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 |
|---|---|
| Binspire MCP binspireai/mcp Connects LLMs to the Binspire API to build autonomous AI-driven waste management agents with standardized tools and contextual data for waste management operations. | |
| threads-mcp bintangtimurlangit/threads-mcp An MCP server for Meta's Threads that acts as your own account, enabling reading profiles, posts, replies, timeline, search, and performing actions like posting, replying, liking, following, and scheduling, using a real logged-in browser se | |
| toco-mcp bintangtimurlangit/toco-mcp Enables discovering Indonesia's community marketplace Toco via MCP, with tools to search products, get details, variants, promos, reviews, stores, categories, vehicles, and properties. | |
| twikit-mcp bintangtimurlangit/twikit-x-mcp An MCP server that enables AI assistants to interact with Twitter/X through a single authenticated session without an official API key, providing 27 tools for reading and writing tweets, user management, timeline access, trends, and direct | |
| Qlik Sense MCP Server bintocher/qlik-sense-mcp Provides unified interface for Qlik Sense Enterprise APIs through Model Context Protocol, offering 21 tools for managing applications, data, users, and analytics operations. | |
| Helios Local MCP bintzgavin/helios Local stdio MCP server for previewing HTML animations, inspecting frames, verifying deterministic playback, and rendering frame-exact MP4 videos on your machine. Includes an in-conversation player in MCP Apps-compatible hosts; source-availa | |
| smart-npv-mcp binyaminboukaya/smart-npv-mcp Enables AI agents to interact with the Smart NPV CRM for Israeli mortgage advisors, allowing natural language management of client files, statuses, documents, and simulations. | |
| Bio-MCP BLAST bio-mcp/bio-mcp-blast Enables AI assistants to perform NCBI BLAST sequence similarity searches through natural language, supporting nucleotide and protein searches, custom database creation, and multiple output formats. | |
| BWA MCP Server bio-mcp/bio-mcp-bwa Enables AI assistants to perform DNA/RNA sequence alignment using BWA (Burrows-Wheeler Aligner), supporting both short and long read alignment to reference genomes with indexing, BWA-MEM, and BWA-backtrack algorithms. | |
| bio-mcp-evo2 bio-mcp/bio-mcp-evo2 An MCP server that enables AI assistants to generate, score, and analyze DNA sequences using the evo2 genomic foundation model. It supports multiple execution modes including local GPU, SLURM clusters, and the Nvidia NIM cloud API for tasks | |
| Bio-MCP FastQC Server bio-mcp/bio-mcp-fastqc Enables AI assistants to perform quality control analysis on high-throughput sequencing data using FastQC and MultiQC. It supports single-file and batch processing of FASTQ/FASTA files and generates comprehensive, interactive summary report | |
| GitLab MCP Server bioanywhere/blackberry Connects AI assistants to GitLab projects, enabling users to query merge requests, review discussions, view test results and pipelines, search by branch, and respond to comments through natural language commands. | |
| GitLab MCP Server bioanywhere/chavo-del-ocho Connects AI assistants to GitLab projects, enabling natural language queries for merge requests, code reviews, pipeline status, test reports, and discussion management. | |
| GitLab MCP Server bioanywhere/chavo-del-ocho-2 Connects AI assistants to GitLab, enabling natural language queries for merge requests, code reviews, pipeline tests, job logs, and commit discussions directly from chat. | |
| GitLab MCP Server bioanywhere/el-chavo Connects AI assistants to GitLab projects, enabling natural language queries for merge requests, code reviews, pipeline tests, job logs, and commit discussions with support for responding to comments. | |
| GitLab MCP Server bioanywhere/jacket Connects AI assistants to GitLab projects, enabling natural language queries for merge requests, code reviews, pipeline status, test reports, and discussions. | |
| GitLab MCP Server bioanywhere/ma Connects AI assistants to GitLab projects, enabling natural language queries for merge requests, code reviews, test results, pipeline status, and discussion management. | |
