Agent Skills

consult7

agentsszeider296 stars

MCP server to consult a language model with large context size

Install

uvx consult7
README.md

Consult7 MCP Server

Consult7 is a Model Context Protocol (MCP) server that enables AI agents to consult large context window models via OpenRouter for analyzing extensive file collections - entire codebases, document repositories, or mixed content that exceed the current agent's context limits.

Why Consult7?

Consult7 enables any MCP-compatible agent to offload file analysis to large context models (up to 2M tokens). Useful when:

  • Agent's current context is full
  • Task requires specialized model capabilities
  • Need to analyze large codebases in a single query
  • Want to compare results from different models

"For Claude Code users, Consult7 is a game changer."

How it works

Consult7 collects files from the specific paths you provide (with optional wildcards in filenames), assembles them into a single context, and sends them to a large context window model along with your query. The result is directly fed back to the agent you are working with.

Example Use Cases

Quick codebase summary

  • 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"

Deep analysis with reasoning

  • 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"

Generate a report saved to file

  • 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-3.1-pro-preview"
  • Mode: "think"
  • Output File: "/Users/john/reports/code_review.md"
  • Result: Returns "Result has been saved to /Users/john/reports/code_review.md" plus a one-line metadata footer, instead of flooding the agent's context

Featured: Gemini 3.1 Models

Consult7 supports Google's Gemini 3.1 family:

  • Gemini 3.1 Pro (google/gemini-3.1-pro-preview) - Flagship reasoning model, 1M context
  • Gemini 3 Flash (google/gemini-3-flash-preview) - Ultra-fast model, 1M context
  • Gemini 3.1 Flash Lite (google/gemini-3.1-flash-lite-preview) - Ultra-fast lite model, 1M context

Quick mnemonics for power users:

  • gemt = Gemini 3.1 Pro + think (flagship reasoning)
  • gemf = Gemini 3 Flash + fast (ultra fast)
  • gptt = GPT-6 Astra + think (latest GPT, effort xhigh)
  • grot = Grok 4.7 + think (effort xhigh)
  • oput = Claude Opus 4.8 + think (adaptive thinking)
  • fabt = Claude Fable 5.1 + think (deepest reasoning, effort xhigh; premium)
  • ULTRA = Run GPTT, GROT, and FABT in parallel (3 frontier models)
  • FUSE = Fusion: a frontier panel deliberates and a judge synthesizes, in one call

These mnemonics make it easy to reference model+mode combinations in your queries.

Note on Fable 5.1. anthropic/claude-fable-5.1 is Anthropic's most capable model but priced at a premium (~2× Opus 4.8). It does not replace Opus 4.8 as the everyday Claude choice for single calls. Since v3.11.0 it holds the Anthropic seat in the ULTRA panel (which is meant for hard questions anyway). Unlike Opus 4.8 (adaptive thinking only), OpenRouter honors Fable's effort scale, so mid/think map to effort=high/effort=xhigh.

Featured: Fusion (multi-model analysis)

Consult7 supports OpenRouter's Fusion (openrouter/fusion) — a single call where a panel of frontier models (Opus, GPT, Gemini Pro) answers your query in parallel and a judge model synthesizes their responses into one answer. Reach for it on hard questions where multiple perspectives help and the cost of being wrong outweighs a few extra completions.

  • Context: 128K — smaller than the 1M–2M single models, so it's best for hard questions on moderate input, not giant file bundles.
  • Mode → research depth: fast / mid / think map the panel's web-search/fetch budget to max_tool_calls of 2 / 8 / 16.
  • Mnemonic: FUSE = openrouter/fusion.

Trivial prompts answer directly (no panel); the panel fires only when the question warrants deliberation. Fusion is billed per panel run, so it costs more than a single-model call.

Installation

Claude Code

Simply run:

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

Claude Desktop

Add to your Claude Desktop configuration file:

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

Replace your-openrouter-api-key with your actual OpenRouter API key.

No installation required - uvx automatically downloads and runs consult7 in an isolated environment.

Command Line Options

uvx consult7 <api-key> [--test]
  • <api-key>: Required. Your OpenRouter API key
  • --test: Optional. Test the API connection

The model and mode are specified when calling the tool, not at startup.

Supported Models

Consult7 supports all 500+ models available on OpenRouter. Below are the flagship models with optimized dynamic file size limits:

Model Context Use Case
openai/gpt-6-astra 1M Latest top-tier GPT, effort-based reasoning; premium price
google/gemini-3.1-pro-preview 1M Flagship reasoning model
google/gemini-3-flash-preview 1M Gemini 3 Flash, ultra fast
google/gemini-3.1-flash-lite-preview 1M Ultra-fast lite model
anthropic/claude-fable-5.1 1M Most capable; premium price — reserved for hard problems
anthropic/claude-opus-4.8 1M Best quality, adaptive thinking
anthropic/claude-sonnet-4.6 1M Excellent reasoning, fast
anthropic/claude-haiku-4.5 200k Budget, very fast
x-ai/grok-4.7 500k Frontier Grok, effort-based reasoning
x-ai/grok-4.20 2M Automatic reasoning, huge context
x-ai/grok-4.1-fast 2M Largest context window
openrouter/fusion 128k Multi-model panel + judge (see Featured: Fusion)

Superseded IDs still work with their tuned settings: openai/gpt-5.6-sol, x-ai/grok-4.6, anthropic/claude-fable-5.

