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 |
|---|---|
| HL7 v2.5.1 Reference MCP Server coffeemilktea/hl7-v2-mcp-server Enables LLMs to retrieve segment, field, message-structure, and code-table details; parse pipe-delimited messages; and validate messages with deep profiles for ORM^O01, ADT^A08/A31/A40, and ORU^R01. | |
| altium-mcp coffeenmusic/altium-mcp Use Claude to control or ask questions about your Altium project. | |
| Wrike MCP Server cofficient-dev/wrike-mcp Enables users to connect their own Wrike accounts and manage spaces, folders, tasks, comments, timelogs, and attachments through natural language MCP tools, with secure per-user authentication and data isolation. | |
| litestar-mcp cofin/litestar-mcp A Litestar plugin that automatically exposes marked routes as MCP tools and resources over Streamable HTTP. | |
| bugzilla-mcp cog-gtm/bugzilla-mcp MCP server for managing Bugzilla tickets and projects, with a built-in cron job for scheduled polling. | |
| cog-brain cog-sh/cog-brain Turns a plain-Markdown Obsidian vault into a second brain that any MCP-speaking coding agent can search, read, extend, and maintain, using swappable SQLite, Qdrant, or markdown memory backends with automatic re-indexing and wiki-link graph | |
| RoofScope MCP Server cogear/roofscope-mcp Enables MCP clients to find reports by address or name, read roof/gutter/siding measurements and file links, check account prices and delivery options, and—when explicitly enabled—place or upgrade report orders. | |
| AssemblyAI MCP Server cogell/assembly-ai-mcp Enables AI assistants to transcribe audio files from URLs or local paths using AssemblyAI's services, with support for speaker diarization, language detection, and asynchronous job management through a standardized MCP interface. | |
| Mural MCP Server cogell/mural-mcp Enables AI assistants to interact with Mural visual collaboration workspaces through OAuth 2.0 authentication, allowing users to list and retrieve workspace information. | |
| Proton MCP Server cogghaus/proton-mcp-server Enables full Proton Mail management through the Model Context Protocol by connecting to a local Proton Mail Bridge instance. It allows users to list, search, read, send, and organize emails using natural language commands. | |
| vastai-host-mcp cogni-ai-ou/vastai-host-mcp Enables Vast.ai providers to manage hosted machines, update pricing, run self-tests, and automate host operations through natural language. | |
| Postman MCP Server cogni-dao/luma-mcp An MCP server that exposes Postman API requests as tools, enabling natural language interaction with APIs via MCP-compatible clients. | |
| @cogniahq/mcp cogniahq/cognia-mcp Enables AI assistants to query end-to-end encrypted memories from Cognia workspace via MCP. Supports search, retrieval, and action execution against connected services like Slack, Notion, and GitHub. | |
| A2A MCP cognicellai/a2a-mcp Bridges local MCP hosts to A2A v1-compatible agents, exposing A2A client operations as MCP tools. | |
| Adversa cognis-digital/adversa LLM red-team harness that scans for OWASP LLM Top 10 and MITRE ATLAS vulnerabilities, providing prioritized findings in table, JSON, SARIF, or via an MCP server for AI agents. | |
| aegis cognis-digital/aegis MCP server for auditing AI agent permissions and access by scanning for the trifecta of credentials, injection, and reach without heavy infrastructure. | |
| agentpassport cognis-digital/agentpassport Cryptographically verifiable, scope-narrowing delegation chains for AI agents, enabling human-anchored authorization across multiple hops. | |
| aicard cognis-digital/aicard Enables AI agents to auto-generate NIST AI RMF and EU AI Act Annex IV compliant model and system cards via MCP. | |
| biascope cognis-digital/biascope MCP server for scanning AI systems and code for demographic, occupational, and geographic biases. Enables CI integration and AI agent-driven bias detection. | |
| codegraph-mcp cognis-digital/codegraph-mcp A no-train, on-prem code knowledge graph served over the Model Context Protocol, enabling AI agents to query code structure (symbols, calls, cross-language edges) with a tamper-evident audit log. | |
| creatorforge cognis-digital/creatorforge MCP server for AI content generation, enabling agents to learn a voice, generate content ideas, write scripts, and produce multi-platform content deterministically. | |
| Guardpost MCP Server cognis-digital/guardpost Runtime agent firewall for PII redaction, rate limits, and policy enforcement, enabling autonomous agent security via MCP integration. | |
| hallumark cognis-digital/hallumark MCP-native auditor for LLM hallucination and grounding issues in RAG systems. Provides prioritized findings in table, JSON, or SARIF format for CI gating and AI agent integration. | |
| leadforge cognis-digital/leadforge Enables lightweight CRM pipeline management with email sequences, project scanning, and MCP-based interaction for AI agents. | |
| ledgermind cognis-digital/ledgermind Local LLM cost & token forensics proxy with anomaly detection, enabling security teams to scan for cost anomalies and abuse patterns, and expose results via MCP for autonomous agents. | |
| locateanything cognis-digital/locateanything A local GeoGuessr-for-real-life: reads EXIF GPS and reasons over visual clues using a local uncensored vision-language model + a reasoning model — no cloud, no API keys, nothing uploaded. | |
