Best Eval AI Skills & MCP Servers

CogmemAi — Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory benchmark) and 91% on LoCoMo (above human performance). Autonomous memory capture: your Ai's work is saved even wh

MCP server for markdown plan review — companion to the MD Feedback VS Code extension. AI agents read annotations, mark tasks done, evaluate quality gates, and generate session handoffs. 27 tools for Claude Code, Cursor, and other MCP-compatible clients.

Persistent memory for AI coding agents. Local-first knowledge engine with atomic facts, entity graph, and hybrid retrieval. Auto-integrated with Claude Code via hooks; MCP-native for Cursor, Continue, Cline, Windsurf, and any other MCP client.

Skar turns a captured AI agent trace into a committed pytest regression test. MCP server + CLI. Use when a tool-using agent run fails and you want to lock the failure as an executable test.

Model Context Protocol (MCP) server for LightRAG - 30 fully working tools with complete RAG and Knowledge Graph integration

MCP server for Formulon Excel-compatible formula and workbook evaluation

Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.

MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management

MCP server for efficient PDF text extraction, search, and metadata retrieval for Claude Code

MCP server for paper-search-agent: academic paper discovery, access planning, and full-text retrieval via campus network

Model Context Protocol server for digitalcalculator.info financial calculators. v0.3.0 ships 9 calculator tools (mortgage monthlyPayment, compound-interest futureValue, retirement401k projection, Social Security estimatedBenefit, paycheck netPay, IRA cont

MCP server for understanding Javascript internals from ECMAScript specification. Provides vector search over the ECMAScript spec, section content retrieval, and JavaScript code execution with spec section tracing via engine262.

Adaptive memory system for AI applications. Multi-strategy retrieval, cognitive scoring, knowledge graph, and self-improving ML. Connects via MCP or REST API.

MCP server for @agentdance/node-webrtc — lets AI agents discover, evaluate, and get started with the pure-TypeScript WebRTC stack

Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1

MCP server unit testing, end to end (e2e) testing, and server evals

Cloudflare-hosted MCP server for code indexing, retrieval, and assistant memory with a direct remote MCP endpoint and local stdio bridge.

NIA AI Web Evaluation Agent MCP Server - Autonomous browser testing and debugging

An MCP server that serves information from Braintrust documentation as well as your evals and logs.

Context-aware tool retrieval for language models - unlock the full potential of LLM function calling without context window limitations or constraints.

Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents — sub-millisecond queries, token budgeting, no embeddings, no API keys. Built on CodeGraphContext for 155-language tree-sitter indexing.

Playwright-based testing and evaluation framework for MCP servers

Federal Reserve Economic Data (FRED) MCP Server - Access all 800,000+ economic time series with search, browse, and data retrieval capabilities

Sciverse MCP server — exposes academic paper retrieval (search_papers / semantic_search / read_content) to MCP-compatible coding agents (Claude Code, Cursor, Codex CLI, Windsurf, ...).