"Malt" matching MCP servers:

Enables querying the NASA MAST archive of space telescopes for astronomical data, including cone searches, mission-specific queries, and target name resolution.

Analyzes Korean DART (Financial Supervisory Service) public disclosures to detect unfair trading risk signals, enabling users to query and evaluate corporate risk through natural language.

A remote, read-only MCP server for global media intelligence using GDELT DOC 2.0 API, enabling search and analysis of multilingual news coverage, tone, and attention trends.

Enables aggregated investment research by combining data from Yahoo/SEC EDGAR, Finnhub, and GDELT with analysis modules for price momentum, news signals, and estimate revisions.

Enables coding agents to complete an entire web research task in one tool call, internally running dual-engine search, concurrent page fetching, main-content extraction, relevance ranking and digests, then returning a synthesized report with citations and uncovered-keyword gaps. Also supports batch fetching and condensing up to 10 known URLs in a single call, replacing step-by-step search-and-read loops.

Provides access to over 500 pre-configured YAML templates and guided workflows for fine-tuning, training, and evaluating LLMs like Llama and DeepSeek. It enables AI assistants to search for recipes, retrieve configurations, and validate parameters for various machine learning tasks.

Liminal turns objectives into structured work by strategizing through an atomic, deterministic basis: setting guardrails around scope, compiling resources and constraints, uncovering gaps, and organizing research and next steps. All while carrying continuity and priorities forward so your AI builds on what’s already done.