59559 Model Context Protocol servers — searchable, rated, ready to install.
MCP server that pays x402-gated HTTP endpoints — fetch, and on a 402 authorize, sign, retry
MCP server and CLI for Brave DevTools
MCP server for siGit (sigit.si): browse repos, search code, manage PRs/issues, web search.
Connect Claude to Lawmatics: matters, contacts, pipelines, tasks, forms, custom fields, invoices.
Self-hosted homelab log intelligence over MCP, CLI, and REST with SQLite/FTS.
Isolated dev environments, one per git worktree: ports, env, and DB slices as agent tools.
Build browser games on gamedev.pl from your coding agent.
Your AI agent deploys, migrates & upgrades self-hosted Odoo ERP on a server you own.
Your runbooks as agent tools: scripts from runbooks.json served as typed, allowlisted MCP tools.
Local-first, read-only MCP server for recall over your Gmail: search, contacts, threads, digests.
Kubernetes MCP server for diagnosis, resource management, GitOps, and RBAC-enforced operations.
Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.
AI security scanner for Solidity + free CC0 dataset of Sherlock audit-competition acceptance rates.
Generate and read PDFs for AI agents: a generate_pdf and a read_pdf tool, priced per document.
MCP server for Google Cloud Armor WAF log patrol: deny summaries and false-positive checks
Cost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts.
Task management for teams building with AI agents. Agents claim tasks and report progress.
Gmail MCP server for email triage: search, labels, archive, trash, unsubscribe, snooze.
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
Cite or capture a web page; installs the capture extension in Firefox and Chrome.
Send end-to-end encrypted email and files. Encryption happens on your machine, not our server.
Proves AI-generated Python does what you asked: lint, types, security, sandbox run, exact fixes.
Deploy and host the apps your AI assistant builds — a real server, database, and shareable URL.
POST /mcp