"memory" matching MCP servers:

Central Bank of Russia (CBR) data for AI agents — daily and historical currency rates, key rate, inflation, and macro statistics. Five typed MCP tools, in-memory TTL cache, MIT-licensed, no API key required.

Enables AI assistants such as Claude, ChatGPT and Gemini to query French National Assembly voting records from the public CIVIX open data API in French, with sources cited for each scrutin. It lets users look up roll-call votes by topic, individual deputies' positions, parliamentary groups and vote breakdowns without inventing figures from memory.

Enables AI assistants to compute exact Sri Lankan tax figures — APIT/salary tax, annual income tax, withholding tax, VAT and SSCL — under the official Inland Revenue Department rules in force on any given date since 1 January 2023. Every result is returned with precise decimal amounts and the dated IRD sources and rule versions used, so rates are never recalled from memory.

Enables models to retrieve Ukrainian and EU legislation, ECHR and CJEU case law, ICJ case cards, and Ukrainian public registries, and to check any legal quote against the official source text, flagging verbatim matches, normalised matches, or mismatches with the differences marked. It also reports which operations have been tested per source, so drafted legal statements can be anchored to quoted articles and their versions rather than recalled from memory.

Enables MCP clients to explore and query Israeli government open data from data.gov.il through the CKAN API, including dataset discovery, resources, organizations, tags, and tabular datastore records. Ships a searchable in-memory catalog snapshot with Hebrew normalization and fuzzy matching, plus tools, resources, and prompts for guided analysis over stdio or Streamable HTTP.

Enables AI assistants to access real-time legislative data from the Korean National Assembly including members, bills, votes, and schedules through 276 Open APIs. Supports dual transport modes (stdio/HTTP), configurable Lite/Full tool profiles, and in-memory caching for efficient querying.

Enables AI assistants to retrieve the exact, structured text of 10 major Indian Acts — pulling individual sections or Constitution articles, browsing chapters and section ranges, and running ranked keyword searches — with repealed laws flagged and their replacements named. All results are sourced directly from the underlying Act texts rather than model memory, preventing hallucinated section numbers, punishments, or outdated law.