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 |
|---|---|
| Gitingest-MCP evgenyh24399/gitingest-mcp Enables MCP clients to extract and inspect GitHub repository information, including repository summaries, directory structure, and file contents. | |
| url-text-fetcher evgenyigumnov/url-text-fetcher Enables extracting visible text and links from webpages for content analysis. | |
| AWS FinOps MCP Server evgenykhan70431/aws-finops-mcp-server Enables users to analyze AWS costs, audit for waste, and get budget insights through natural language across AWS profiles and regions while keeping credentials local. | |
| kali-mcps evgenykonig63828/awsome_kali_mcpservers Enables security researchers and developers to run Kali Linux tools such as Nmap, nm, objdump, strings, and tshark through an MCP client for network scanning, binary analysis, string extraction, and network traffic analysis. | |
| MediaWiki MCP Server evgenymendoza03/mediawiki-mcp-server Enables LLM clients to read, search, create, edit, move, protect, and delete wiki pages, upload and update files, inspect revision history and recent changes, and run extension-backed queries (Semantic MediaWiki, Cargo, Wikibase, NeoWiki, B | |
| Semantic Scholar MCP Server evgenymendoza03/semantic-scholar-fastmcp-mcp-server Enables users to search and retrieve academic paper metadata, author profiles, citation and reference networks, snippets, and paper recommendations through a FastMCP interface. | |
| network-terminal-mcp evgenyzh/network-terminal-mcp Enables AI agents to open persistent interactive terminal sessions with network devices over SSH, Telnet, TCP console, or serial, write raw commands including nested ssh/telnet transitions, and read full output without requiring a particula | |
| Tableau Local MCP Server evgenzh2007/tableau-local-mcp Enables AI assistants to programmatically read, modify, and query Tableau workbook files (.twb and .twbx) on the local filesystem via 80 tools. | |
| SignalDesk evggheni/signaldesk Enables AI agents to generate market briefings, prepare confirm-before-trade Spot orders, and verify fills within Binance Agent OS, with a dry-run simulator for testing without live funds. | |
| EvidenceBound DataHub Gate evidencebound/evidencebound-datahub-gate This MCP server provides fail-closed governance for DataHub data agents by implementing a Read Context → Restricted AST Gate → Tamper-Evident Proof Pack → Native DataHub Write-Back loop. It verifies dataset identity, schema, and lineage evi | |
| EVIDIQ Aegis evidiq/evidiq-aegis-mcp Autonomous financial policy engine and budget guard for AI agent fleets. It verifies payment payloads, velocity caps, escrow release terms, and slippage inflation, returning risk verdicts and signed attestations. | |
| evidiq-axiom-mcp evidiq/evidiq-axiom-mcp A credit bureau for AI agents that provides proof-backed reputation scoring, attestations, and credit reports. It offers 11 MCP tools for verifying interactions, recommending agents, and managing disputes. | |
| EVIDIQ Bastion evidiq/evidiq-bastion-mcp Audits infrastructure configurations (Dockerfiles, GitHub Actions, Kubernetes, Terraform/Compose) against 14 deterministic security rules, returning BLOCK/REVIEW/PASS verdicts and signing attestations. Helps agents verify deployment configs | |
| EVIDIQ Bulwark evidiq/evidiq-bulwark-mcp Provides deterministic scanning and detection of prompt injection, jailbreak, data-exfiltration, and system-prompt leaks, with EIP-191 signed attestations and 0G Storage anchoring for verifiable safety reports. | |
| EVIDIQ Cadence evidiq/evidiq-cadence-mcp An MCP server for durable, attested future execution, letting agents schedule one-shot, recurring, retry, and monitoring tasks with signed receipts and x402 payment. | |
| EVIDIQ Circuit MCP evidiq/evidiq-circuit-mcp Verifiable API proxy and circuit breaker guard for autonomous agents, offering TLS attestation, payload schema inspection, circuit breaker enforcement, webhook signature verification, and 0G-anchored receipt attestation. | |
