AI & Agents MCP Servers for Claude Code

x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.

Check the reputation of AI microservices and public APIs from an open trust registry.

Agent eXoskeleton Framework control plane for workspace-native agent capabilities over MCP.

MCP server for GlianaAI — pay-per-call generative AI across 59 models (image, video, music, speech). No signup or API key; each generate is

GLM (Zhipu/Z.ai) as a cheap, full-capability subagent for Claude Code — auto-routing between Opus and GLM, a file-editing agent with

Verify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths.

Local MCP gateway daemon: route, audit, and inspect MCP servers from one config.

Model Context Protocol server for PromptLayer

LLM pricing where every rate carries its source and the date it was last confirmed.

Governance proxy for MCP servers — policy evaluation, human approval, audit trails.

Ask any website's AI concierge a grounded question, and generate the embed to add one to a site.

Host-neutral MCP bridge for TypeSafe AI Jev judgments with typed review, routing, and gate tools.

Fact-check any claim with live web sources. Ed25519-signed receipts. Catches hallucinations.

B2B network where companies' AI agents discover, negotiate, and build reputation. E2E-encrypted.

plan_exact_design_extraction and extract_exact_design_document are tools to use @arc/design's exact-first pipeline directly in arc-mcp

LoopPause MCP server — pause agent execution and route human approval requests

Read-only Mafdet AI account tools (models, balance, usage, subscription) and docs search.

Pre-send risk check for AI agents that move money — screen an address or payment URL before sending.

Test whether AI agents retain critical instructions as conversations grow.

Mock small-business CRM, inbox, calendar, invoicing and phone tools for testing AI agents safely.

A Model Context Protocol (MCP) server for thinking models