Consult LLM MCP

An MCP server that lets Claude Code consult stronger AI models (o3, Gemini 2.5 Pro, DeepSeek Reasoner, GPT-5.1 Codex) when Sonnet has you running in circles and you need to bring in the heavy artillery.

> Still getting this error after your fix. Ask gemini
  E5108: Error executing lua: attempt to call method 'child' (a nil value)

⏺ Let me consult Gemini to understand the Neovim treesitter API changes:

⏺ consult-llm:consult_llm (MCP)(prompt: "Neovim plugin broken due to treesitter
                                API changes...", files: ["lua/testonly.lua"],
                                model: "gemini-2.5-pro")
  ⎿ The issue is that iter_matches() can return nil nodes in newer Neovim
    versions. Switch to iter_captures() which never returns nil nodes, and use
    named_child(0) instead of child(0) to get only meaningful syntax nodes.
    … +93 lines (ctrl+r to expand)

⏺ The LLM identified the issue - iter_matches() API changed. Switching to
  iter_captures() approach now.

Features

• Query powerful AI models (o3, Gemini 2.5 Pro, Gemini 3 Pro Preview, DeepSeek Reasoner, GPT-5.1 Codex) with relevant files as context
• Direct queries with optional file context
• Include git changes for code review and analysis
• Comprehensive logging with cost estimation
• Gemini CLI mode: Use the gemini CLI to take advantage of free quota
• Codex CLI mode: Use the codex CLI for OpenAI models
• Web mode: Copy formatted prompts to clipboard for browser-based LLM services
• Simple: provides just one MCP tool to not clutter the context

Quick start

1. Add to Claude Code:

   claude mcp add consult-llm -e GEMINI_API_KEY=your_key -- npx -y consult-llm-mcp

   For global availability across projects, add --scope user.

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

2. Verify connection with /mcp:

   ❯ 1. consult-llm            ✔ connected

3. Ask a question:

   "Consult Gemini about how to fix the race condition in server.ts"

Example workflows

Some real-world examples. Click to expand.

  <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

> I need help implementing a -b/--background flag for my Rust CLI. Use consult LLM with web mode

⏺ I'll use web mode to copy the formatted prompt to your clipboard so you can
  paste it into any browser-based LLM service.

⏺ consult-llm:consult_llm (MCP)(prompt: "What is the best approach to implement a
                                 -b/--background flag for the \"workmux add\" command that
                                 creates a tmux window in the background without switching to
                                 it?\n\nThe current implementation automatically switches to
                                 the newly created window via `tmux::select_window()` in the
                                 `setup_environment()` function. I need to make this behavior
                                 conditional based on a flag passed from the
                                 CLI.\n\nConsider:\n1. Where should the background flag be
                                 threaded through the call chain?\n2. Should I modify the
                                 existing SetupOptions struct or add a parameter?\n3. What's
                                 the most maintainable approach given the codebase
                                 structure?\n4. Are there any edge cases to consider (e.g.,
                                 should select_pane also be conditional)?", files:
                                 ["src/cli.rs","src/workflow.rs","src/tmux.rs"], web_mode:
                                 true)
  ⎿  ✓ Prompt copied to clipboard!

     Please paste it into your browser-based LLM service and share the response
     here before I proceed with any implementation.

     Note: File paths were included:
       - src/cli.rs
       - src/workflow.rs
       - src/tmux.rs

> [User pastes the response from the external LLM]

⏺ Thank you! Based on the recommendations, I'll now implement the solution...

This is useful when:

• You want to use a free browser-based LLM service instead of API credits
• You prefer a specific LLM's web interface
• You want to review the full prompt before submitting it

⏺ Fixed! Added nil checks for both node and child and updated the iter_matches call to handle the newer API properly.

