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 |
|---|---|
| sci-calc-mcp aubreyhayes47/sci_calc_mcp sci_calc_mcp is a lightweight, high-performance Model Context Protocol (MCP) server that exposes scientific calculator operations as atomic tools. | |
| gravity-relay-mcp aucf/gravity-relay-mcp Acts as a local stdio MCP service that lets Codex delegate implementation tasks to Antigravity CLI while conserving tokens; it returns compact review packets with changed files, diff stats, and run history for Codex to review and iterate. | |
| Claude Code MCP auchenberg/claude-code-mcp An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface. | |
| trundler auckland-ai-collective/trundler A local MCP server for grocery shopping, enabling product search, specials, and browsing across NZ supermarkets, with cart and order history for Countdown/Woolworths via browser-assisted login. | |
| registree aucontraire/registree Provides coding agents with a live registry of class definitions and constructor signatures from the codebase, enabling verification of calls before writing them to prevent hallucinated parameters. | |
| obsidian-wiki-mcp aud1ence/obsidian-wiki-mcp MCP server that implements Karpathy's LLM Wiki pattern for Obsidian vaults, enabling persistent knowledge storage and BM25 search across AI sessions. | |
| Tmux MCP Server audibleblink/tmux-mcp-server Enables AI assistants to manage local tmux sessions, including creating and controlling sessions, windows, and panes, sending commands, and capturing terminal output. | |
| openapi-to-mcp audiencelabv3/openapi-to-mcp Auto-generates MCP tools from your OpenAPI spec, allowing natural language interaction with any API via configurable headers and serverless deployment. | |
| audiencescore audiencescore/audiencescore Reference MCP server for the AudienceScore protocol: query a vendor's audience score (percent of verified thumbs-up over receipt-gated reviews) and get back a signed, recomputable score manifest an agent can verify without trusting the serv | |
| garmin-claude-mcp audifykse/garmin-claude-mcp Enables Claude to read recent Garmin activities and wellness data through intervals.icu, design structured workouts, and create, update, or delete planned workouts that sync to Garmin Connect and the user's watch. | |
| RedPanal MCP Server audio-research-projects/redpanal-mcp-server Enables interaction with the RedPanal audio platform to list, detail, download, and upload audio files. | |
| MCP Python Interpreter audrey756/mcp-python-interpreter Enables LLMs to interact with Python environments, execute code and scripts, manage packages, and read or write files within an isolated working directory. | |
| VSCode MCP Server audreygarnier/vscode-mcp Enables AI coding agents and MCP clients to query a running VSCode instance for real-time LSP diagnostics, symbol hover/definition/type info, reference navigation, and workspace-wide symbol renames, replacing slow tsc/eslint/build runs. Als | |
| multiCAD-mcp audreykarahan/multicad-mcp Enables AI assistants like Claude for Desktop or Cursor to drive CAD applications such as AutoCAD, ZWCAD, GstarCAD, and BricsCAD through natural-language or direct tool calls. It covers drawing shapes, managing layers and blocks, manipulati | |
| mcptube-vision audreyr77259/mcptube Enables turning YouTube videos into a persistent, structured knowledge base by extracting transcripts and scene-change visual frames, compiling wiki pages with cross-references, and answering agentic search queries over the accumulated know | |
| Niblet audreysoto36741/niblet-skill-mcp It provides real screen references and a design skill for coding agents building user interfaces. This enables agents to ground their UI construction in existing product screens and specific design standards. | |
| Ombre-Brain audreytruong6415/ombre-brain This system provides Claude with a long-term, persistent memory by tagging events using emotional valence and arousal coordinates. It enables memories to naturally decay over time and actively surface based on emotional intensity, mimicking | |
| SerpApi MCP Server audreyvandermeer/serpapi-mcp Enables AI assistants to run real-time searches across Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and many other engines, returning structured JSON or token-efficient Markdown results such as answer boxes, organic results, news, images | |
| Biochemistry Archive MCP Server audreyzw/biomcp-bench This server provides agents with access to key data across UniProt, RCSB PDB, and ChEMBL archives. It enables the completion of complex biochemical and drug discovery tasks by offering structured tool endpoints. | |
| Augent augentdevs/augent MCP server that turns any audio or video source into structured, searchable intelligence for agents, enabling download, transcription, semantic search, speaker identification, and more. | |
| hockey-card-analyst augforce/hockey-card-analyst Interprets advanced hockey player cards to translate metrics into plain-language assessments, supporting player evaluation, claim verification, and player comparisons with deterministic rules. | |
| obsbotd auggiesoft/obsbotd Enables control of OBSBOT Tiny-series cameras (gimbal, zoom, focus, AI tracking, snapshots) through MCP tools. | |
| projectlibre-mcp augmdc/projectlibre-mcp Read-only MCP server for ProjectLibre .pod files that enables finding project files, summarizing Gantt charts, inspecting tasks, and analyzing schedules without opening ProjectLibre. | |
| AlphaFold MCP Server augmented-nature/alphafold-mcp-server A comprehensive Model Context Protocol (MCP) server that provides access to the AlphaFold Protein Structure Database through a rich set of tools and resources for protein structure prediction analysis. | |
| UniProt MCP Server augmented-nature/augmented-nature-uniprot-mcp-server A comprehensive Model Context Protocol (MCP) server providing advanced access to the UniProt protein database. | |
