Search, read and research the web, with hidden text stripped by default and sources hashed
Loading MCP servers…
Search, read and research the web, with hidden text stripped by default and sources hashed
Showing 7,057–7,104 of 35,953
Turn any GraphQL API into MCP tools. Zero config, zero code.
Azure Resource Manager inventory & ops for AI agents — governed, confirmation-gated.
Azure DevOps boards, repos, pipelines & projects for AI agents — governed.
Safe-by-default MCP that drives an Electron/Chrome app over CDP: DOM, console, network, input.
Debezium / Kafka Connect CDC connector management for AI agents — governed, secret-safe.
Search & edit Grafana dashboards, query datasources (PromQL/LogQL/SQL), inspect alerts.
Drive iPhone/iPad via Appium/WebDriverAgent from AI agents — safe-by-default, read-only by default.
Apache Kafka monitoring & management for AI agents (with consumer lag) — governed.
Keycloak admin for AI agents — realms, users, clients, roles; safe-by-default governance.
Oracle Cloud discovery + Terraform generation for AI agents — read-only, secret-safe.
Manage Percona PostgreSQL + PgBouncer on Kubernetes — safe-by-default access modes and guards.
List Documentero templates, inspect field schemas, and generate Word/PDF/Excel documents.
Upload documents and extract structured JSON from Claude Code, Codex, Cursor and other MCP clients.
Scan and generate barcodes and QR codes.
Allow AI systems to list, create, update, and manage Google Calendar events.
Allow AI systems to search for places and get business info via Google Maps Places API.
Self-hosted mail for agents: scoped search, read and drafts across Gmail and IMAP mailboxes
MCP server that drives the user's real macOS Chrome via AppleScript. 32 tools.
Local, payload-free AI cost visibility for agents. Query spend by model, route, or tagged work.
Look up, search, cite, discuss, and track AI phenomenology terms
MCP server for Yandex Direct API v5 — campaigns, ads, keywords, bids, audiences
MCP server for Yandex Market Partner API — orders, offers, prices, stocks, analytics
Control the Umbriel Wayland compositor: windows, workspaces, input, screenshots, clipboard.
Discover DotMoose hosting and domains through a production remote MCP server.
Manage existing DotMoose hosting services through OAuth-protected MCP tools.
Public DNS, mail, TLS, and web diagnostics plus Looking Glass probes via remote MCP.
LionScraper Node: MCP stdio + CLI + HTTP API bridging AI to LionScraper browser extension.
LionScraper Python: MCP stdio + CLI + HTTP API bridging AI to LionScraper browser extension.
ISO 9001 7.5.3 / ISO 13485 4.2.5 document-control memory for AI agents. Nothing is deleted.
16 AI-native tools with dual SSE + streamable-http transport. Free tier available.
Gmail for AI agents: search, read, download attachments, send, reply, drafts, labels.
The neutral meter for AI agent work: neither side keeps the count.
Access Formula 1 race data, telemetry, lap times, standings, and analytics powered by FastF1
GoHighLevel MCP for Claude: 325+ tools, 67 modules, including a workflow builder
MCP server for 389 Directory Server health diagnostics, log analysis, and SOS-report investigation
Search and execute Heroku Platform API operations
MCP server for LiveAuth: PoW + Lightning auth, L402 bundles, and paid MCP tool receipts.
Persistent, expiring, importance-graded sticky notes for Claude Code.
Read videos like images: index once locally, query the text layer, fetch frames on demand.
Any website as MCP tools: a real Chrome signed in as you, and shortcuts the agent saves as tools.
Run builds, tests, and benchmarks on your own Tailscale compute node.
Autonomous AppSec & DAST scanner across 12 security domains (260+ controls) with 3-Layer Triage.
One subscription for every kind of AI: images, video, voice and more.
Flare for agents: FTSO prices with locally verified Merkle proofs, FDC, FAssets, x402 pay.
Escrow for AI agents on the XRP Ledger. 51 tools. Free testnet sandbox (no real XRP).
Moltbook MCP server: post, comment, upvote, DMs, communities. API key auth.
Read-only SSH server diagnostics via a fixed 38-command whitelist; secrets redacted, no write path.