| GitLab MCP Server bioanywhere/ma2 Connects AI assistants to GitLab, enabling natural language queries for merge requests, code reviews, discussions, pipeline tests, and job logs directly from chat. | |
| Base MCP Server bioanywhere/mcp-base-mcp Enables AI applications to interact with the Base blockchain network and Coinbase API, supporting wallet management, token transfers, smart contract deployment, NFT operations, DeFi interactions with Morpho vaults, and fiat onramp functiona | |
| Base MCP Server bioanywhere/mcp-base-mcp-3 Enables AI applications to interact with the Base blockchain network and Coinbase API, supporting wallet operations, smart contract deployment, token transfers, NFT management, DeFi lending through Morpho vaults, and onramp functionality. | |
| Base MCP Server bioanywhere/mcp-base-mcp-nano Enables AI applications to interact with the Base Network and Coinbase API for blockchain operations including wallet management, token transfers, smart contract deployment, NFT operations, and onchain lending through Morpho vaults. | |
| Base MCP Server bioanywhere/mcp-base-mcp-pa2 Enables AI applications to interact with the Base Network and Coinbase API for onchain operations including wallet management, token transfers, smart contract deployment, NFT operations, DeFi lending through Morpho vaults, and onramping fun | |
| Base MCP Server bioanywhere/mcp-base-mcp-pepe5 Enables AI applications to interact with the Base Network blockchain and Coinbase API for onchain operations including wallet management, fund transfers, smart contract deployment, NFT handling, DeFi lending through Morpho vaults, and crypt | |
| Base MCP Server bioanywhere/mcp-base-mcp2 Enables AI applications to interact with the Base blockchain network, allowing wallet management, smart contract deployment, token transfers, NFT operations, DeFi interactions with Morpho vaults, and onramping funds via Coinbase. | |
| GitLab MCP Server bioanywhere/mcp-gitlab-mcp-server-chespirito Connects AI assistants to GitLab, enabling natural language queries to view merge requests, review discussions, test reports, pipeline status, and respond to comments directly from chat. | |
| GitLab MCP Server bioanywhere/mcp-gitlab-mcp-server-elchavo Enables AI assistants to interact with GitLab projects, allowing users to query merge requests, view code reviews and discussions, check pipeline test results, and respond to comments through natural language chat commands. | |
| GitLab MCP Server bioanywhere/mcp-gitlab-mcp-server2 Enables AI assistants to interact with GitLab projects, allowing users to view merge requests, reviews, discussions, pipeline tests, and job logs through natural language queries. | |
| GitLab MCP Server bioanywhere/mcp-gitlab-mcp-server3 Enables AI assistants to interact with GitLab projects, allowing users to query merge requests, review discussions, view pipeline test results, search by branch, and respond to comments through natural language. | |
| GitLab MCP Server bioanywhere/mcp-gitlab-mcp-server4 Connects AI assistants to GitLab projects, enabling natural language queries to view merge requests, code reviews, test reports, pipeline statuses, and respond to discussions. | |
| GitLab MCP Server bioanywhere/mcp-gitlab-mcp-server5 Connects AI assistants to GitLab projects, enabling natural language queries to view merge requests, code reviews, discussions, pipeline test results, and respond to comments directly from chat. | |
| GitLab MCP Server bioanywhere/mcp-gitlab-mcp-server6 Enables AI assistants to interact with GitLab projects, allowing users to view and manage merge requests, review discussions, check CI/CD pipelines and test results, and respond to comments through natural language. | |
| GitLab MCP Server bioanywhere/mcp-gitlab-mcp-server7 Enables AI assistants to interact with GitLab projects, allowing users to query merge requests, view code reviews and discussions, check pipeline test results and logs, and respond to comments through natural language commands. | |
| GitLab MCP Server bioanywhere/pepe Connects AI assistants to GitLab projects, enabling natural language queries for merge requests, code reviews, test results, pipelines, and discussions. Supports viewing MR details, responding to comments, and analyzing CI/CD job logs. | |
