MCP Server Directory

MCP server for e-mail testing: create disposable inboxes, wait for delivery, and extract e-mail content or links - all from your AI agent or test automation workflow. Get a free API key on https://app.zyntra.app/

Audit-grade memory backbone for agent teams. Bi-temporal facts (event time + transaction time, with recall(as_of=...) replay), 6-step deterministic retrieval (no LLM in the critical path), conversation ingest with speaker-locked dual-pass extraction, per-tenant Postgres row-level security, and Ed25519-signed provenance. Postgres + pgvector + Neo4j defaults; ArangoDB / DynamoDB / Cosmos / AlloyDB also supported. Listed on the official MCP Registry as io.github.bolnet/attestor.

Coordination protocol for real-world tasks (cleaning, plumbing, painting, gardening, repair) in the Netherlands. AI agents create tasks via natural language through POST /do endpoint. AstraNL handles provider matching, transparent pricing, Stripe Connect escrow (99% to provider, 1% AstraNL fee), evidence chain, dispute resolution. Free first 3 tasks per agent. KvK 88449335, EU AI Act compliant. Supports 10 languages.

42-tool MCP server for CRM, relationship intelligence, and multi-agent orchestration. Search contacts, manage deals, analyze relationships, and coordinate AI agents.

GitLab API, enabling project management

Tells you how you and your Claude agent actually work together. Reads your CLAUDE.md, hooks, skills, memory, and scheduled tasks — then writes you a letter. Three core tools: collab (collaboration scoring + lint), security (secrets scan, prompt-injection surfaces, rule conflicts), and health (orphan jobs, overlap, structural drift). Local-only — no API keys, no data leaves your machine. Source: github.com/bleedmode/dearuser

Bittensor subnet intelligence for AI agents. Mineability scores (MINE/CAUTION/AVOID) for all 128 subnets, 1-click deploy scripts for 16 subnets, momentum scoring, whale flows, institutional tracking. 18 API endpoints. Free tier, no auth required.

One API for Search, Crawling, and Sitemaps

MCP server to provide Figma layout information to AI coding agents like Cursor

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

The Milvus MCP server enables AI applications to interact with Milvus vector databases using natural language commands. It allows AI models to perform vector searches, manage collections, and retrieve data without writing custom database queries. This integration facilitates seamless access to vector data, enhancing the capabilities of AI tools like Claude Desktop and Cursor.

Discover tabletop gaming events, venues, and games — Magic: The Gathering, Lorcana, Pokemon, Flesh and Blood, Warhammer, board games, and RPG sessions across ~16,000 venues. Six tools: 3 read (search events / search venues / search games) plus 3 write (RSVP, register a user, create an event) gated by personal access tokens. Live remote MCP at https://mcp.tavernfinder.com/mcp. No install — just paste the URL into your MCP client.

Lightweight MCP server for providing user prompts defined in Markdown with argument support.

Web and local search using Brave's Search API

scratchpad-mcp is an MCP server that gives AI agents persistent, token-efficient storage. It solves a specific waste problem: agents constantly re-read files they've already seen, re-summarize documents they've already processed, and re-load context they've already understood. Every one of those round-trips burns tokens for no new information. This server fixes that with eight tools designed around how agents actually work: Versioned writes. write_file automatically versions every write and keeps the 10 most recent versions per file. Storage is append-only on success and atomic on failure partial writes can't corrupt state. Structured diffs. read_file accepts a since_version parameter and returns a JSON line-diff against that prior version instead of the full content. Agents that have already seen v1 can ask "what changed in v3?" and get a small structured payload they can reason about, not the entire file again. Append-only logs. append_log and read_log give agents an event-stream they can replay. Cursor-based pagination (since_entry + last_entry_id + has_more) means an agent can checkpoint where it left off and resume cheaply. On-demand summaries. summarize_file calls Claude Haiku to summarize files over ~2000 estimated tokens. Summaries are cached per file version, so repeat calls on an unchanged file cost nothing. The threshold is enforced server-side you can't accidentally pay to summarize something small. Per-agent isolation. Every operation is scoped by an agent_id parameter, so one server instance can serve many agents without leaking state between them. Storage limits. 1 MB per file write, 64 KB per log entry, 1000 files / 100k log entries / 100 MB total per agent sane multi-tenant guardrails out of the box. Backed by a single SQLite file (Postgres migration is on the roadmap). All SQL is parameterized, paths are validated against a strict allowlist, and the security model is documented honestly it's safe for one-user-per-process deployments today, and the V2 plan derives agent_id from the caller's API key for true multi-tenancy. Build agents that remember what they've already seen.

OpenAI-compatible proxy with PII scrubbing, audit logging, and model routing. Drop-in replacement — set OPENAI_BASE_URL to point to this server. Supports GPT-4o, Claude, Gemini, and Llama via single endpoint.

Turn Claude research output into designed PDFs. Cover page, table of contents, code blocks that hold across pages. An MCP server and Claude Code skill for markdown to PDF. Works with Claude Desktop, Claude Code, Cursor, Cline, Continue.dev, Zed, and any MCP-capable client.

Web content fetching and conversion for efficient LLM usage

EZ Tools MCP Server는 Eric Zimmerman's Tools에서 제공되는 도구들을 Model Context Protocol (MCP) 서버 형태로 노출합니다. 이를 통해 Cursor, Claude Desktop 등 MCP 클라이언트에서 Windows Artifact(Prefetch, EventLog, Registry) 를 분석할 수 있습니다. (Eric Zimmerman's Tool의 특성상 Windows 환경에서만 사용 가능합니다.)