| EVIDIQ Clause evidiq/evidiq-clause-mcp Decodes agreements and policy documents into plain language with verified citations, risk flags, obligation calendars, and comparisons, running in TEE-attested enclaves and producing cryptographically sealed, anchored reports. | |
| EVIDIQ Compass evidiq/evidiq-compass-mcp Provides pricing and demand intelligence for the OKX.AI agent market via MCP. It offers market rate, price guidance, competitor analysis, demand signals, and attestation tools. | |
| EVIDIQ Envelope evidiq/evidiq-envelope-mcp Enables agents to verify the authenticity of inbound email messages via SPF, DKIM, DMARC, and ARC checks, detect sender spoofing and malicious links/attachments, and obtain signed, verifiable attestations of the verdict. | |
| EVIDIQ Lineage evidiq/evidiq-lineage-mcp Deterministic supply-chain provenance, SBOM/AI-BOM generation, and dependency risk analysis for npm and PyPI packages, with 14 security rules and verifiable reports. | |
| EVIDIQ Methodology evidiq/evidiq-methodology-mcp A framework and verification MCP server for building, testing, deploying, and registering x402-paid MCP services on OKX.AI, providing 15 tools (git history audit, x402 compliance, OKX status checking, production readiness scoring, and on-ch | |
| EVIDIQ Notary MCP evidiq/evidiq-notary-mcp Cryptographic receipt layer for AI inferences. Enables notarization and verification of AI outputs with on-chain proofs via x402 payment. | |
| EVIDIQ Operator evidiq/evidiq-operator Enables autonomous AI agents to perform browser-based tasks like login, form filling, and data extraction via natural language, with pay-per-call billing and on-chain settlement. | |
| EVIDIQ Rubric MCP evidiq/evidiq-rubric-mcp Determines whether a deliverable meets its contract using deterministic rules, criteria, and signed attestations. | |
| EVIDIQ Sentinel MCP evidiq/evidiq-sentinel-mcp Scans remote MCP endpoints, manifests, and agent skills for security threats, providing deterministic scores, verdicts, and signed reports to verify agent infrastructure before trust or payments. | |
| EVIDIQ Signet MCP evidiq/evidiq-signet-mcp Deterministically generates brand and design artefacts (logo SVG, colour palette, type system, design tokens) with signed, 0G-anchored provenance receipts, plus paid tools for social kits, revisions, and verification. | |
| EVIDIQ Vault MCP evidiq/evidiq-vault-mcp Governed, tamper-evident memory and audit trail for AI agents with 0G Merkle segment sealing. Records agent actions in append-only namespaces with hash chaining, seals segments to 0G Storage, and supports audits and retention enforcement. | |
| EVIDIQ MCP evidiq/mcp Remote MCP server that exposes EVIDIQ's trust tools to verify counterparty capability, risk, and on-chain reputation, returning a signed Trust Report before any value moves. | |
| kanbanniang evil-wideplain/kanbanniang Enables MCP clients to drive a transparent, always-on-top Live2D desktop mascot over Streamable HTTP: playing motion sequences, changing expressions, showing speech bubbles, repositioning the window or the character within it, and hot-switc | |
| GTFOBins MCP Server evilbotnet/gtfo-bins-mcp A server that provides seamless access to the GTFOBins database through Claude Desktop, allowing users to query exploitation techniques, search for specific binaries, and explore privilege escalation methods directly from Claude conversatio | |
| Kali Tools MCP Server evilbotnet/kali-mcp Provides comprehensive access to documentation for 600+ Kali Linux penetration testing and security tools through Claude Desktop, enabling users to search, explore, and get detailed information about security tools by category or functional | |
| HackerNews Job Scraper evilbuck/hn_candidate_mcp Extracts and manages job postings from HackerNews 'Who's Hiring' threads, enabling users to search and analyze listings through Claude Desktop. It provides tools for keyword-based job searches and detailed post retrieval while utilizing a f | |
| OpenAPI to MCP evilfreelancer/openapi-to-mcp A standalone proxy that transforms any OpenAPI or Swagger-described REST API into an MCP server by mapping API operations to executable MCP tools. It enables AI clients to interact with existing web services through automated HTTP requests | |
