AI & Agents MCP Servers for Perplexity

Routes AI tasks to dynamic LLM-generated skills via an orbital classifier.

Typed, calibrated and certified decisions over a context, with abstention and evidence.

Unified CLI and MCP server for Google NotebookLM (Enterprise + Personal)

MCP server for OpenAI GPT-5 API with dual interface support (simple + messages)

MCP server for fetching actual free models from OpenRouter API

MCP Server for OTP

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

quickstart for mcp deployment

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

MCP Server for prompt engineering suggestions

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

Discover and rank Stellar 8004 agents with a read-only MCP server and fail-closed contract probes.

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

Objective-Driven Cognitive Architecture Engine — summon experts, councils, and autonomous organizations from any objective

Local-first orchestration agent — a pluggable ReAct hub that fuses dokoro memory + tachibot multi-model council over MCP. Default brain

MCP server that models how you think, not what you know

MCP server that turns a raw project idea into a polished, cost-aware first prompt: stack pick, under-recommended OSS tools, and

A cheap, deterministic first-pass filter for unsupported claims in LLM output, computed without a second model call. Not a standalone

Session handoff for Claude Code: list sessions and build handoff docs another agent continues from.

AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.

Write Velaris, audit what it can touch, and run it under an effect budget.