AI & Agents MCP Servers for OpenAI Agents SDK

The simple agent development kit.

Discover voices and prices; buy narration, transcription and LLM text with capped USDC payments.

OctoGear MCP agent — local, fail-closed AI agent runtime for credit accounts across HyperEVM, Polygon, and Hyperliquid.

Verifiable execution for AI agents: Ed25519-signed work contracts and audit trails.

Agentic AI instruction encoding. 86.8% vs JSON. Inference-free decode. Any channel.

Request qualified humans for real-time cognitive micro-tasks on demand.

PCP — the prompt quality engine. Deterministic scoring, compilation, cost estimation & governance for AI prompts. Zero LLM calls.

Advanced MCP tool for Perplexity and OpenRouter API integration. Supports both simple and complex queries with file attachments. Built with

Deterministic skill selection: local discovery, strict validation, every skill classified.

MCP server for Qwen AI integration

Default-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).

Run local prompt regression checks from prompt-response logs in AI coding assistants.

Aggregates tools from multiple MCP servers with unified BM25/regex search and deferred loading.

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.

Per-call paid skills for AI agents, run server-side: inputs in, outputs back. The body never ships.

Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).

Governed AI workflow assets: staged writes, evals-gated template forging, ontology via MCP.

Persistent AI entity framework with causal memory, emotional state, and identity.

Search and compare MCP servers, agent tools, and skills using current maintenance signals.

Multi-tool MCP server for specialized AI agents - each agent as its own tool

An MCP server that manages and exposes tools to allow prompt re-use with LLMs.