AI & Agents MCP Servers for Claude Desktop

Self-hosted MCP server: sandboxed browser, desktop, vision, code-edit packs for any agent.

Discover verified AI inference nodes, get the best node+model per task, pre-price chains.

Verify AI work against criteria and get signed receipts. From Spoolis, guarantees for AI work.

Browse and discover the public three.ws agent marketplace and skills catalog. Read-only.

Fixes the names and jargon speech-to-text gets wrong before your agent acts on a dictated prompt.

AI spend calculator + optimizer — unified cost report across vendors

A Model Context Protocol (MCP) server that provides access to multiple Large Language Model (LLM) APIs including ChatGPT, Claude, DeepSeek

Reversibly compress tool outputs to recoverable handles; expand to exact original bytes on demand.

Runtime constitutional verification for AI answers — claim reasoning, ECS, red team, audits.

Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.

Developer assessment/setup MCP; admitted Once boundaries protect writes, not sibling connectors.

Set autopilot scopes and a daily SOL spend cap, then propose, execute, and undo agent actions.

Decision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.

Render themed charts as hosted URLs. Embed in markdown, emails, and Slack. Hosted MCP, zero setup.

A MCP server for get deepseek COT

Verify that an agent's claimed outcome actually happened, using independently gathered evidence

AI Agent Guardrails MCP server - security layer

High-performance, modular MCP v2 server with safe profiles, worker pool, caching, and stdio.

MCP instruction indexing server with search, CRUD, validation, and cross-repo knowledge promotion.

Recovers malformed LLM JSON. MCP build: 218/300 on MALFORMED-300 (library build 282/300).

Discover Kavel's AI photo/video generators, get tuned prompts, and open the right tool on kavel.ai.