AI & Agents MCP Servers for Windsurf (legacy)

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

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.

Agent reasoning, memory, and token-optimized context for AI applications.

MCP server that exposes Claude-style skills to any MCP client.

Adorbis AI MCP server — one key, every model, auto-routed. Use Adorbis AI from Claude Code, Cursor, Cline, and any MCP-compatible tool.

MCP server: static worst-case token-budget analysis for LLM-agent workflows (LangGraph/CrewAI/OpenAI-Agents) + signed budget certificates.

Comprehensive MCP server with 34 reasoning modes (30 accessible via 13 focused tools) including historical reasoning, academic research

Paid Capture and Guard tools for public-source observations before autonomous actions.