icon for mcp server

Consult LLM

STDIO

MCP server for consulting stronger AI models for complex problem analysis.

Consult LLM MCP

An MCP server that lets Claude Code consult stronger AI models (o3, Gemini 2.5 Pro, DeepSeek Reasoner) when you need deeper analysis on complex problems.

Features

  • Query powerful AI models (o3, Gemini 2.5 Pro, DeepSeek Reasoner) with file context
  • Direct prompt support for simple questions or automatic prompt construction from markdown and code files
  • Git diff to feed code changes
  • Usage tracking with cost estimation
  • Comprehensive logging

Configuration

  • OPENAI_API_KEY - Your OpenAI API key (required for o3)
  • GEMINI_API_KEY - Your Google AI API key (required for Gemini models)
  • DEEPSEEK_API_KEY - Your DeepSeek API key (required for DeepSeek models)
  • CONSULT_LLM_DEFAULT_MODEL - Override the default model (optional)
    • Options: o3 (default), gemini-2.5-pro, deepseek-reasoner

Usage with Claude Code

Installation

Add the MCP server to Claude Code:

claude mcp add consult-llm -- npx -y consult-llm-mcp

Or for global availability:

claude mcp add --scope user consult-llm -- npx -y consult-llm-mcp

Optionally you can provide environment variables directly in the MCP configuration:

claude mcp add \
  -e OPENAI_API_KEY=your_openai_key \
  -e GEMINI_API_KEY=your_gemini_key \
  -e DEEPSEEK_API_KEY=your_deepseek_key \
    consult-llm -- npx -y consult-llm-mcp

Example workflows

Click to expand.

Explain the problem, and tell CC to consult a smarter LLM 

  <Some long explanation of the issue here>

Consult LLM for assistance, use gemini

⏺ I see the issue! The problem is that the frontend is trying to use the hint
for "isn't" but the server generated a hint for "isn't it" (the full phrase).
This is a mismatch between how the frontend segments text and how the server
generates hints.

Let me consult the LLM to get assistance on this segmentation mismatch issue.

⏺ Write(hint-segmentation-issue.md) ⎿  Wrote 53 lines to
hint-segmentation-issue.md # Hint Segmentation Mismatch Issue ## Problem
Description There's a mismatch between how the frontend segments text for
clickable words and how the backend generates hints. This causes hint unlocking
to fail when the segments don't match exactly. ## Example Case **Original
Text**: "Hello! Nice weather, isn't it?" … +43 lines (ctrl+r to expand)

⏺ consult-llm:consult_llm (MCP)(model: "gemini-2.5-pro", files: ["/project/hint
-segmentation-issue.md","/project/web/src/compo
nents/HintsText.tsx","/project/web/src/utils/hi
nts.ts","/project/server/src/routes/public/hint
s.ts","/project/server/src/llm/hints.ts"]) ⎿ An excellent analysis of the
problem. The root cause has been correctly identified: a race condition within
the `handleConfirmGenerateHints` function in `HintsText.tsx`. The component
state updates in the background after `await generateHints()`, but the function
continues executing with a stale `activeSegment` variable, causing it to request
a hint for a smaller text segment ( e.g., "isn't") instead of the full,
newly-available hint phrase (e.g., "isn't it"). … +607 lines (ctrl+r to expand)

⏺ Perfect! The LLM identified the core issue - there's a race condition in
handleConfirmGenerateHints where the function uses stale state after async
operations. The solution is to re-target the hint key after generation to find
the correct matching hint.

Let me implement this solution:

⏺ Update Todos ⎿  ☐ Fix hint segmentation mismatch by implementing smarter hint
key targeting in handleConfirmGenerateHints

MCP Tool: consult_llm

The server provides a single tool called consult_llm for asking powerful AI models complex questions.

Parameters

  • files (optional): Array of file paths to process

    • Markdown files (.md) become the main prompt
    • Other files are added as context with file paths and code blocks

  • prompt (optional): Direct prompt text for simple questions

    • Alternative to using markdown files
    • Either files or prompt must be provided

  • model (optional): LLM model to use

    • Options: o3 (default), gemini-2.5-pro, deepseek-reasoner

  • git_diff (optional): Include git diff output as context

    • files (required): Specific files to include in diff
    • repo_path (optional): Path to git repository (defaults to current directory)
    • base_ref (optional): Git reference to compare against (defaults to HEAD)

Example Usage

With files:

{
  "files": ["src/auth.ts", "src/middleware.ts", "review.md"],
  "model": "o3",
  "git_diff": {
    "files": ["src/auth.ts", "src/middleware.ts"],
    "base_ref": "main"
  }
}

With direct prompt:

{
  "prompt": "Analyze the performance implications of using async/await vs Promise.then() in Node.js",
  "files": ["src/database.ts"],
  "model": "gemini-2.5-pro"
}

Supported Models

  • o3: OpenAI's reasoning model ($2/$8 per million tokens)
  • gemini-2.5-pro: Google's Gemini 2.5 Pro ($1.25/$10 per million tokens)
  • deepseek-reasoner: DeepSeek's reasoning model ($0.55/$2.19 per million tokens)

Logging

All prompts and responses are logged to ~/.consult-llm-mcp/logs/mcp.log with:

  • Tool call parameters
  • Full prompts and responses
  • Token usage and cost estimates
Example 
[2025-06-22T20:16:04.673Z] TOOL CALL: consult_llm
Arguments: {
  "files": [
    "refactor-analysis.md",
    "src/main.ts",
    "src/schema.ts",
    "src/config.ts",
    "src/llm.ts",
    "src/llm-cost.ts"
  ],
  "model": "deepseek-reasoner"
}
================================================================================
[2025-06-22T20:16:04.675Z] PROMPT (model: deepseek-reasoner):
## Relevant Files

### File: src/main.ts

...

Please provide specific suggestions for refactoring with example code structure
where helpful.
================================================================================
[2025-06-22T20:19:20.632Z] RESPONSE (model: deepseek-reasoner):
Based on the analysis, here are the key refactoring suggestions to improve
separation of concerns and maintainability:

...

This refactoring maintains all existing functionality while significantly
improving maintainability and separation of concerns. The new structure makes
it easier to add features like new LLM providers, additional context sources,
or alternative prompt formats.

Tokens: 3440 input, 5880 output | Cost: $0.014769 (input: $0.001892, output: $0.012877)

CLAUDE.md example

While not strictly necessary, to help Claude Code understand when and how to use this tool, you can optionally something like the following to your project's CLAUDE.md file:

## consult-llm-mcp

Use the `consult_llm` MCP tool to ask a more powerful AI for help with complex
problems. Include files to git_diff when asking feedback for changes.

Use Gemini 2.5 Pro.

Claude Code seems to know pretty well when to use this MCP even without this instruction however.

Be the First to Experience MCP Now