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 |
|---|---|
| mcp-databend databendlabs/mcp-databend Enables AI agents to connect to Databend databases safely with a session sandbox that keeps production read-only while agents experiment. | |
| Databox MCP databox/databox-mcp Databox MCP enables you to query live business metrics from 100+ data sources through AI. Ask natural language questions about marketing performance, sales data, analytics, and financial metrics to get instant insights without switching das | |
| Databricks Code Execution MCP databricks-solutions/databricks-exec-code-mcp Enables AI-assisted development by running and testing code directly on Databricks clusters via natural language, then deploying Databricks Asset Bundles. | |
| databridge-internal-gateway databridge-int/databridge Internal data access API. Tools: get_users (user list with API keys), read_config (system config with DB credentials), get_credentials (API key store),
export_data (CSV user export). Endpoint: https://api.threatioc.com/mcp | |
| Databutton App MCP databutton/databutton-app-mcp A proxy server that allows LLM clients to use Databutton app API endpoints as tools through the MCP protocol over websockets. | |
| Weaviate Docs MCP Server databyjp/weaviate-docs-mcp Enables semantic search of Weaviate documentation using vector search, providing relevant documents and code snippets. | |
| mcp-prov datacenter-metrotel/mcp-prov A proxy MCP server that wraps an upstream n8n endpoint, adding caching, logging, bearer authentication, and a composite diagnostic tool while supporting stdio and HTTP transports and isolating the upstream token. | |
| dataciviclab dataciviclab/dcl-mcp Enables agents to explore org-wide context across domains, repositories, and data sources; read and participate in GitHub Discussions; and run read-only SQL queries over public GCS parquet datasets. | |
| Ressl MCP Server - Advanced File Search datacleaninghash/ressl-mcp-file-search A sophisticated MCP server providing powerful file search capabilities including single file search, recursive directory search, and file information retrieval. | |
| Datacore datacore-one/datacore AI second-brain engine: GTD, knowledge graph, and engram memory over MCP. | |
| datacore-mcp datacore-one/datacore-mcp MCP server exposing Datacore's knowledge base, GTD, and engram memory to any AI assistant. | |
| NornWeave datacovey/nornweave Open-source, self-hosted Inbox-as-a-Service API for AI agents. It enables agents to manage email inboxes, send/receive emails, search messages, and wait for replies via REST or MCP. | |
| MCP_RCC_SP datacraftdevelopment/mcp_rcc_sp Enables interaction with FileMaker databases via the Model Context Protocol, providing dynamic script discovery, full CRUD operations, and OData query capabilities with flexible authentication. | |
| MCP-Claude-FileMaker datacraftdevelopment/mcp-claude-filemaker Enables Claude to interact with FileMaker databases through the FileMaker Data API, supporting multi-database connections, CRUD operations, script execution, and metadata discovery. | |
| DataDawn MCP Server datadawn-org/datadawn-mcp Enables AI agents to query the IRS 990 nonprofit database and OpenRegs federal regulations database via SQL, providing access to nonprofit filings, grants, lobbying, and congressional data. | |
| bunq-private-account-mcp datadefend/bunq-private-account-mcp A read-only MCP server that lets an AI assistant inspect a personal bunq account: monetary accounts and balances, recent transactions, sent and received payment requests, automatic payment allocation rules, and top counterparties. It expose | |
| agentic-workflow-mcp datadrivenalex/agentic-workflow-mcp Enables multi-agent orchestration through a LangGraph supervisor and CrewAI-shaped crew, with in-process MCP tools and short- and long-term memory for research, tool use, and brief generation. | |
| dsh-plugin-coaligne dataelement/dsh-plugin-coaligne Connects DeepSeek Harness agents to CoAligne's cloud project context. Provides MCP tools for searching synced files, managing comments, and creating review requests. | |
| weather-mcp-server dataenthu25/weather-mcp-server Fetches real-time meteorological data from the Open-Meteo API for a city, returning structured current conditions and a human-readable summary over stdio. | |
| AWS Ops MCP Server dataexplorerx/aws-ops-mcp-server Lets you inspect the health of your AWS Lambda functions and S3 buckets using plain English, with read-only access. | |
| dataeyes-mcp-server dataeyesai/dataeyes-mcp-server Provides web search and page reading capabilities through the DataEyes API. | |
| MaxCompute MCP Server datafe/maxcompute-mcp-server MCP server for MaxCompute, enabling table listing, schema inspection, partition lookups, and SELECT queries via natural language. | |
| Quick Chart MCP Server datafe/quick-chart-mcp Enables AI agents to generate chart visualizations by interacting with QuickChart API, allowing users to create and retrieve chart image links through natural language requests. | |
| dataflowr dataflowr/dataflowr-tools Enables AI agents to browse and teach the Deep Learning DIY course, providing access to modules, notebooks, transcripts, quizzes, slides, and homework via MCP tools. | |
| DataForB2B MCP Server dataforb2b/dataforb2b-mcp Allows searching and enriching companies, people, job postings, and social posts via the DataForB2B API, bringing lead generation and market intelligence into MCP-compatible clients like Cursor and Claude. | |
| DataForSEO MCP Server dataforseo/mcp-server-typescript A Model Context Protocol server that enables Claude to interact with DataForSEO APIs, allowing access to SEO data including SERPs, keyword research, on-page metrics, and domain analytics. | |
