"Designing a memory system for persona-based agents to improve user experience" matching MCP servers:

MCP server that silently monitors state changes in structured data sources (e.g., government open data) and provides a pull-based channel for AI agents to retrieve real mutations since their last cursor.

MCP servers for Czech government & business data: ARES (Business Register) + ČNB (FX rates). Native AI access to company lookups, VAT status, bank accounts, currency conversion.

Provides real-time access to Israeli emergency alerts from the official Pikud Haoref (Home Front Command) API. Enables AI assistants to check current alerts, retrieve alert history with intelligent city filtering, and monitor emergency notifications including rocket alerts, aerial intrusions, and earthquakes.

Provides AI assistants with specialized tools to interact with NIST's Open Security Controls Assessment Language (OSCAL) framework. It enables agents to retrieve schemas, explore models, and generate valid OSCAL documentation for security compliance automation.

Torify gives AI agents the Japanese locale primitives that standard libraries lack — imperial era date conversion (wareki), qualified invoice number validation with NTA registry lookup, corporate number lookup (法人番号), postal code resolution, name romanization (Hepburn), and kanji-to-kana conversion via Yahoo! JLP. 31 endpoints total. No authentication required for MCP. Pay-per-call $0.02/call via

Enables querying SINTEGRA TO (state tax information) through a read-only MCP server, using natural language.

MCP server for consulting vehicle data from DETRAN TO official source. Read-only, pay-per-use, works with any MCP-compatible client.

Finds companies registered at JUCESP from a partner's name, CPF, or CNPJ, returning the NIRE of each participation. It is a read-only MCP server hosted at api.mcp.ai.

Enables users to query IPVA (vehicle property tax) data from the official SEFAZ TO source via a read-only MCP tool.

Enables AI assistants to query the official DETRAN TO source for CRLV printing via a read-only, hosted MCP server with pay-per-query prepaid credit.

Read-only MCP server for querying SEFAZ Tocantins (SEFAZ TO) NFC-e (electronic consumer invoice) data from official government sources via natural language, working with any MCP-compatible client such as Claude, Cursor, VS Code, and more.

Enables searching and fetching GOV.UK Design System guidance via locally-crawled SQLite FTS5 data, with tools like search, fetch, and version.

A Python FastMCP server that re-exposes Kindora's public funder and grant tools for ChatGPT, enabling grant discovery from IRS 990 filings and Grants.gov.

Enables querying of a locally pinned snapshot of the Education-to-Workforce Indicator Framework — 99 indicators and 11.8M observations — to browse questions, describe metrics, resolve places, and fetch or rank data across national, state, county, and district levels.

Provides access to EPA's Air Quality System API with 31 tools for querying air quality data, monitoring sites, and pollution measurements across the United States through natural language.

Enables users to search and query information about military service alternative companies in South Korea through the Military Manpower Administration (MMA) API. Supports filtering by service type, industry, company size, location, and recruitment status.

MCP server for structured Australian macroeconomic and financial data from the Australian Bureau of Statistics (ABS), the Reserve Bank of Australia (RBA), and the Australian Prudential Regulation Authority (APRA).

Facilitates retrieval of National Park Services data using the NPS API, allowing users to list national parks by state and access detailed information about specific parks.

Provides a read-only MCP tool to consult official SEFAZ TO negative debt certificates via a hosted, prepaid API.

Exposes Denmark's Statistical Bureau API as programmable resources, making it easy to integrate with language models and modern AI applications to enable natural language queries for statistical data.