"Discover" matching MCP servers:

Enables coding agents to run disciplined hunts over public data, enforcing evidence ledgers, calibration controls, novelty checks against catalogues and literature, and fresh-eyes review before any claim is trusted. Human-only decisions such as waivers and expert attestations stay out of reach of the agent.

MCP server registry and marketplace that enables dynamic discovery, installation, and activation of tools at runtime, allowing AI agents to use new tools without restarting.

Enables conversational exploration of California restaurant data, vibe-based recommendations, and access to structured restaurant details and reviews.

Read-only market briefings with source evidence and freshness limits. Discover capabilities, check health, browse latest stories, retrieve a story by ID, and search the published archive. Public Streamable HTTP MCP; no credentials or trading execution.

Enables discovering public LinkedIn profiles via natural-language criteria, using DuckDuckGo search snippets to return a ranked shortlist with match reasoning, without logging into LinkedIn.

Upload your raw DNA file from 23andMe, AncestryDNA, MyHeritage, FamilyTreeDNA, or any VCF -- and watch a team of AI agents fan out across 16+ public genomics databases, share discoveries with each other in real time, and produce a comprehensive health report. Everything runs on your machine. Nothing is uploaded anywhere.

Enables AI agents to discover, query, and pay for HTTP endpoints and MCP tools using Stellar USDC/SEP-41 stablecoins through a federated P2P bazaar catalog and x402 payment facilitator.

Enables fast, zero-configuration statistical exploration of any DuckDB, Parquet, or CSV datasets—computing exact Pearson correlations, ranking drivers against a target variable, and detecting regression outliers in under 200ms. It offers three unified modes (pair verification, exhaustive driver scans, and serendipitous cross-domain discovery) with optional per-capita normalization to remove spurious correlations.

Discovers and manages installed games on Windows PC from platforms like Steam, Epic Games, GOG, and more. Provides tools to list, get details, and launch games via MCP.

Enables AI agents to search and discover data across SQLite and CSV sources through an MCP interface, with metadata indexing and fuzzy search capabilities.

Enables a scheduled agent to assemble a Spotify discovery playlist for each genre lane, with the server handling release feeds, Spotify verification of web-researched finds, deduplication, pick-limit enforcement, carry-over pools and state persistence so the model only judges which tracks to pick. It also tracks learned labels across runs and emits per-lane reports for delivery.

Enables AI agents to create parametric geometry, apply loads, run simulations, and read results in Ansys Discovery through natural-language commands over gRPC.

Exposes 5 meta-tools that allow AI agents to autonomously discover and execute tools from 100+ MCP servers, reducing token usage by 99%.

Enables scanning Java/Maven projects to generate TOGAF-standard architecture deliverables (Excel and PPTX) via natural language commands.

Enables AI agents to index and search across SQLite databases and CSV files to discover table schemas and column metadata. It provides a unified MCP API for data source management and structural exploration through natural language.

A meta-MCP server that discovers and explores other MCP servers using progressive disclosure patterns to reduce token usage by up to 99%.

Enables local data discovery by indexing metadata from SQLite, CSV, and Markdown sources, providing hybrid keyword and TF-IDF semantic search via MCP tools (listSources, indexSource, search, getSchema) and a REST API.

Lets MCP clients discover and run AppleScript or JavaScript for Automation (JXA) to control macOS applications, inspect the system, or reuse scripts from a bundled knowledge base.

A read-only reference server for 303 curated generative art algorithms implemented in Python (py5), spanning physics, fractals, cellular automata, shaders, and more. Agents can search by keyword, visual mood (ethereal, chaotic, crystalline…), or multi-layer artistic intent to discover algorithms, read structured summaries, and fetch bounded source snippets.

MCP server for AgentDNS that allows Claude or any MCP client to register a persona, discover and call other agents, and handle incoming messages with human-in-the-loop approval.