consult7

Consult7is a Model Context Protocol (MCP) server that enables AI agents to consult large context window models viaOpenRouterfor analyzing extensive file collections - entire codebases, document repositories, or mixed content that exceed the current agent's context limits.

- Files:["/Users/john/project/src/.py", "/Users/john/project/lib/.py"]
- Query:"Summarize the architecture and main components of this Python project"
- Model:"google/gemini-3-flash-preview"
- Mode:"fast"

- Files:["/Users/john/webapp/src/.py", "/Users/john/webapp/auth/.py", "/Users/john/webapp/api/.js"]
- Query:"Analyze the authentication flow across this codebase. Think step by step about security vulnerabilities and suggest improvements"
- Model:"anthropic/claude-opus-4.8"
- Mode:"think"

- Files:["/Users/john/project/src/.py", "/Users/john/project/tests/.py"]
- Query:"Generate a comprehensive code review report with architecture analysis, code quality assessment, and improvement recommendations"
- Model:"google/gemini-2.5-pro"
- Mode:"think"
- Output File:"/Users/john/reports/code_review.md"
- Result:Returns"Result has been saved to /Users/john/reports/code_review.md"instead of flooding the agent's context

claude mcp add -s user consult7 uvx -- consult7 your-openrouter-api-key

{ "mcpServers": { "consult7": { "type": "stdio", "command": "uvx", "args": ["consult7", "your-openrouter-api-key"] } } }

- Absolute paths only:/Users/john/project/src/.py
- Wildcards in filenames only:/Users/john/project/.py(not in directory paths)
- Extension required with wildcards:.pynot
- Mix files and patterns:["/path/src/.py", "/path/README.md", "/path/tests/_test.py"]

- All Python files:/path/to/dir/.py
- Test files:/path/to/tests/_test.pyor/path/to/tests/test_.py
- Multiple extensions:["/path/.js", "/path/.ts"]

Automatically ignored:__pycache__,.env,secrets.py,.DS_Store,.git,node_modules

Size limits:Dynamic based on model context window (e.g., Grok 4.20: ~8MB, GPT-5.6 Sol: ~4MB)

The consultation tool accepts the following parameters:

- files(required): List of absolute file paths or patterns with wildcards in filenames only
- query(required): Your question or instruction for the LLM to process the files
- model(required): The LLM model to use (see Supported Models above)
- mode(required): Performance mode -fast,mid, orthink
- output_file(optional): Absolute path to save the response to a file instead of returning it

- If the file exists, it will be saved with_updatedsuffix (e.g.,report.md→report_updated.md)
- When specified, returns only:"Result has been saved to /path/to/file"
- Useful for generating reports, documentation, or analyses without flooding the agent's context

- Whentrue, routes only to endpoints with ZDR policy (prompts not retained by provider)
- ZDR available: Gemini 3.1 Pro/Flash, Claude Opus 4.8, GPT-5, GPT-5.5
- Not available: GPT-5.6 Sol, Grok 4.20, Claude Fable 5 (returns error)

Claude Code will automatically use the tool with proper parameters:

{ "files": ["/Users/john/project/src/*.py"], "query": "Explain the main architecture", "model": "google/gemini-3-flash-preview", "mode": "fast" }

from consult7.consultation import consultation_impl result = await consultation_impl( files=["/path/to/file.py"], query="Explain this code", model="google/gemini-3-flash-preview", mode="fast", # fast, mid, or think provider="openrouter", api_key="sk-or-v1-..." )

# Test OpenRouter connection uvx consult7 sk-or-v1-your-api-key --test

- New default GPT: GPT-5.6 Sol(openai/gpt-5.6-sol) — the latest top-tier GPT, ~1M context / 128K output, effort-based reasoning (mid→effort=medium,think→effort=high). Replaces GPT-5.5 as thegpttdefault; GPT-5.5 stays available as a legacy model. ZDR isnotsupported on GPT-5.6 Sol (GPT-5.5 still is).
- Grok 4.5 not added:x-ai/grok-4.5is region-restricted on OpenRouter (returns a 403 "not available in your region") and could not be verified against the real API, so it was not integrated. Grok 4.20 remains thegrotdefault.

