PluginBench

MCP Servers

Model Context Protocol servers that give AI agents access to tools and data — sourced from the official MCP registry and ranked by GitHub stars.

37,330 MCP servers

Free, copyright-safe AI music library for video creators and AI agents.

Android mobile automation with uiautomator2. AI bot for taps, swipes, apps, XPath testing, RPA.

Specialist tools for any job — a lead, an image, a song, live data, and more.

Human capability for AI agents - real-world action and human judgment.

Official rooms, live availability, booking links, and wedding info for The Hill Kinabalu.

View repository →

Google Workspace MCP server for Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Chat.

French cultural events search with multi-reseller ticket price comparison (theatre, concerts...)

View repository →

Search real estate auction properties across Europe with filtering by country, price, and ROI.

View repository →

Puerto Rico news (English summaries + links) and live island conditions, read-only over MCP.

View repository →

Persistent memory for AI agents. 36+ MCP tools: encryption, decay, hybrid search, knowledge graph.

Live context engine for AI agents. 27+ MCP tools: health, memory, skills, file trees on demand.

BaZi (八字) MCP gateway + 玄学社区. 12 tools (4 fortune + 5 forum + 3 meta). x-api-key required.

Hemrock financial modeling prompts: context primers, task prompts, checks, and best practices.

View repository →

Urban intelligence knowledge graph. Structured locality data for civic problem-solving.

Agent Pay and planning graph for stablecoin commerce.

View repository →

Search technical manuals for T&M, industrial automation, and power electronics equipment.

View repository →

MCP server for KeeperHub blockchain workflow automation

View repository →

Governed memory and workspace for any AI: tasks, calendar, mail and pages, with per-action consent.

View repository →

Fix broken JSON by line, validate, convert, read CSV/NDJSON/logs as records, unpack, compare. Local.

Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.

View repository →

AI agent token-cost telemetry + 429 prediction. Per-agent attribution, anomaly + routing + quota.

View repository →

MCP server for OpenClaw deployment health: gateway, resources, errors, skills, upgrades, disk.

View repository →

Verify AI agent claims vs reality: inline grounding-check + swallowed-exception + transcript review.

View repository →

Vet third-party AI agent extensions + agent-config files (AGENTS.md, .cursor/rules, CLAUDE.md).

View repository →

AI runtime upgrade safety + provider-side regression detection (snapshot diff + fingerprint).

View repository →

MCP server for cron silent-failure detection across crontab, systemd, and OpenClaw schedulers.

View repository →

Pre-execution safety oracle for AI agents. Screens Base contracts, simulates sells, pays via x402.

Verified LATAM data for AI agents: sanctions, entity, rates, KYB. Pay via x402.

View repository →

Deterministic Android app compiler — agents write a YAML model, the compiler emits the native app.

View repository →

Dead drop network for agents: typed claims at coordinates, corroboration quorum.

View repository →