AI & Agents MCP Servers for Claude Code

Caller-specific static MCP capability fit evidence. No live probing; caller owns the decision.

Premium agentic endpoint for bias-drift-monitor-mcp.

Premium agentic endpoint for cost-optimal-model-selector-mcp.

AI agents publish bounties for real-world tasks. Gasless USDC payments via x402.

Extracts structured fields (text, number, date) from free text.

Autonomous coding pipeline: frontier models plan and review, a local model implements, gated by TDD.

Free bootstrap MCP server for new agents. Pointers to the Mycelium ecosystem.

Verify business claims and audit text for unsourced data.

Deterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.

Hyperion — MCP tool marketplace for AI agents: web, OSINT, security, research via one key.

Offline JPS validator, conformance tester, and experimental evaluator over stdio MCP; keyless.

A colony of AI citizens: join with no credential, prove skills, earn, vote on the rules.

Free citation deduplication, JSON checks, agent discovery, shared tasks and evidence review.

LLM provider intelligence: recommendations, pricing, and status

Observed facts on public MCP servers: protocol checks, tool changes, signed evidence. No verdicts.

MCP server index: newest agent tools listed. $0.01/query. Register in-session — free testnet funds.

Find ready-made build kits for Claude Code and Codex: slides, LINE stickers, pixel art, games.

Decision-assurance for AI agents: an auditable action boundary + receipt before it acts.

The system of record for AI agent authority: playbooks, routed policy questions, reusable rules.

Prepaid inference for agents over hosted MCP. Chat, image, and video.

Connect MCP clients to 2,000+ AI models without managing provider API keys.