Quick mnemonics:

  • gptt = openai/gpt-6-astra + think (latest GPT, deep reasoning [effort xhigh]; premium)
  • gemt = google/gemini-3.1-pro-preview + think (Gemini 3.1 Pro, flagship reasoning)
  • grot = x-ai/grok-4.7 + think (Grok 4.7, deep reasoning [effort xhigh]; 500K context — use x-ai/grok-4.20 for bigger bundles)
  • oput = anthropic/claude-opus-4.8 + think (Claude Opus, adaptive thinking)
  • opuf = anthropic/claude-opus-4.8 + fast (Claude Opus, no reasoning)
  • fabt = anthropic/claude-fable-5.1 + think (Claude Fable, deepest reasoning [effort xhigh]; premium, hard problems only)
  • fabm = anthropic/claude-fable-5.1 + mid (Claude Fable, high-effort reasoning; premium)
  • gemf = google/gemini-3-flash-preview + fast (Gemini 3 Flash, ultra fast)
  • ULTRA = call GPTT, GROT, and FABT IN PARALLEL (3 frontier models for maximum insight)
  • FUSE = openrouter/fusion (one call: a frontier panel deliberates, a judge synthesizes; mode sets web-research depth)

You can use any OpenRouter model ID (e.g., deepseek/deepseek-r1-0528). See the full model list. File size limits are automatically calculated based on each model's context window.

Performance Modes

  • fast: No reasoning requested - quick answers, simple tasks. GPT-6 Astra, Grok 4.7 and Fable reason by design, so on them fast means their own default level (billed), shown in the footer as reasoning: model default
  • mid: Moderate reasoning - code reviews, bug analysis
  • think: Maximum reasoning - security audits, complex refactoring

File Specification Rules

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

Common patterns:

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

Automatically ignored: __pycache__, .env, secrets.py, .DS_Store, .git, node_modules. Wildcards skip them; naming one explicitly is an error.

Fail fast: a relative or missing path, a directory, a wildcard that matches nothing, an explicitly named ignored file, a binary file (NUL bytes in the first 8 KB), or files over the model's size budget fail the whole call before anything is sent to the model (no cost). The error lists every problem.

Size budget: one total for all files together, no per-file limit: (model context − output reserve − reasoning reserve) × ~4 bytes per token, e.g. ~4 MB for 1M-context models, ~2 MB for Grok 4.7 (500K), ~8 MB for Grok 4.20 (2M). A second check on the estimated token count keeps a 10% safety margin. A size error states the budget and the total requested.

Tool Parameters

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, or think
  • output_file (optional): Absolute path to save the response to a file instead of returning it
    • The path is checked before the model is called, so a bad path costs nothing
    • If the file exists, it will be saved with _updated suffix (e.g., report.md → report_updated.md, then report_updated_1.md, ...)
    • When specified, returns "Result has been saved to /path/to/file" plus the metadata footer
    • Useful for generating reports, documentation, or analyses without flooding the agent's context
  • zdr (optional): Enable Zero Data Retention routing (default: false)
    • When true, routes only to endpoints with ZDR policy (prompts not retained by provider)
    • ZDR available: GPT-6 Astra, Grok 4.7, Gemini 3.1 Pro/Flash, Claude Opus 4.8, GPT-5, GPT-5.5, Grok 4.6
    • Not available: Claude Fable 5.1 and 5, GPT-5.6 Sol, Grok 4.20 (returns error)

Usage Examples

Via MCP in Claude Code

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"
}

Via Python API

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-..."
)

Testing

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

Uninstalling

To remove consult7 from Claude Code:

claude mcp remove consult7 -s user

Version History

v3.11.2

  • No per-file size limit. The files share one total budget, so a single large file can use all of it (before, one file was capped at half the budget). Size errors report the total requested and the budget, and token errors mention the 10% safety margin.
  • Binary files fail fast (NUL bytes in the first 8 KB) instead of being sent as garbage tokens.
  • Unknown model IDs: when a model is not in OpenRouter's model list, errors say so, name the assumed 128K context, and suggest the closest listed IDs. Variant IDs such as model:nitro use the base model's context size.
  • Footer: wall-clock time, the mode always shown ([fast] too), zdr shown when on. Both token estimates now use the same prompt text, and a rejected fast call no longer claims reasoning disabled.

