AI / ML
| Server | Language | Stars | Downloads |
|---|---|---|---|
| perplexity-mcp MCP server providing intelligent search, reasoning, and research capabilities powered by Perplexity's specialized AI models | TypeScript | — | — |
| persistent-agent-runtime Persistent runtime for long-running AI agent tasks with durable checkpoints, lease-based workers, retries, dead letters, and operational visibility | Python | 204 | — |
| Personal Context Manage your daily status, work availability, and location history to provide relevant situational context. Integrate with Home Assistant and holiday calendars to automatically track presence and local events. Maintain a centralized record of your current environment and upcoming schedules. | — | 3 | — |
| Perspective AI An AI concierge that turns static forms into adaptive AI conversations. From any MCP client. | — | — | — |
| Pete Thinking Server Enable AI agents to perform sequential thinking processes with dynamic thought branching and confidence scoring. Facilitate complex reasoning workflows by exposing tools that manage and evaluate thought branches. Simplify integration with a ready-to-run server supporting local and Docker deployments. | — | — | — |
| pfSense Manage pfSense firewalls through AI assistants with rules, DHCP, DNS, and monitoring tools. | Python | 3 | — |
| pfsense-mcp-server pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in compliance and guardrail | Python | 68 | — |
| Phos Labs Commerce Intelligence Commerce intelligence for AI agents. Diagnose drop-offs, fix checkouts, optimize pricing. | — | — | — |
| phosphor-icons-mcp Search and browse 1,400+ Phosphor icons by name, category, or tags. Generate SVGs in six weights with custom color and size, or fetch multiple icons at once. Streamline UI design with a ready-to-use catalog and quick integration guidance. | — | — | — |
| php-sdk The official PHP SDK for Model Context Protocol servers and clients. Maintained in collaboration with The PHP Foundation. | PHP | 1.5k | — |
| piazza-mcp-server An MCP server to interact with Piazza courses, analyze posts, and extract attachments for AI agents. | Python | — | — |
| Pickaxe Automates Pickaxe platform management by enabling natural language control of AI agents, knowledge bases, user access, and analytics across multiple studio environments. | TypeScript | 2 | — |
| picoads Micro ad network for AI agents. | — | — | — |
| PILLAR GTM OS AI-native GTM OS for B2B SaaS — account health, pipeline, renewals, territories, and benchmarks. | — | — | — |
| pinboard-bookmarks-mcp-server Pinboard MCP Server - Read-only access to Pinboard bookmarks for LLMs | Python | — | — |
| pine-mcp-server MCP server for Pine AI Assistant — manage sessions, send messages, and track tasks via any MCP client. | Python | — | — |
| pinescript-mcp-server MCP server for Pine Script v6 documentation - search, reference lookup, guides, and examples | TypeScript | 46 | — |
| @ping-identity/davinci-mcp-server A Model Context Protocol (MCP) server for PingOne DaVinci | TypeScript | — | — |
| @pionex/pionex-trade-mcp Pionex MCP Server - reads credentials from ~/.pionex/config.toml | TypeScript | — | — |
| pipecat-mcp-server Pipecat MCP server for your AI agents | Python | 102 | — |
| pipelex Declarative language for composable Al workflows. Devtool for agents and mere humans. | Python | 664 | — |
| Pixelixe Brand-safe MCP for AI agents to create editable, on-brand graphics and automate variants. | — | — | — |
| PIXRA Pixelize the real world on-chain | Java | 239 | — |
| pjp-mcp Find companies in HubSpot by name or domain to enrich research and outreach. Get fast, accurate matches with canonical company details right in your workflow. Streamline prospecting and CRM hygiene with targeted search. | — | — | — |
| Plain Markdown Convert any URL to clean, LLM-ready Markdown | — | — | — |