> Still not working:

  E5108: Error executing lua /Users/raine/code/testonly.nvim/lua/testonly.lua:92: attempt to call method 'child' (a nil value)
  stack traceback:
          /Users/raine/code/testonly.nvim/lua/testonly.lua:92: in function 'reset_all_exclusive'
          /Users/raine/code/testonly.nvim/lua/testonly.lua:110: in function 'reset_all_exclusive'
          [string ":lua"]:1: in main chunk

  Ask gemini

⏺ Let me consult with a more powerful AI to understand the current Neovim treesitter API changes:

⏺ consult-llm:consult_llm (MCP)(prompt: "I'm debugging a Neovim plugin that's broken due to treesitter API changes. The error is \"attempt to call method 'child' (a nil value)\" on line 92. The
                               code is trying to access child nodes from treesitter matches but the API seems to have changed in newer Neovim versions.\n\nHere's the problematic
                               code:\n```lua\nfor _, match, _ in parsed_query:iter_matches(root, bufnr, start_row, end_row) do\n    for id, node in pairs(match) do\n        local name =
                               parsed_query.captures[id]\n        if name == \"call\" and node then\n            local child = node:child(0)  -- ERROR HERE\n            if child then\n
                                    local text = vim.treesitter.get_node_text(child, bufnr)\n                -- ... rest of logic\n            end\n        end\n    end\nend\n```\n\nWhat's the
                               correct way to iterate over treesitter query matches and access child nodes in current Neovim versions? What API changes should I be aware of?", files:
                               ["/Users/raine/code/testonly.nvim/lua/testonly.lua"])
  ⎿  Problem
     -------

     … +93 lines (ctrl+r to expand)

⏺ Perfect! The issue is that iter_matches() can return nil nodes in the match table. Let me fix this by switching to the recommended iter_captures() approach:

⏺ Update(lua/testonly.lua)
  ⎿  Updated lua/testonly.lua with 7 additions and 10 removals
       85      local root = parser:parse()[1]:root()
       86      local start_row, _, end_row, _ = root:range()
       87
       88 -    for _, match, _ in parsed_query:iter_matches(root, bufnr, start_row, end_row) do
       89 -      for id, node in pairs(match) do
       90 -        local name = parsed_query.captures[id]
       91 -        if name == "call" and node then
       92 -          local child = node:child(0)
       93 -          if child then
       94 -            local text = vim.treesitter.get_node_text(child, bufnr)
       88 +    for id, node, _ in parsed_query:iter_captures(root, bufnr, start_row, end_row) do
       89 +      if parsed_query.captures[id] == "call" then
       90 +        local first_child = node:named_child(0)
       91 +        if first_child then
       92 +          local text = vim.treesitter.get_node_text(first_child, bufnr)
       93
       94 -            if text == "it.only" or text == "describe.only" then
       95 -              toggle_test_exclusive(child)
       96 -            end
       94 +          if text == "it.only" or text == "describe.only" then
       95 +            toggle_test_exclusive(first_child)
       96            end
       97          end
       98        end

⏺ Fixed! The key changes:

  1. Switched from iter_matches() to iter_captures() which never returns nil nodes
  2. Used named_child(0) instead of child(0) to get only meaningful syntax nodes (not punctuation)
  3. Simplified the iteration logic since iter_captures() directly gives us the node and capture ID

  Your <leader>tr mapping should now work properly with the current Neovim treesitter API.

> /consult The branch completions should dynamic. Git should be called only when
using tab to autocomplete. Ask gemini and codex

⏺ I'll consult both Gemini and Codex about making the branch completions dynamic (only
  calling git when tab-completing). Let me gather the relevant context first.

⏺ consult-llm - consult_llm (MCP)(prompt: "I have a Rust CLI tool using clap that needs dynamic shell completions. Currently, the branch completions are generated at completion script
                                 generation time via `possible_values()`. Instead, I need the git operations to only run when the user presses TAB to autocomplete.\n\nCurrent setup:\n1.
                                 `WorktreeBranchParser` implements `TypedValueParser` with `possible_values()` that calls git\n2. Shell completions are generated via clap_complete's
                                 `generate()` function\n3. The completions are sourced at shell startup: `source <(workmux completions zsh)`\n\nThe problem: Running `workmux completions
                                 zsh` takes ~210ms because it runs git operations during completion generation, not during actual tab completion.\n\nHow can I implement truly dynamic
                                 completions where git is only called when the user presses TAB? What's the best approach with clap and clap_complete for zsh?", model:
                                 "gemini-3-pro-preview", files: ["/Users/raine/code/workmux/src/cli.rs","/Users/raine/code/workmux/src/git.rs"], web_mode: false)
  ⎿ The root cause of the slow startup (~210ms) is that `clap_complete::generate()` executes your `possible_values()` logic (git operations) *while generating the script*. This bake
    s the *current* branches into the static script, which is both slow (happens every time you `source` it) and incorrect (branches become stale).
    … +116 lines (ctrl+o to expand)