| BioOntology MCP Server augmented-nature/bioontology-mcp-server A production-ready Model Context Protocol (MCP) server that provides comprehensive access to the BioOntology API for searching, annotating, and exploring over 1,200 biological ontologies. | |
| Unofficial BioThings.io MCP Server augmented-nature/biothings-mcp-server Provides access to BioThings.io APIs for comprehensive gene and variant annotations, enabling seamless integration of biological data into workflows. | |
| ChEMBL MCP Server augmented-nature/chembl-mcp-server A comprehensive Model Context Protocol (MCP) server providing advanced access to the ChEMBL chemical database. | |
| Unofficial Clinical Trials MCP Server augmented-nature/clinicaltrials-mcp-server Provides access to the ClinicalTrials.gov API, enabling search, analysis, and retrieval of clinical trial data through MCP tools. | |
| Ensembl MCP Server augmented-nature/ensembl-mcp-server A comprehensive Model Context Protocol (MCP) server that provides access to the Ensembl REST API for genomic data, comparative genomics, and biological annotations. | |
| GeneOntology MCP Server augmented-nature/geneontology-mcp-server A comprehensive Model Context Protocol server for accessing Gene Ontology (GO) data, enabling AI systems to perform ontology-based analysis, gene annotation research, and functional enrichment studies. | |
| GTEx MCP Server augmented-nature/gtex-mcp-server Enables AI assistants to query and analyze genomics data from the GTEx Portal through 25 specialized tools for gene expression analysis, eQTL/sQTL associations, and genetic variant lookups across 54 human tissue types. | |
| KEGG MCP Server augmented-nature/kegg-mcp-server Enables natural language querying and analysis of KEGG biological databases, including pathways, genes, compounds, reactions, diseases, and drugs. | |
| NCBI Datasets MCP Server augmented-nature/ncbi-datasets-mcp-server Provides comprehensive access to the NCBI Datasets API, enabling genomic, taxonomic, and biological data operations through 31 specialized tools. | |
| OpenFDA MCP Server augmented-nature/openfda-mcp-server A comprehensive MCP server that provides access to U.S. FDA public datasets via the openFDA API, enabling querying of drug adverse events, labeling, recalls, approvals, shortages, NDC directory, and medical device regulatory data. | |
| OpenTargets MCP Server augmented-nature/opentargets-mcp-server Unofficial Model Context Protocol server for accessing Open Targets platform data for gene-drug-disease associations research. | |
| PDB MCP Server augmented-nature/pdb-mcp-server A Model Context Protocol (MCP) server that provides access to the Protein Data Bank (PDB) - the worldwide repository of information about the 3D structures of proteins, nucleic acids, and complex assemblies. | |
| ProteinAtlas MCP Server augmented-nature/proteinatlas-mcp-server A comprehensive Model Context Protocol (MCP) server for accessing Human Protein Atlas data, providing information about protein expression, subcellular localization, pathology, and more. | |
| Unofficial PubChem MCP Server augmented-nature/pubchem-mcp-server A comprehensive Model Context Protocol server providing access to over 110 million chemical compounds with extensive molecular properties, bioassay data, and chemical informatics tools from the PubChem database. | |
| PubMed MCP Server augmented-nature/pubmed-mcp-server Provides comprehensive access to NCBI's PubMed database of over 36 million biomedical citations, allowing users to search, retrieve, and analyze literature directly through MCP tools. It supports advanced queries, citation management, full- | |
| Reactome MCP Server augmented-nature/reactome-mcp-server Model Context Protocol server for accessing Reactome pathway and systems biology data. | |
| STRING-db MCP Server augmented-nature/string-db-mcp-server A comprehensive Model Context Protocol (MCP) server for accessing the STRING protein interaction database. This server provides powerful tools for protein network analysis, functional enrichment, and comparative genomics through the STRING | |
| SureChEMBL MCP Server augmented-nature/surechembl-mcp-server A comprehensive Model Context Protocol (MCP) server for accessing the SureChEMBL chemical patent database. | |
| Fabric MCP Server augmentedivan/fabric-mcp-server An MCP server that exposes Fabric patterns as tools for Cline, enabling AI-driven pattern execution directly within Cline tasks. | |
| VisionCraft MCP Server augmentedstartups/visioncraft-mcp-server Delivers up-to-date computer vision and GenAI knowledge to AI assistants via a comprehensive knowledge base and RAVEN engine, enabling accurate and efficient responses. | |
| ProofPay MCP Server augstentatious/proofpay-agent Provides Solana Pay invoice creation, payment verification, and artifact release tools for ZeroClaw agents, enabling custody-minimized paid delivery of sealed artifacts while keeping encryption keys and policy operator-owned. | |
| Suwayomi MCP Server augumenter/suwayomi-mcp Enables AI assistants to manage a self-hosted Suwayomi manga library through natural language, including searching, adding titles, and downloading chapters. | |
| Digital Life Library MCP Server august-lky/digital-life-library Enables AI companions to look up and save meme/slang explanations with provenance, scan messages for known terms, and manage a local bookshelf with reading progress and bookmarks. | |
| mcp-akshare august1996/mcp-akshare 将akshare数据接口转换为MCP工具格式的Python项目 | |
| Microsoft Fabric MCP augustab/microsoft_fabric_mcp A read-only Model Context Protocol server for Microsoft Fabric, enabling natural language queries to workspaces, lakehouses, tables, jobs, and dependencies. |
31,651–31,700 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.