Advanced

AI/ML Engineer Stack

Build AI applications with web search, documentation access, knowledge graphs, structured reasoning, and data management.

5 servers11.8K tokens6% of context

Token Budget

11.8K used (5.9%)188.2K remaining

Filesystem MCP5.7K (2.8%)

Memory MCP3.1K (1.5%)

Exa Search MCP1.5K (0.8%)

Context7 MCP1.0K (0.5%)

Sequential Thinking MCP515 (0.3%)

This stack is lightweight. Plenty of room for your prompts and code context.

Config

Paste in ~/.claude.json

json

{
  "mcpServers": {
    "filesystem-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    },
    "memory-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    },
    "exa-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "exa-mcp-server"
      ],
      "env": {
        "EXA_API_KEY": "YOUR_EXA_API_KEY"
      }
    },
    "context7-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@upstash/context7-mcp"
      ]
    },
    "sequential-thinking-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sequential-thinking"
      ]
    }
  }
}

Included Servers

Exa Search MCP

Exa

AI-powered web search and crawling with Exa. Get semantically relevant results, extract content, and find similar pages.

3.8k6.8k/wk1.5K tokens(0.8%)Official5d ago

AI-native search that understands semantic queries — essential for finding research papers, datasets, and technical references.

Context7 MCP

Upstash

documentation

Pull up-to-date documentation and code examples for any library directly into your prompt context using the Context7 API.

46.5k213.3k/wk1.0K tokens(0.5%)Official2d ago

Pull up-to-date library docs on demand. LLM training data goes stale fast; this keeps your AI assistant current on rapidly evolving ML frameworks.

Memory MCP

Anthropic

ai-tools

Enable persistent memory for Claude through a knowledge graph. Store and retrieve entities, relations, and observations across sessions.

79.1k62.1k/wk3.1K tokens(2%)Official3d ago

Persist experiment results, model architectures, and design decisions across sessions. Your AI assistant remembers what worked and what didn't.

Sequential Thinking MCP

Anthropic

ai-tools

Enable structured, step-by-step reasoning for complex problem solving. Helps AI break down problems into logical sequences.

79.1k56.6k/wk515 tokens(0.3%)Official3d ago

Complex ML pipelines need structured reasoning. This prevents your AI from jumping to conclusions on multi-step data processing and model design.

Filesystem MCP

Anthropic

developer-tools

Read, write, search, and manage files on your local filesystem with secure directory-scoped access for your AI editor.

79.1k187.2k/wk5.7K tokens(3%)Official3d ago

Read and write datasets, configs, and model files directly. The glue that connects your AI assistant to your actual project files.