⏺ consult-llm - consult_llm (MCP)(prompt: "I have a Rust CLI tool using clap that needs dynamic shell completions. Currently, the branch completions are generated at completion script
                                 generation time via `possible_values()`. Instead, I need the git operations to only run when the user presses TAB to autocomplete.\n\nCurrent setup:\n1.
                                 `WorktreeBranchParser` implements `TypedValueParser` with `possible_values()` that calls git\n2. Shell completions are generated via clap_complete's
                                 `generate()` function\n3. The completions are sourced at shell startup: `source <(workmux completions zsh)`\n\nThe problem: Running `workmux completions
                                 zsh` takes ~210ms because it runs git operations during completion generation, not during actual tab completion.\n\nHow can I implement truly dynamic
                                 completions where git is only called when the user presses TAB? What's the best approach with clap and clap_complete for zsh?", model:
                                 "gpt-5.1-codex-max", files: ["/Users/raine/code/workmux/src/cli.rs","/Users/raine/code/workmux/src/git.rs"], web_mode: false)
  ⎿ **Findings**
    - `WorktreeBranchParser::possible_values` (`cli.rs:41-72`) runs git during script generation, so `workmux completions zsh` always pays the git cost (~210ms) even though the resu
    lt is only needed at tab time.
    … +77 lines (ctrl+o to expand)


⏺ Summary from Gemini and Codex

  Both agree on the same solution:

  Root Cause

  clap_complete::generate() calls possible_values() during script generation, not at tab-completion time. This means git runs every shell startup.

...

This example shows using the /consult slash command to ask multiple LLMs (Gemini and Codex) about the same problem in parallel and compare their responses. Both LLMs independently arrived at the same solution, providing confidence in the approach.

Modes

consult-llm-mcp supports three modes of operation:

| Mode | Description | When to use | | ------- | ----------------------------- | ---------------------------------------------------------------- | | API | Queries LLM APIs directly | You have API keys and want the simplest setup | | CLI | Shells out to local CLI tools | Free quota (Gemini), existing subscriptions, or prefer CLI tools | | Web | Copies prompt to clipboard | You prefer browser UIs or want to review prompts |

API mode (default)

The default mode. Requires API keys configured via environment variables. See Configuration for details.

CLI mode

Instead of making API calls, shell out to local CLI tools. The CLI agents can explore the codebase themselves, so you don't need to pass all relevant files as context, but it helps.

Gemini CLI

Use Gemini's local CLI to take advantage of Google's free quota.

Requirements:

1. Install the Gemini CLI
2. Authenticate via gemini login

Setup:

claude mcp add consult-llm -e GEMINI_MODE=cli -- npx -y consult-llm-mcp

Codex CLI

Use OpenAI's Codex CLI for OpenAI models.

Requirements:

1. Install the Codex CLI
2. Authenticate via codex login

Setup:

claude mcp add consult-llm -e OPENAI_MODE=cli -- npx -y consult-llm-mcp

[!TIP] Set reasoning effort with -e CODEX_REASONING_EFFORT=high. Options: none, minimal, low, medium, high, xhigh (gpt-5.1-codex-max only).

Web mode

Copies the formatted prompt to clipboard instead of querying an LLM. Paste into any browser-based LLM (ChatGPT, Claude.ai, Gemini, etc.).

When to use: Prefer a specific web UI, want to review the prompt first, or don't have API keys.

Workflow:

1. Ask Claude to "use consult LLM with web mode"
2. Paste into your browser-based LLM
3. Paste the response back into Claude Code

See the "Using web mode..." example above for a concrete transcript.

Configuration

Environment variables

• OPENAI_API_KEY - Your OpenAI API key (required for OpenAI models in API mode)
• GEMINI_API_KEY - Your Google AI API key (required for Gemini models in API mode)
• 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, gemini-3-pro-preview, deepseek-reasoner, gpt-5.1-codex-max, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1
• GEMINI_MODE - Choose between API or CLI mode for Gemini models (optional)
  • Options: api (default), cli
  • CLI mode uses the system-installed gemini CLI tool
• OPENAI_MODE - Choose between API or CLI mode for OpenAI models (optional)
  • Options: api (default), cli
  • CLI mode uses the system-installed codex CLI tool
• CODEX_REASONING_EFFORT - Configure reasoning effort for Codex CLI (optional)
  • See Codex CLI for details and available options

Custom system prompt

You can customize the system prompt used when consulting LLMs by creating a SYSTEM_PROMPT.md file in ~/.consult-llm-mcp/:

npx consult-llm-mcp init-prompt

This creates a placeholder file with the default system prompt that you can edit to customize how the consultant LLM behaves. The custom prompt is read on every request, so changes take effect immediately without restarting the server.

To revert to the default prompt, simply delete the SYSTEM_PROMPT.md file.

MCP tool: consult_llm

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

Parameters

• prompt (required): Your question or request for the consultant LLM

• files (optional): Array of file paths to include as context

  • All files are added as context with file paths and code blocks

• model (optional): LLM model to use

  • Options: o3 (default), gemini-2.5-pro, gemini-3-pro-preview, deepseek-reasoner, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1

• web_mode (optional): Copy prompt to clipboard instead of querying LLM

  • Default: false
  • When true, the formatted prompt (including system prompt and file contents) is copied to clipboard for manual pasting into browser-based LLM services

• 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)

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)
• gemini-3-pro-preview: Google's Gemini 3 Pro Preview ($2/$12 per million tokens for prompts ≤200k tokens, $4/$18 for prompts >200k tokens)
• deepseek-reasoner: DeepSeek's reasoning model ($0.55/$2.19 per million tokens)
• gpt-5.1-codex: OpenAI's Codex model optimized for coding
• gpt-5.1-codex-mini: Lighter, faster version of gpt-5.1-codex
• gpt-5.1: Broad world knowledge with strong general reasoning

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

[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)

Activation methods

1. No custom activation (simplest)

When you add an MCP to Claude Code, the tool's schema is injected into the agent's context. This allows Claude to infer when to call the MCP from natural language (e.g., "ask gemini about..."). Works out of the box, but you have less control over how the MCP is invoked.

2. Slash commands (most reliable)

Explicitly invoke with /consult ask gemini about X. Guaranteed activation with full control over custom instructions, but requires the explicit syntax. For example, you can instruct Claude to always find related files and pass them as context via the files parameter. See the example slash command below.

3. Skills

Automatically triggers when Claude detects matching intent. Like slash commands, supports custom instructions (e.g., always gathering relevant files), but not always reliably triggered. See the example skill below.

Recommendation: Start with no custom activation. Use slash commands if you need reliability or custom instructions.

Example skill

Here's an example Claude Code skill that uses the consult_llm MCP tool to create commands like "ask gemini" or "ask codex". See examples/SKILL.md for the full content.

Save it as ~/.claude/skills/consult-llm/SKILL.md and you can then use it by typing "ask gemini about X" or "ask codex about X" in Claude Code.

This one is not strictly necessary either, Claude (or other agent) can infer from the schema that "Ask gemini" should call this MCP, but it might be helpful in case you want to have more precise control over how the agent calls this MCP.

Example slash command

Here's an example Claude Code slash command that uses the consult_llm MCP tool. See examples/consult.md for the full content.

Save it as ~/.claude/commands/consult.md and you can then use it by typing /consult ask gemini about X or /consult ask codex about X in Claude Code.

Development

To work on the MCP server locally and use your development version:

1. Clone the repository and install dependencies:

   git clone https://github.com/yourusername/consult-llm-mcp.git
   cd consult-llm-mcp
   npm install

2. Build the project:

   npm run build

3. Install globally from the local directory:

   npm link

4. Add the MCP server to Claude Code using the global command:

   claude mcp add consult-llm -- consult-llm-mcp

Now when you make changes:

1. Rebuild: npm run build
2. Restart Claude Code to pick up the changes

Alternatively, you can use the dev script for development without building:

claude mcp add consult-llm -- npm run dev

This runs the TypeScript source directly with tsx, allowing faster iteration without rebuilding.

To unlink the global version later:

npm unlink -g

Related projects

• workmux — Git worktrees + tmux windows for parallel AI agent workflows
• claude-history — Search and view Claude Code conversation history with fzf
• tmux-file-picker — Pop up fzf in tmux to quickly insert file paths, perfect for AI coding assistants