"Pocket" matching MCP servers:

Enables LLMs to read a user-owned, local-first memory store kept in a portable folder (USB, SSD or laptop), with per-profile permissions limiting what each client can see and access cut off when the pocket is locked or unplugged. Also lets models propose new memories for the user to review and approve, keeping provenance and keeping canonical memory free of direct model writes.

A small, readable MCP learning project implemented in TypeScript that uses a local JSON notebook to demonstrate core MCP features such as tools, resources, prompts, sampling, and notifications.

Lets AI assistants search every Pokémon TCG Pocket card by name, type, rarity, set, evolution stage, ability effect and attack, in six languages, with typo tolerance and semantic search.

Enables AI assistants to interact with the PocketOption trading platform via MCP, including balance checks, candle data, asset screening, and trade placement, with support for multi-agent coordination.

The first commercial implementation of HTTP 402 Payment Required for creator content. AI agents discover music, video, and text catalogs as pre-indexed Pockets (list_pockets, search_pockets — free, no key) and pull licensed content per-use through a 402 paywall. Tiered per-pull pricing by content type; 85% of every pull pays the rights holder instantly, with attribution and an audit trail.

AgentSearch web search (and optional page extract) via MCP stdio. Direct local API or Pocket portal.

Enables managing a Pokémon TCG Pocket card catalog and personal collection in SQLite, with card search, collection statistics, meta deck queries, and OCR-based capture rounds processed locally.

Enables MCP agents to inspect and precisely edit a paired browser editor project through local stdio, with batch commands, previews, exports, validation, and guarded undo/redo while keeping changes hand-editable.

Enables AI assistants to search, browse, and manage your Pocket Casts podcast library.

Enables LLM agents to search Regulations.gov federal dockets, retrieve docket abstracts and metadata, and list rulemaking documents, giving read access to federal regulatory data.

One todo list every AI coding agent can write to — Claude Code, Codex, Cursor — scoped per project, local-first, self-hostable.

A Model Context Protocol (MCP) server for Socket integration, allowing AI assistants to efficiently check dependency vulnerability scores and security information.

A local MCP server for interacting with a network lab, supporting read-only and configuration tools for devices like Arista EOS switches.

Enables AI assistants to rapidly gather and synthesize structural, chemical, conservation, and literature data about protein binding pockets for drug-target triage. Useful as a reconnaissance step before computational binder design.

MCP server for the LookTwice API, enabling validation of emails, EU VAT numbers, IBANs, and domains, plus product screening against U.S. CPSC recalls.

Enables managing PocketBase instances through intent-first tools for schema inspection, record CRUD, bulk operations, authentication, file handling, and server monitoring, with optional destructive operations gated behind explicit opt-in.

Stateful outbound TCP/UDP MCP server enabling LLMs to perform multi-step network protocols like HTTP/1.x, SMTP, Redis, and DNS.

Wraps the CourtListener API for real-time federal docket monitoring, with pluggable client-list connectors (SharePoint, Excel, webhook) and tools for docket monitoring and client matching via elicitation.

Enables AI agents to analyze local or base64-encoded PCAP/PCAPng captures through bounded MCP tools for protocol summaries, conversations, DNS/HTTP/TLS/QUIC inspection, credential and beacon detection, entropy checks, filtering, and Zeek-compatible export.

A complete MCP server for PocketBase, exposing 55 tools to manage collections, records, authentication, files, logs, settings, backups, and crons.