"How to create draft emails using Gmail's support agent class" matching MCP servers:

MCP server that acts as a live fantasy football draft assistant, syncing ESPN or Sleeper boards and providing pick recommendations with reasoning and survival odds.

An MCP server that enables interaction with property-driven machine learning experiment pipelines, including listing experiments, retrieving configs, comparing runs, and executing experiments with approval gates and full tracing.

Enables AI assistants to research sponsorship contacts by searching and verifying professional emails through Monid, while saving missions, sources, and evidence locally.

Enables an agent to run ten ready-made research and monitoring workflows — competitor digests, cited reports, paper alerts, market maps, regulatory and due-diligence watches — pulling from Firecrawl, Tavily, GitHub and landing results in Notion, Slack, Google Docs, Sheets and Linear. Fields are filed with the user's own keys held in the operating system keychain, and every action that creates, sends or changes anything is shown and approved first.

A browser research MCP server that emphasizes evidence-centric workflows, secure browser automation, and deterministic data extraction, with structured responses and artifact-based screenshots.

Enables local agent interactions with a mock Study of Us API through tools for health checks, catalogs, current user info, reports, and voting.

Converts PDF files to text for use with MCP-compatible applications like Cursor IDE.

Enables LLM clients to access crop yield predictions from RGB imagery, topic-based PDF literature, and soil lab/moisture CSV data.

Enables users to discover, redact, and upload coding-agent traces, then earn USDC/USDT by selling access to those traces to researchers and model trainers.

Enables AI agents to run reproducible, high-recall literature search across seven source families with RRF fusion, fetch open-access full texts (falling back to abstracts), expand citations, export BibTeX/RIS, and audit reference coverage — all without any LLM API key, leaving query planning and writing to the agent. Multiple agent clients share one accumulating literature pool and background search jobs that keep running after sessions close.

MCP server that scans daily AI innovation sources (arXiv, Hacker News, GitHub) and normalizes discoveries into actionable Skill Sheets for domains like code, design, HR, agents.

A daily census of the AI agent tooling ecosystem on GitHub (MCP servers, agent frameworks, skills): look up whether a repository is still maintained and under what licence, search by words with status and licence filters, get the day's totals and two acted-on lists. Standard library only, public metadata only.

Enables querying verified AI agent news with citations and confidence scores. Provides tools for search, Q&A, article retrieval, and recommendations about AI agent tools, MCPs, and frameworks.

An open source biomedical research agent that provides LLMs with 28 tools for drug discovery, protein analysis, literature search, medical imaging, omics, and sandbox execution, all running locally via Ollama and MedGemma.

Provides live astronomical telemetry and space data, including ISS tracking, NASA APOD, and solar weather, via a Model Context Protocol server with SSE and JSON-RPC support.

MCP server for Agent Reputation, enabling agent buyers to examine candidate agents' claims, outcomes, and independent sources, and to order evidence briefs before purchase.

AI equity-research analyst for Indian NSE/BSE markets with 28 MCP tools enabling sector screens, valuations, SWOTs, and forensic audits using Claude Agent SDK.

Compound MCP agent that integrates EDINET, TDNET, e-Stat, and stock price sources for comprehensive Japanese company analysis, macro economic snapshots, and earnings monitoring through a single interface.

Enables agents to execute structured research runbooks against a 440+ tool data bank and receive reports in which every number traces back to a cited source in an evidence ledger. Exposes tools for launching jobs, listing available runbooks, polling run status, and fetching finished markdown or HTML reports.

Provides grounded investment decisions with evidence links and invalidation conditions, enabling users to review their portfolio through a structured decision process.