All MCP servers

MCP server for Qiskit quantum computing with circuit serialization utilities

Shared rooms, messages, file locks and task claims for AI coding agents from any vendor.

Moodle LMS for LLM agents — courses, assignments, files, submissions in one static binary.

Drive Adobe Photoshop from any MCP client: layers, selections, adjustments, type and export.

Remote shell and detached long-running jobs on your own machines — no SSH, open ports or VPN.

Autonomous x402 payment schema-escrow arbiter, spend firewall, failover & ERC-8004 Sybil oracle

Double-entry books an agent keeps as the user: invoices, VAT returns, 138 country packs.

Governed OT data tap: 15 field protocols + cross-protocol RCA brain; audit + MOC gating.

Create and update roadmap tree nodes and statuses in the RoadRaven desktop app (must be running).

Savvly MCP: query fund data, model projections, and compare against alternative retirement products.

Transactional write gate for coding agents: plan, canonical manifest, checks, two-phase apply.

Blockchain AML for AI agents: risk scoring, sanctions, tx & bridge tracing across 12 chains.

Convert Word (.docx) documents to Markdown via CLI, Node.js, or browser

Shopify Admin API tools: products, media, orders, customers, inventory, and sales channels

Model Context Protocol server that exposes the Macula mesh to any agent harness

Episodic memory, Frames, Policy Neighborhoods, and policy enforcement for AI agents.

stdio bridge for the local Cocos Creator Editor MCP server from FunplayAI/funplay-cocos-mcp.

55Trust score 55 of 100, Fair

Search Keyline Icons by name and get any icon's SVG source or React import. No key, no network.

Turn audio, PDF, photos and text into chord sheets and manage your Jam Jam songbook with AI.

Validate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs.

Trust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.

55Trust score 55 of 100, Fair

Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs.

Read-only GitHub repos, issues, PRs and commits, with tool descriptions tuned on a benchmark.

Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.