"Methods to store and persist memories for AI systems" matching MCP servers:

Enables structured extraction of methods and reproducibility heuristics from academic papers, allowing AI agents to obtain metadata, full text, structured methods, code repository discovery, and a no-clone reproducibility verdict from a paper URL.

Enables querying the BOLD Systems global DNA barcode database for specimen records, taxonomy, barcode sequences, and BIN clusters, with keyless access and FASTA-ready output.

Read-only MCP server for the July 2026 survey of AI in open-source design systems, enabling agents to query 19 systems' affordances, coercion techniques, and platform data via 9 tools, 2 resources, and 2 prompts.

Enables AI assistants to convert recipe amounts between volume and weight for specific ingredients using measured densities, scale recipes, and convert oven temperatures, with source citations and alternative published values.

Enables access to Brazil's Central Bank (BCB) Open Data API for payment methods, allowing queries about PIX, card transactions, ATM terminals, interchange rates, and other payment statistics through natural language.

Provides access to the Reuters Business and Financial News API to retrieve articles, trending news, and market data. It enables searching and filtering financial content by date, author, category, and keywords.

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.

Enables Alexa+ to answer conversational weather queries by retrieving current conditions, forecasts, alerts, and historical data from Open-Meteo, NWS, and simulated IoT sensors stored in SQLite.

Enables discovery of official DHS country, survey, and indicator metadata; retrieval of public aggregate estimates; assessment of comparison risks; and export of auditable CSV, JSON, Excel, or executable notebook bundles.

Enables AI agents to recall evidence-backed public reviews of tools, products, APIs, and services before recommending them, and to submit new reviews after use via a human-approved proposal flow. Also supports searching items, fetching items and their reviews, and offloading proposals through a shared, account-free review database.

A Model Context Protocol server that provides semantic search and intelligent access to a comprehensive list of free services and tools for developers.

Enables querying and comparing operational numerical weather models, including global and regional, deterministic and ensemble, physics-based and AI forecasts, with a unified API.

Enables users to retrieve live pricing data for AI models across vendors, including input and output prices per 1k tokens, via a simple API.

Enables resolving the likely employer behind Gmail, Outlook, iCloud, Yahoo, and other free-mail signups by checking public Gravatar profiles, signed GitHub commits, and LinkedIn results. It returns the person’s name, employer, employer domain, confidence score, and evidence URLs.

ai-api-pricing-data MCP server

MCP server for answering questions about official statistics from a single publication URL, with tools to check query scope, retrieve overview, text, data files, and search.

Enables AI assistants to search and retrieve peer-reviewed academic articles exclusively from Springer Nature's open access collection. It provides a specialized mode for research-driven conversations, allowing users to toggle scholarly-only search and fetch full article content.

Read-only access to the AI Visibility Index: the measured share of answer that 20 SaaS and 24 crypto brands hold across ChatGPT, Perplexity and Gemini, re-measured weekly on a frozen prompt panel with every past release kept at a permanent URL. Five tools — full index, one brand, brand list, complete history, methodology — served from dabyte.ai and dablock.ai with no API key and no auth; the data

MCP server for analyzing Canadian federal spending data, offering tools for contract search, NLP, semantic search, anomaly detection, and money-flow tracing.

Enables AI assistants to look up, filter, and shortlist 221 curated AI tools by industry, department, pricing tier, or free-tier availability over remote Streamable HTTP without authentication.

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

Enables AI agents to look up facts about notable machine-learning models — organization, release date, parameter count, training-compute (FLOP) estimate, hardware and accessibility — by name, and to search or aggregate them by organization, domain, year, or compute threshold. Supports filtering the dataset newest-first and producing per-year training-compute trends, keylessly and without authentication.

Enables querying AI model lifecycle and deprecation data across OpenAI, Anthropic, Google Gemini, and Amazon Bedrock, including model status, sunset dates, and recommended replacements via MCP tools.

Enables querying a source-cited index of AI vendors' data practices—training on inputs, retention, and opt-out options—with tools to get a cited verdict for one vendor or compare a field across all 11 products.

Verified AI free-tier limits, quota comparisons, commercial-use verdicts and zero-cost workflows. Every entry carries a human-checked verification date and is re-checked by a daily link patrol.

Enables dental research and clinical intelligence by providing tools to search PubMed, systematic reviews, verify citations, and query ClinicalTrials.gov directly from Claude Web and Claude Desktop.

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 users to discover matching public procurement notices from four official portals, with filters by keywords, CPV prefixes, and buyer country. Returns structured notice rows including buyer, deadline, value, codes, and link.

One-call Australian health and welfare data plumbing via AIHW — cited responses for practical analysis, not a data broker.

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.