- Added Claude Fable 5(anthropic/claude-fable-5) — Anthropic's most capable model, 1M context. Premium price (~2× Opus 4.8), so it'sreserved for specifically hard problemsand isnotpart of theULTRApanel; it does not replace Opus 4.8 as the default Claude model. New mnemonicsfabt(think) /fabm(mid). Unlike Opus 4.8 (adaptive thinking only), OpenRouter honors Fable's effort scale, somid/thinkmap toeffort=high/effort=xhigh(maxintentionally not exposed — it tends to overthink at ~2× token cost). ZDR not supported (Fable requires 30-day retention).
- Response-length prompt tuned:the system prompt now asks the model to match answer length to the task (thorough when the question needs depth, concise otherwise) instead of a blunt "be concise".

- Surface mid-stream API errors: when OpenRouter sends an error as a streaming data chunk (after the initial 200), the call now returns that error message instead of a misleading "No content received".

- AddedFusion(openrouter/fusion) — a multi-model panel plus a judge in one call;modemaps to web-research depth (fast/mid/think→max_tool_calls2/8/16). NewFUSEmnemonic.
- Upgraded Claude Opus 4.7 →4.8(1M context, adaptive thinking);oput/opufnow point to 4.8, and 4.7 is kept as a legacy ID.
- The response footer now reports thecall cost in USD(from OpenRouter usage accounting), e.g.cost: $0.0923.

- Toggle-reasoning footer now distinguishesmidvsthinkfor adaptive models (Opus, Grok)
- Friendlier error message when a model has no Zero Data Retention endpoint
- output_filereturn now includes the metadata footer so callers can verify what ran

- Upgraded models: GPT-5.5, Claude Opus 4.7, Grok 4.20
- Claude Opus 4.7 (1M context) uses adaptive thinking —reasoning.enabled=true
- Grok 4.20 (2M context) uses automatic reasoning —reasoning.enabled=true
- Updated mnemonics:gptt→ GPT-5.5,oput/opuf→ Claude Opus 4.7,grot→ Grok 4.20
- Legacy model IDs still supported

- Upgraded GPT-5.2 → GPT-5.4 (~1M context)

- Upgraded models: Gemini 3.1 Pro, Claude Opus 4.6, Claude Sonnet 4.6, Grok 4.1 Fast
- Added new models: Claude Haiku 4.5, Gemini 3.1 Flash Lite
- Updated mnemonics:gemt→ Gemini 3.1 Pro,oput/opuf→ Claude Opus 4.6
- Legacy model IDs still supported

- Fixed GPT-5.2 thinking mode truncation issue (switched to streaming)
- Addedgoogle/gemini-3-flash-preview(Gemini 3 Flash, ultra fast)
- Updatedgemfmnemonic to use Gemini 3 Flash
- Addedzdrparameter for Zero Data Retention routing

- Updated to GPT-5.2 with effort-based reasoning

- Addedgoogle/gemini-3-pro-preview(1M context, flagship reasoning model)
- New mnemonics:gemt(Gemini 3 Pro),grot(Grok 4),ULTRA(parallel execution)

- Removed Google and OpenAI direct providers - now OpenRouter only
- Removed|thinkingsuffix - usemodeparameter instead (now required)
- Cleanmodeparameter API:fast,mid,think
- Simplified CLI fromconsult7 <provider> <key>toconsult7 <key>
- Better MCP integration with enum validation for modes
- Dynamic file size limits based on model context window

- Addedoutput_fileparameter to save responses to files

- New file list interface with simplified validation
- Reduced file size limits to realistic values

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

A Model Context Protocol (MCP) server that enables AI assistants to integrate with Prometheus Alertmanager

A comprehensive MCP server for tooling interactions(40+) and resource accessibility(60+) plus many useful prompts to interact with Algorand Blockchain.

An MCP server that provides control over Android devices through ADB. Offers device screenshot capture, UI layout analysis, package management, and ADB command execution capabilities.

A Binary Ninja plugin, MCP server, and bridge that seamlessly integrates Binary Ninja with your favorite MCP client.

integration that connects BloodHound with AI through MCP, allowing security professionals to analyze Active Directory attack paths using natural language queries instead of Cypher.

A specialized MCP gateway for LLM enhancement prompts and jailbreaks with dynamic schema adaptation. Provides prompts for different LLMs using an enum-based approach.

Obtains latest dependency details for Clojure libraries.

A Model Context Protocol (MCP) server for CODESYS V3 programming environments.

MCP Server that exposes Creatify AI API capabilities for AI video generation, including avatar videos, URL-to-video conversion, text-to-speech, and AI-powered editing tools.