AI & Agents MCP Servers for Claude Code

Production MCP server for multi-agent AI research with OpenRouter

File-claim coordination for parallel AI coding agents: claim files before edits, no stomping.

Local stdio MCP server that runs coding tasks through OpenCode or trusted CLI worker profiles.

Operating contracts for AI agents. Structured instructions compiled into system prompts.

AI cost tracking: 11 tools for spend, budgets, and Claude Code + Cursor + Cline costs

An MCP server for interacting with Magnet (magnet.run)

Browse 160+ LLM models and live pricing — no API key needed for catalog. Add key to route chat.

Open model files with recorded SHA-256 and licence labels. Ask for what's missing.

Read, replay and fork recorded coding-agent runs.

Prices, context windows, lifecycle and deprecation dates for 270+ AI/LLM models. Daily, no key.

Typed Jev decisions in one batched tool: choice, score, and yes/no probabilities.

Multiplayer for AI coding agents: collision detection before the edit, messaging, delegation.

Rate-limited MCP HTTP proxy: sliding window plus token bucket pacing so long tasks avoid 429 errors.

Detect fabrication and hallucination in any LLM output. 30+ models supported.

Provider-independent agent runtime for the terminal — cloud and local models, real tools, MCP, plugins, memory, sub-agents, and Dulus OS.

Pay-per-token Claude & Grok inference, settled in BSV, via the inference.bsvkey.com gateway.

MCP server for interacting with Novita AI API

Search receipt-verified agent build packs, with each pack's real M-of-N pass rate.

SkillFM Beacon MCP: AI health checkups, token usage, LLM cost optimization, BYOK monitoring, and safe agent cleanup.

Discover and transact on the AntSeed P2P AI network from any MCP-compatible agent.

Delegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.