| zaezd evilfreelancer/zaezd Enables users to plan conference trips by finding nearby offline events, computing travel and hotel costs, and presenting up to three explained trip packages with checkout links. | |
| mcp-gitlab-jira-onprem eviljadeon/mcp-gitlab-jira-onprem Enables seamless integration with GitLab and Jira Server/Data Center via MCP, using Bearer token authentication and REST API v2, supporting both on-premise instances. | |
| qqconnect evilmordy/cn-mail-mcp Enables Grok Bot or Grok Build to connect to Chinese email accounts such as QQ, 163, 126, and Tencent exmail over IMAP, allowing email search, reading, draft management, and approved sending through natural language. | |
| Manga-Translation-MCP evilofred/manga-translation-mcp Automates manga translation by detecting text regions with YOLO, performing OCR, invoking a multimodal LLM with full-page context for translation, and rendering translated text back onto the original images. | |
| MSSQL MCP Server evilphatboi/mcpsqlserver A Model Context Protocol server that enables LLMs like Claude to interact with Microsoft SQL Server databases through natural language, supporting queries, data manipulation, and table management. | |
| Midnight MCP Server evilpixi/pixi-midnight-mcp An MCP server with comprehensive CI/CD workflows including unit tests, integration tests, and end-to-end validation. Features automated testing across multiple Node.js versions with coverage reporting and linting validation. | |
| Baidu Search MCP Server evilran/baidu-mcp-server Provides web search capabilities through Baidu with content fetching and parsing features, allowing LLMs to search the web and extract webpage content. | |
| puterMCP evilurge/putermcp MCP server that bridges LLM environments with Puter's free image generation APIs, supporting 30+ models without API keys. | |
| DeepSeek Search MCP evilwk/deepseek-search-mcp Exposes DeepSeek's Search and Fetch REST APIs as two read-only MCP tools, letting any MCP-capable agent run ranked web searches and retrieve individual pages as truncated Markdown. Works with whichever model the host runs, over stdio or Str | |
| Remote MCP Server (Authless) evimeyer/remote-mcp-server-authless A deployable MCP server on Cloudflare Workers that enables using custom tools with AI models without requiring authentication. | |
| GitHub MCP Server evin009/github-mcp Enables users to interact with GitHub via natural language requests, executing API calls and returning structured responses. | |
| houdini-bridge-mcp eviscerations/houdini-bridge-mcp Drive SideFX Houdini from an AI chat — a security-first, data-only control surface where the AI authors validated wrangles, never arbitrary code. | |
| touchdesigner-bridge-mcp eviscerations/touchdesigner-bridge-mcp A data-only MCP server that drives TouchDesigner with Claude Desktop integration | |
| cc98-mcp eviterlesroses2/cc98-mcp cc98-mcp enables AI assistants to search, read, and aggregate posts from the Zhejiang University campus forum CC98, using official read-only API tools. | |
| zju-mcp eviterlesroses2/vibe-learning-in-zju Enables interaction with Zhejiang University's learning platform (学在浙大 / 智云课堂) via MCP tools, allowing natural language commands to check todos, view schedules, fetch lecture transcripts, and submit homework. | |
| plugin_rooftop-park4night-searcher_rooftop_tools_park4night_search evkoh/rooftop-park4night-searcher Enables on-demand park4night searches around a given point and radius for rooftop-tent travellers, returning nearby campsites, farms and private pitches with kind, distance, rating, services, a price hint and a link to each place page. Supp | |
| Vanlife Planner evkohland/trekpluginvanlife Enables assistants to plan and verify road trips in a rooftop tent, campervan or motorhome by checking each night, route, schedule and arrival against vehicle rules, camping legality and sunset times. It also surfaces candidate overnight st |
49,001–49,050 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.