containers, EPFS filesystems, distributed training, and inference services through MCP tools. | |
| fluency-discord-mcp coretez/discord-mcp-server Enables MCP clients to read, post to, and moderate a Discord server through the Discord REST API, with opt-in guardrails and dry-run safeguards. | |
| CalDAV MCP Server coretracker/caldav-mcp-boilerplate Enables managing calendars, events, contacts, and todos via a CalDAV server (Radicale) through MCP tools. | |
| CoreViz MCP coreviz/cli Exposes a visual library with semantic search, tagging, editing, and management of photos as tools for AI agents like Claude Code. | |
| datamining-skill coreworkstr-art/datamining-skill Enables AI assistants to inspect and extract data from local CSV, TSV, JSONL and log files far larger than available RAM, using bounded memory, crash-resilient resumable runs, and streamed progress. All file access is confined to user-appro | |
| advanced-gmail-mcp coreyepstein/advanced-gmail-mcp A Gmail MCP server for Claude Code that enables full email management across multiple Gmail accounts, including tools for listing, searching, reading, sending, and organizing emails with OAuth2 authentication. | |
| Slack MCP Server coreyepstein/advanced-slack-mcp A Slack MCP server for Claude Code that provides full messaging, channels, search, and threads across multiple Slack workspaces. | |
| John Deere Operations Center MCP Server coreyfransen08/john-deere-ops-mcp Enables interaction with the John Deere Operations Center to browse organizations, field details, and agricultural operation data. It utilizes a Cloudflare Workers architecture with an integrated OAuth proxy for secure access via any MCP-co | |
| Vivado MCP Server coreyhahn/vivado_mcp A Model Context Protocol (MCP) server that enables AI assistants like Claude to directly interact with AMD/Xilinx Vivado FPGA development tools. | |
| ops-toolbox coreyhiggins/mcp-server-example A dependency-free MCP server providing tools for tailing logs, checking endpoint health, and searching/updating a runbook of past fixes. | |
| FinDataMCP coreyjwang/findatamcp An MCP server that enables Claude Desktop to access and analyze financial data through Yahoo Finance integration. | |
| OpenChronicle coreyleung-art/openchronicle Local-first memory MCP server that captures macOS screen and app context into persistent Markdown, enabling any tool-capable LLM agent to query its working history. | |
| MCP Sequence Simulation Server coreymhudson/mcp-sequence-simulation Enables the generation, mutation, and evolution of DNA and protein sequences using various evolutionary models and phylogenetic algorithms. It supports realistic next-generation sequencing read simulation and population-level evolutionary t | |
| svmmon-mcp coreywessel/svmmon-mcp Generate TikTok slideshows from Claude (and any MCP client) using your Svmmon account. | |
| claude-session-export coreyx/claude-session-export Enables Claude Code sessions to list projects and sessions and export session transcripts to readable text files, including its own or another project's history. | |
| Milesight Gateway MCP Server corgan2222/milesight-mcp Enables managing applications, devices, profiles, multicast groups, and downlinks on a Milesight UG-series LoRaWAN gateway through natural language. | |
| tickward MCP corgicorner/tickward-mcp OAuth MCP server providing thin edge adapter access to the tickward public API via REST endpoints. | |
| pybme-mcp corinne-wf-home/pybme-mcp Enables LLM agents to perform Bayesian Maximum Entropy geostatistical analysis through natural language rather than code, supporting spatial, network, and physics-informed uncertainty modeling. | |
| Weather MCP Server corinnnnnn/weather-mcp-server Real-time weather query MCP server for Chinese cities and global cities using wttr.in API. | |
| nativegate coriqo/nativegate nativegate is a code generator that produces MCP servers from legacy native codebases: point it at a Fortran deck or C++ header and it generates pybind11/f2py bindings, a Python package, a FastAPI service that exposes the native routines as |
40,401–40,450 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.