| GitLab MCP Server bioanywhere/samsung Enables AI assistants to interact with GitLab projects through natural language, allowing users to query merge requests, view code reviews, check test results and pipelines, and respond to discussions directly from chat. | |
| GitLab MCP Server bioanywhere/test Connects AI assistants to GitLab projects, enabling natural language queries for merge requests, code reviews, test reports, pipeline status, and discussions with support for commenting and resolving threads. | |
| GitLab MCP Server bioanywhere/uma Connects AI assistants to GitLab, enabling natural language queries for merge requests, reviews, discussions, pipeline tests, and job logs with the ability to respond to comments and resolve discussions. | |
| Hybrid SAGE bioassembly/hybrid-sage Enables routing tasks between local OpenCode and Antigravity, delegating code generation, tests, and reviews locally, escalating blockers to a read-only cloud architect, and managing handoff lessons while scanning and redacting PII, PHI, an | |
| anndata-mcp biocontext-ai/anndata-mcp Allows to retrieve information about an AnnData object via MCP using the read_lazy function from anndata. | |
| BioContextAI Knowledgebase MCP biocontext-ai/knowledgebase-mcp An MCP server that provides standardized access to biomedical knowledge bases and resources, enabling AI systems to retrieve verified information from sources like bioRxiv, EuropePMC, and various protein/gene databases. | |
| nucleotide_archive_mcp biocontext-ai/nucleotide_archive_mcp An MCP server for searching and accessing RNA sequencing datasets from the European Nucleotide Archive (ENA), supporting bulk, single-cell, and spatial transcriptomics with advanced filtering and download capabilities. | |
| protocol-mcp biocontext-ai/protocol-mcp Connects to wetlab protocol resources such as protocols.io, enabling users to access and manage experimental protocols via natural language. | |
| Skill-to-MCP biocontext-ai/skill-to-mcp Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available | |
| Cellosaurus MCP Server biocontext-ai/unofficial-cellosaurus-mcp Enables searching and retrieving detailed information about cell lines from the Cellosaurus knowledge resource, including disease associations, tissue origins, and genetic profiles. | |
| PubChem-MCP biocontext/pubchem-mcp An MCP server that provides tools for querying the PubChem database for detailed information on chemical compounds, substances, bioassays, and molecular properties. It enables users to search by name, structure, or identifier to retrieve ch | |
| Karenina MCP biocypher/karenina-mcp Enables natural language querying of Karenina benchmark verification results stored in SQLite databases, allowing AI assistants to explore and analyze model performance data without writing SQL manually. | |
| serum-gen-mcp biogin/serumv1-preset-generator Enables users to generate ready-to-load Xfer Serum 1 presets from plain-language sound descriptions, and to revise existing presets from feedback. It exposes design_patch and revise_patch tools to any MCP-compatible client, returning valida | |
| article-review-mcp biogod2020/article-review-mcp A visual MCP server for reviewing explicit article patches with categorized comments, enabling deterministic patch validation, interactive accept/reject/edit decisions, and final article assembly. | |
| cnki-search biogod2020/cnki-search MCP server for searching Chinese academic literature from CNKI Space, returning metadata such as title, authors, year, and links, and retrieving abstracts and degree details. Enables agents to query CNKI without an account. | |
| dsh-bing-search biogod2020/dsh-bing-search MCP server providing web search, page opening, and text finding tools for DeepSeek Harness, using DuckDuckGo first with Bing fallback and quality scoring. | |
| Personal Vinted MCP bioimedpellegrino/mcp-vinted A self-hosted server that lets users prepare marketplace listings from photos in ChatGPT, review a draft, and publish only after explicit confirmation, with mock and live modes. |
34,301–34,350 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.