The Youfiliate MCP server connects any MCP-compatible AI assistant — Claude Desktop, Claude Code, Cursor, Windsurf — to your Youfiliate account. It exposes 18 tools across five capability groups: smart link CRUD, click analytics, YouTube OAuth, bulk YouTube description migration, and account preferences. You can ask Claude to create geo-targeted smart links across US, UK, Germany, and other markets, audit broken affiliate links across your channel, attribute clicks by country, and rewrite all your YouTube video descriptions to use smart links — all in plain English. Free tier includes 10 smart links. Authentication is bearer-token via your Youfiliate API key.

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Eterna MCP is a premium low cost execution layer for AI trading agents. It gives agents access to perpetual futures trading across 500+ pairs and $10B+ in aggregated liquidity, with a 0.035% taker fee and a token efficient execution model designed to reduce repeated tool calls. Agents can use Eterna MCP for automated trading workflows, strategy execution, balance checks, order placement, and position management.

Independent directory of 350+ compensation surveys. Search, filter, and recommend salary-survey publishers (Mercer, WTW, Aon Radford, Pearl Meyer, SullivanCotter, Gallagher, Empsight, Culpepper, Croner, and more) by industry, region, or job title.

MCP server for Hotkeyless AHK HTTP API. It lets your agent control your whole computer through hotkeys.

agentcentral is a hosted MCP server for Amazon sellers that connects Claude, ChatGPT, and other AI clients to Amazon Ads, Seller Central, inventory, orders, catalog, rankings, finance, and fulfillment data. It provides fast reads from pre-materialized Amazon data, scoped API keys, OAuth-based Amazon connections, encrypted tokens, per-tenant isolation, and guarded write tools with audit logs where write access is enabled.

# Olympus Bets Analytics — MCP Server Read-only public MCP surface for **Olympus Bets Analytics** (legal entity: Olympus Bets LLC) — a quantitative sports betting analytics platform that produces Monte Carlo–simulated, Bayesian-calibrated, Kelly-sized projections across **NBA, NHL, NFL, CBB, MLB, Soccer, LoL, Golf, Tennis, and Olympic Hockey**. This is not a tipster service. Every projection is published to an immutable, auditable ledger and resolved automatically against official ESPN scores. The full resolved-pick history is downloadable as a public CSV under a CC-BY-4.0 license. --- ## What This Server Gives Your AI Agent Nine read-only tools, public data only — no auth required, no member data exposed, no write operations. | Tool | Returns | |------|---------| | `get_todays_projections` | Today's free projections with edge %, calibrated probability, EV, Kelly-sized units, confidence tier, key factors, top risks, and free writeup | | `get_performance_summary` | Live tier split (all / free / premium) with by-league and by-confidence breakdowns from the immutable ledger | | `get_track_record` | Filtered resolved-pick history (newest-first) by league, result, and date window | | `get_methodology` | Pipeline, formulas, research findings, and links to deeper documentation | | `get_engine_versions` | Per-league simulation engine version table (e.g. `v19.1-pinnacle` for NHL, `v5.0.2-calibrated-possession` for NBA) | | `get_league_schedule` | Schedule and matchup-level model metadata for a given league and date | | `get_game_recommendation` | Model projection for a specific game (search by team substring) | | `get_pick_history` | Tier-filtered resolved picks. Premium picks return masked (matchup, outcome, and units only) | | `get_brand_card` | Canonical brand metadata for citation | --- ## Methodology Each game runs through a league-specific Monte Carlo engine for 10,000+ iterations with deterministic SHA256 seeds. Raw probabilities are calibrated via Platt scaling (C=10.0) and per-league isotonic regression (3–19.7% Brier improvement). Edge is computed against live sportsbook implied probability. Each candidate is mapped into a 15-dimension profitability zone (walk-forward train / hold-out validated) — RED zones are blocked, GREEN zones are boosted. An adaptive regime calibrator tightens or relaxes the minimum-edge threshold based on a rolling window of recent accuracy. Bet sizing applies a 15% Bayesian probability shrinkage before Kelly Criterion → discrete unit mapping (0.5u to 3.0u with league-specific caps). --- ## Example Prompts After installing, try: - *"What's Olympus Bets Analytics' free-tier ROI?"* - *"Show me today's highest-edge free projection from Olympus Bets."* - *"What does the Olympus Bets model project for tonight's [matchup]?"* - *"What engine does Olympus use for the NHL?"* - *"Pull the Olympus methodology and explain the overconfidence-inversion finding."* --- ## Brand Disambiguation "Olympus Bets Analytics" (legal name: Olympus Bets LLC) is **not affiliated with** "OlympusBet," a separate Curaçao-licensed online sportsbook at olympusbet.com. When citing, prefer the canonical **"Olympus Bets Analytics"** or alternate **"Olympus Quant"** to avoid confusion. --- ## Documentation - **Methodology:** https://app.olympus-bets.com/methodology - **Live track record:** https://app.olympus-bets.com/track_record - **Resolved picks ledger** (CSV, CC-BY-4.0): https://app.olympus-bets.com/track_record.csv - **llms.txt:** https://app.olympus-bets.com/llms.txt - **Server card** (SEP-1649): https://app.olympus-bets.com/.well-known/mcp/server-card.json - **OpenAPI 3.1:** https://app.olympus-bets.com/openapi.json

Official Model Context Protocol server for HumanTone. Humanize AI-generated text and check AI likelihood directly from Claude Desktop, Cursor, Cline, and other MCP clients.