v3.11.1

  • Fail fast before any paid call. A missing file in a list, a wildcard that matches nothing, an explicitly named ignored file (.env, secrets.py, ...), or files over the model's per-file or total size limit now fail the call with a clear error before anything is sent. Before, these were reported only inside the prompt (or dropped), and the paid call went through on partial input.
  • output_file is checked before the call. A relative or unwritable path fails at no cost. If saving still fails after the call, the response is returned instead of being lost.
  • Errors set isError=true in the MCP result, so clients and wrappers can detect failures without parsing text.
  • Upstream error messages no longer include the OpenRouter account user_id.
  • Footer: 1 file (not 1 files). On fast, models that always reason (GPT-6 Astra, Grok 4.7, Fable) show reasoning: model default.
  • Shorter tool description (under 2,000 characters, file rules first). Claude Code truncated the old one before the file rules.

v3.11.0

  • New ULTRA panel: GPTT + GROT + FABT (3 models in parallel). Gemini 3.1 Pro leaves the panel (gemt and all Gemini models stay available); Opus 4.8 (oput/opuf) stays available but its ULTRA seat goes to Fable.
  • gptt → GPT-6 Astra (openai/gpt-6-astra, 1M context, $10/$50 per M) — also the model used by consult7 <key> --test. Reasoning is mandatory on Astra, so mid/think now map to effort=high/effort=xhigh (GPT-5.6 Sol used medium/high). ZDR supported.
  • grot → Grok 4.7 (x-ai/grok-4.7, 500K context; grok 4.6 had been the default since v3.10.0). Same effort mapping (high/xhigh). ZDR supported.
  • fabt/fabm → Claude Fable 5.1 (anthropic/claude-fable-5.1, 1M context). Same effort mapping. ZDR not supported.
  • Superseded IDs (openai/gpt-5.6-sol, x-ai/grok-4.6, anthropic/claude-fable-5) keep working with their previous settings.

v3.9.0

  • 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 the gptt default; GPT-5.5 stays available as a legacy model. ZDR is not supported on GPT-5.6 Sol (GPT-5.5 still is).
  • Grok 4.5 not added: x-ai/grok-4.5 is 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 the grot default.

v3.8.0

  • Added Claude Fable 5 (anthropic/claude-fable-5) — Anthropic's most capable model, 1M context. Premium price (~2× Opus 4.8), so it's reserved for specifically hard problems and is not part of the ULTRA panel; it does not replace Opus 4.8 as the default Claude model. New mnemonics fabt (think) / fabm (mid). Unlike Opus 4.8 (adaptive thinking only), OpenRouter honors Fable's effort scale, so mid/think map to effort=high/effort=xhigh (max intentionally 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".

v3.7.1

  • 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".

v3.7.0

  • Added Fusion (openrouter/fusion) — a multi-model panel plus a judge in one call; mode maps to web-research depth (fast/mid/think → max_tool_calls 2/8/16). New FUSE mnemonic.
  • Upgraded Claude Opus 4.7 → 4.8 (1M context, adaptive thinking); oput/opuf now point to 4.8, and 4.7 is kept as a legacy ID.
  • The response footer now reports the call cost in USD (from OpenRouter usage accounting), e.g. cost: $0.0923.

v3.6.1

  • Toggle-reasoning footer now distinguishes mid vs think for adaptive models (Opus, Grok)
  • Friendlier error message when a model has no Zero Data Retention endpoint
  • output_file return now includes the metadata footer so callers can verify what ran

v3.6.0

  • 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

v3.5.0

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

v3.4.0

  • 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

v3.3.0

  • Fixed GPT-5.2 thinking mode truncation issue (switched to streaming)
  • Added google/gemini-3-flash-preview (Gemini 3 Flash, ultra fast)
  • Updated gemf mnemonic to use Gemini 3 Flash
  • Added zdr parameter for Zero Data Retention routing

v3.2.0

  • Updated to GPT-5.2 with effort-based reasoning

v3.1.0

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

v3.0.0

  • Removed Google and OpenAI direct providers - now OpenRouter only
  • Removed |thinking suffix - use mode parameter instead (now required)
  • Clean mode parameter API: fast, mid, think
  • Simplified CLI from consult7 <provider> <key> to consult7 <key>
  • Better MCP integration with enum validation for modes
  • Dynamic file size limits based on model context window

v2.1.0

  • Added output_file parameter to save responses to files

v2.0.0

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

License

MIT

Related servers

paperclippaperclipai95KThe open-source app everyone uses to manage agents at workserver-nativewindmodelcontextprotocol91KModel Context Protocol Serverseverythingmodelcontextprotocol91KModel Context Protocol Serversfetchmodelcontextprotocol91KModel Context Protocol Servers

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers