Consult7
Enables AI agents to analyze large codebases and document collections by consulting large context window models (up to 2M tokens) via OpenRouter when files exceed the current agent's context limits.
What is Consult7?
Consult7 is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai agents to analyze large codebases and document collections by consulting large context window models (up to 2m tokens) via openrouter when files exceed the current agent's context limits.
Enables AI agents to analyze large codebases and document collections by consulting large context window models (up to 2M tokens) via OpenRouter when files exceed the current agent's context limits.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables AI agents to analyze large codebases and document co
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx consult7Configuration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Consult7
Consult7 is an MCP server that lets AI agents delegate analysis tasks to large-context-window models (up to 2 million tokens) via OpenRouter when the files being examined exceed the current agent's own context limit. You point it at files or glob patterns, provide a query, choose a model and reasoning mode, and Consult7 loads everything into a single large-context call—returning a comprehensive answer your primary agent can then act on. It is particularly valuable for analyzing entire codebases, multi-document research collections, or any corpus that would otherwise require chunking and lose cross-file coherence.
Prerequisites
- Python 3.10 or later with uv or uvx available (pip install uv)
- An OpenRouter API key (sign up at https://openrouter.ai, key format: sk-or-v1-...)
- An MCP-compatible client such as Claude Desktop or Claude Code
- Sufficient OpenRouter credits for the large-context models you intend to use
Install Consult7 via Claude Code
The easiest install for Claude Code users passes the OpenRouter API key directly as a CLI argument to uvx.
claude mcp add -s user consult7 uvx -- consult7 YOUR_OPENROUTER_API_KEYOr add it manually to Claude Desktop config
For Claude Desktop, add the mcpServers entry to claude_desktop_config.json, passing your OpenRouter key as an argument.
{
"mcpServers": {
"consult7": {
"type": "stdio",
"command": "uvx",
"args": ["consult7", "sk-or-v1-YOUR_KEY_HERE"]
}
}
}Verify the connection
Run with the --test flag to confirm your OpenRouter key is valid and the API is reachable before using it in a workflow.
uvx consult7 sk-or-v1-YOUR_KEY_HERE --testUse the consult tool from your AI agent
Invoke Consult7 from Claude by specifying absolute file paths (with wildcards in filenames only), a query, a model identifier, and a reasoning mode (fast, mid, or think).
Save large outputs to a file
For very large analyses, use the output_file parameter to write the response to disk instead of returning it inline, which avoids overflowing your primary agent's context.
Consult7 Examples
Client configuration
Claude Desktop mcpServers entry for Consult7 using uvx.
{
"mcpServers": {
"consult7": {
"type": "stdio",
"command": "uvx",
"args": ["consult7", "sk-or-v1-YOUR_OPENROUTER_KEY"]
}
}
}Prompts to try
Prompts that delegate large-context analysis to Consult7 via the consult tool.
- "Use Consult7 with google/gemini-2.5-flash in fast mode to summarise the architecture of all Python files in /Users/me/myproject/src/*.py"
- "Use Consult7 with google/gemini-2.5-pro in think mode to generate a comprehensive code review for /project/src/*.py and /project/tests/*.py, saving the result to /tmp/review.md"
- "Use Consult7 to compare all markdown files in /docs/*.md and identify any contradictory information across the documentation."
- "Use Consult7 with claude-opus-4 to find all security vulnerabilities in /app/api/*.py and rank them by severity."Troubleshooting Consult7
Authentication error or 401 from OpenRouter
Double-check that your key starts with 'sk-or-v1-' and has not expired. Run 'uvx consult7 YOUR_KEY --test' to get a clear error message. Keys are managed at https://openrouter.ai/keys.
File paths are not found or return no content
Consult7 requires absolute paths. Wildcards are only supported in the filename part, not in directory segments. Use patterns like /home/user/project/src/*.py, not /home/user/*/src/file.py.
Response is truncated or the model refuses the request
Switch to a model with a larger context window (e.g. a 2M-token Grok model for very large repos) or use output_file to write results to disk. The 'think' mode uses more tokens—try 'fast' or 'mid' first to validate your query.
Frequently Asked Questions about Consult7
What is Consult7?
Consult7 is a Model Context Protocol (MCP) server that enables ai agents to analyze large codebases and document collections by consulting large context window models (up to 2m tokens) via openrouter when files exceed the current agent's context limits. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Consult7?
Follow the installation instructions on the Consult7 GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Consult7?
Consult7 works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Consult7 free to use?
Yes, Consult7 is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Consult7 Alternatives — Similar Coding Agents Servers
Looking for alternatives to Consult7? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Consult7 in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Consult7?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.