| mcpharden cognis-digital/mcpharden Scans MCP servers for security hardening issues including capability declarations, transport, and tool descriptions. | |
| memorybank cognis-digital/memorybank Portable long-term memory store for agents, exposed over MCP. | |
| modelroute cognis-digital/modelroute Enables AI agents to scan code for TODO, FIXME, XXX issues via MCP, providing prioritized findings in table, JSON, or SARIF format. | |
| promptpack cognis-digital/promptpack Enables AI agents to scan codebases for prioritized findings (TODO, FIXME, XXX) and retrieve results in table, JSON, or SARIF format via MCP. | |
| ragkit cognis-digital/ragkit A self-hostable, MCP-native RAG pipeline that ingests, indexes, and serves data, enabling AI agents to scan codebases for prioritized findings and integrate with CI workflows. | |
| RAGSHIELD cognis-digital/ragshield RAG corpus poisoning detector that scans for embedding anomalies and backdoor triggers, with an MCP server for AI agent integration. | |
| repolens cognis-digital/repolens Enables LLM agents to acquire token-budgeted, deterministic context packs from repositories, with hash-chained provenance for auditability. | |
| skillhub cognis-digital/skillhub Enables AI agents to scan codebases for TODO/FIXME/XXX patterns and get prioritized results over MCP, supporting CI gates and multiple output formats. | |
| Toolguard cognis-digital/toolguard Runtime allowlist and policy for agent tool-calls, enabling security scanning (e.g., TODO/FIXME/XXX findings) via MCP for AI agents. | |
| Claude Code IDE for Sublime Text cognisant-llc/sublime-claude-code Enables Sublime Text to integrate with Claude Code via the IDE protocol, providing in-editor diff review, selection context sharing, and @-mentions through a local WebSocket/MCP server. | |
| CloudLedger cognisn/cloudledger Enables natural language queries across AWS multi-account security scan history, including infrastructure configurations, public exposures, and organizational relationships. | |
| spindl-workshop cognisn/spindl-workshop Simulates a firewall MCP server that exposes deterministic device information, security rules, and traffic logs. In spindl mode, it spools large responses server-side so clients can query, aggregate, and explore distinct values without fill | |
| cv-builder cognition/cv-studio Provides MCP tools for managing a CV as structured content, including a SQLite-backed snippet library with tools to list, create, update, and match job postings, compose role-tailored CV variants, and manage drafts. | |
| Metabase MCP Server cognitionai/metabase-mcp-server Enables AI assistants to interact with Metabase's analytics platform, managing dashboards, cards, databases, and tables via the Model Context Protocol. | |
| polyflow cognitive-fab/polyflow Enables AI agents to run model-checked workflows durably, receiving one work order at a time with guarantees on admission. | |
| Ares DevOps MCP Server cognitive-stack/ares-devops-mcp An MCP server that provides seamless interaction with Azure DevOps Git repositories, enabling users to manage repositories, branches, pull requests, and pipelines through natural language. | |
| Hermes Search MCP Server cognitive-stack/hermes-search-mcp Enables AI systems to perform full-text and semantic search operations over structured/unstructured data in Azure Cognitive Search, with capabilities for document indexing and management through natural language. | |
| Orion Vision MCP Server cognitive-stack/orion-vision-mcp Enables AI systems to analyze documents and extract form data through Azure Form Recognizer/Document Intelligence, supporting various document types including receipts, invoices, and ID documents. | |
| Search Stock News MCP Server cognitive-stack/search-stock-news-mcp Provides real-time stock news search capabilities via Tavily API, allowing MCP clients to retrieve filtered and customized stock news with various search parameters. | |
| Volume Wall Detector MCP cognitive-stack/volume-wall-detector-mcp An MCP server that analyzes stock trading volume to identify significant price levels (volume walls), supporting features like order book data fetching, trade analysis, and volume distribution tracking. | |
| Verified Repo Memory MCP cognitivemyriad/verified-repo-memory-mcp Provides repository-scoped safe memory for AI coding agents with just-in-time verification against file changes to ensure facts remain accurate. It links memories to specific code citations and automatically marks them as stale if the under | |
| ltspice-mcp cognitohazard/ltspice-mcp An MCP server that connects LLM assistants to real circuit simulation: LTspice and ngspice, plus direct editing of LTspice .asc schematics. Simulation results come back as structured numbers so the assistant can design, verify, and iterate | |
| @cognium/mcp-server cogniumhq/cognium-mcp Enables MCP clients such as Cursor, Claude Desktop, and Claude Code to run deterministic static-analysis tools for scanning projects, listing entry points and reachable sinks, tracing taint paths, explaining findings, and checking sanitizer | |
| SQL Context Pack cognivex006/sql-context-pack Enables AI agents to inspect supported databases read-only, export sanitized DDL and metadata plus bounded masked samples into organized context, and run approved procedure or function updates through a shared local service. |
39,901–39,950 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.