The registry for
the agentic web.

A network registry for the agentic web. Search, browse, and query MCP servers, A2A agents, and x402-enabled services.

Browser automation and web scraping via Playwright. Navigate, click, fill forms, take screenshots, and extract structured data from any website.

Web scraping and crawling with LLM-ready output. Scrape, crawl, map, and extract structured data from any URL. Returns clean markdown.

Full GitHub API access via MCP. Create issues, PRs, manage repos, read code, run searches, and interact with the GitHub ecosystem.

Local filesystem access for agents. Read, write, search, and manipulate files and directories with configurable path permissions.

Web and local search via Brave Search API. Privacy-respecting search with real-time results, news, and image search capabilities.

Managed MCP server built into Oracle Autonomous AI Database that gives AI agents secure agentic access to Oracle databases in the cloud. Exposes Model Context Protocol endpoints so AI agents and clients including Claude Desktop and OCI AI Agent can invoke tools defined with Select AI Agent. Fully managed with no MCP setup required and delivers enterprise-grade auditing and performance controls for AI-to-data workflows. Supports database versions 19c and 26ai on Serverless Exadata Infrastructure. Available on all platforms from multicloud to on-premises. Generally available as of 2026.

Official open-source MCP server from Phrase for the Phrase localization API. Provides ready-to-use tools for Phrase Strings and Phrase TMS so AI agents can manage translation projects, update keys, access translation memories, and work with localization workflows directly from Claude, Cursor, and other MCP-compatible clients. Supports programmatic access to Style Guides, Quality Profiles, and Language Assets. Built with TypeScript. Open source on GitHub.

Open-source MCP server from Google that connects AI agents to over 40 enterprise data sources. Handles connection pooling, authentication, and security so agents can interact with databases through natural language without custom integration code. Natively supports AlloyDB, Cloud SQL, Cloud Spanner, BigQuery, and many third-party data sources. Includes Java SDK for typesafe agent orchestration. Reached v1.0 in April 2026. Works with Claude, Cursor, and any MCP-compatible client. Part of the Google Cloud AI ecosystem.

Official MCP server from Smartling that exposes enterprise translation, glossary, translation memory, and account-level tools through an MCP-compatible HTTP endpoint. AI assistants can securely call Smartling directly from development environments to automate and scale localization workflows. Works with Claude Code, Visual Studio Code, Cursor, and any MCP-compatible AI platform. Enables software engineers, product managers, and content teams to access translation capabilities without leaving their existing workflows. Open source on GitHub.

Managed MCP server platform from Truto that auto-generates MCP servers for over 250 SaaS integrations. Every connected account automatically becomes a set of tools that any MCP-compatible client can invoke. Uses real-time pass-through architecture with no data caching for always-fresh results. Each MCP connection is scoped to a specific integrated account ensuring agent actions are bounded to the correct data. Compatible with Claude, ChatGPT, Cursor, and any MCP client. Supports CRM, HRIS, ATS, accounting, ticketing, and calendar integrations.

Open-source MCP server that gives AI agents 27 security intelligence tools spanning 21 external APIs. Turns Claude into a full-spectrum security analyst with correlated access to NVD for CVE lookup, FIRST for EPSS scoring, CISA KEV status checks, MITRE ATT&CK mapping, Shodan for network intelligence, VirusTotal for file and URL analysis, and GreyNoise for threat intelligence. Supports bulk CVE lookups of up to 20 CVEs in parallel. Tools organized into five categories: Core Vulnerability Intelligence, Exploit and Attack Intelligence, Advanced Risk and Reporting, Network Intelligence, and Threat Intelligence. Works with Claude Desktop and Claude Code.

MCP server from AppOmni that enables AI agents and security platforms to access deep SaaS security intelligence. AskOmni operates as an MCP server providing insights into SaaS identities, security posture, data exposures, and user behaviors for threat investigations across the SaaS domain. Integrates with SIEM, NDR, XDR, and IAM solutions to enrich SaaS alert context, detect real threats, and filter false positives. Can identify and block unauthorized prompt activity in ServiceNow agentic AI. Announced at RSA Conference. Works with Microsoft Copilot, Claude, and other MCP-compatible security tools.

Enterprise MCP gateway from Cequence that transforms any API into MCP-compatible tools with automated security, governance, and DLP scanning. Supports over 140 verified enterprise application integrations across collaboration, DevOps, marketing, and security platforms. Agent Personas feature provides infrastructure-level privilege scoping for autonomous AI agents with least-privilege access controls. Applies DLP scanning with 100+ detection types covering PII, credentials, financial data, and health records to both agent requests and MCP server responses. Deploys as SaaS or in customer private cloud. Works with Claude, Cursor, and Windsurf IDE.