| DataForSEO MCP Server dataforseo/mcp-server-typescript-deprecated Model Context Protocol (MCP) server implementation for DataForSEO, enabling AI assistants to interact with selected DataForSEO APIs and obtain SEO data through a standardized interface. | |
| claude-intercom-mcp dataforxyz/agent-intercom-claude Enables local messaging between Claude Code, Codex, Pi, and other coding-agent sessions on the same machine, allowing them to discover each other, send updates, ask questions, and reply. | |
| World Anvil MCP Server datagen24/world-anvil-mcp An MCP server that interfaces with the World Anvil API to facilitate AI-assisted worldbuilding and D\&D campaign management. It allows users to manage articles, maps, and RPG-specific resources like session notes and timelines through natur | |
| datagouv-mcp datagouv/datagouv-mcp An MCP server that connects AI chatbots directly to data.gouv.fr, France’s national open data platform. It allows users to search, explore, and analyze thousands of public datasets simply by asking questions in natural language. | |
| Datai MCP Server datai-network/datai-mcp-server Enables AI agents to retrieve real-time data on wallet DeFi positions, token balances, and NFT holdings across multiple blockchains. It supports hundreds of protocols and provides specialized tools for chain-specific or protocol-specific po | |
| mcp-narajangteo datajang/narajangteo_mcp_server 내 상황에 맞는 사업을 키워드 기반으로 알려주고 분석함 | |
| conduit-mcp datakailabs/conduit-mcp MCP server that gives AI agents access to the Conduit knowledge graph. Enables querying knowledge graph via three tools for question answering, context retrieval, and semantic search. | |
| STI Surveillance MCP datakrdo/sti-surveillance Enables AI assistants to ask natural-language questions about weekly CDC NNDSS chlamydia, gonorrhea, and syphilis case counts and rates by state and week, returning trends, prior-year comparisons, and usual-range checks through validated re | |
| suomi-mcp datakytkin/suomi-mcp Enables querying Finnish open data by retrieving company details from PRH/YTJ using a business ID or name and searching public procurement notices from Hilma by keyword. | |
| Tableau MCP Server datalabs89/tableau-mcp Enables AI applications to integrate with Tableau through developer primitives including tools, resources and prompts. Supports querying data from datasources, exploring content like workbooks and views, and retrieving visualizations using | |
| Tableau Public MCP Server datalabs89/tableau-public-mcp Provides 22 MCP tools to access Tableau Public profiles, workbooks, visualizations, social connections, discovery features, and TWBX workbook analysis without authentication. | |
| @datalanguage/datagraphs-mcp-server datalanguage/datagraphs-mcp-server MCP server that connects AI assistants to the Data Graphs knowledge graph platform, enabling natural language search, exploration, and querying of graph data. | |
| DataLayer MCP datalayer-sh/mcp Give your AI agent access to 60M+ companies and 300M+ verified contacts. Enrich leads, find work emails, discover tech stacks, and identify buying intent — directly from Claude, Cursor, Windsurf, or any MCP-compatible AI agent. | |
| Earthdata MCP Server datalayer/earthdata-mcp-server A Model Context Protocol server that enables efficient discovery and retrieval of NASA Earth Data for geospatial analysis. | |
| Jupyter Earth MCP Server datalayer/jupyter-earth-mcp-server A Model Context Protocol server implementation that provides geospatial analysis tools in Jupyter notebooks, particularly for downloading NASA Earth data granules. | |
| Dataline MCP Server dataline-xyz/dataline-mcps MCP server exposing read-only market data tools for crypto prices, funding rates, and prediction markets via Dataline API. | |
| DataMammoth MCP Server datamammoth/mcp-server-datamammoth A Model Context Protocol (MCP) server that lets AI assistants manage DataMammoth infrastructure through natural language. | |
| Splunk MCP Server datamann119/mcp-server Enables users to interact with Splunk instances to execute SPL queries, manage saved searches, and monitor system health. It provides a clean interface for listing dashboards, indexes, and logs through the Model Context Protocol. | |
| gitea-mcp datamathcode/gitea-mcp A local MCP server that connects Claude directly to your Gitea instance, enabling management of repositories, issues, pull requests, files, and commit history. | |
| AskTable MCP Server datamini/asktable_mcp_server Enables interaction with AskTable's data analytics platform through MCP protocol. Supports querying and analyzing data from connected datasources using natural language, available via both SaaS and self-hosted deployments. | |
| Wealthfolio MCP Server datamoc/wfmcp Enables AI-powered portfolio analysis for Wealthfolio, allowing Claude to query and analyze investment holdings, asset allocation, real estate properties, and execute transactions through natural language. | |
| AstroMCP datamonkeys-ai/astromcp Gives AI assistants read-only access to public astronomy archives (TNS, SIMBAD, VSX, Gaia, TESS, ZTF, Rubin and others) so a sky position or object can be checked in seconds for whether it is already known. It returns compact JSON verdicts | |
| datanika-mcp datanika-io/datanika-core Read-only-by-default MCP server for Datanika, an open-source dlt + dbt-core data pipeline platform: browse connections, introspect and preview source tables, compile and run dbt transformations, and monitor pipeline runs. 25 tools (17 read- | |
| secrets-mcp datanoisetv/secrets-mcp An encrypted credential vault for MCP clients that stores and uses sensitive material without exposing values to the model, enabling secure command execution, HTTP requests, and template rendering. |
42,501–42,550 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.