Skip to main content
Glama
Analysis MCP
by RCSnyder

analysis-mcp

A FastMCP server for critical thinking and multi-perspective analysis of current affairs.

Uses the LLM-Orchestrator Pattern: Tools return structured prompts for the calling LLM to execute, enabling iterative complexity building through prompt chaining.

๐Ÿง  Core Concept: Prompt Chaining for Complexity

Instead of doing one analysis, chain operations to build increasingly sophisticated insights:

1. deconstruct_claim("AI will replace jobs")
   โ†’ Get structured breakdown
   
2. chain_analysis(previous_output, "extract_assumptions")
   โ†’ Find hidden assumptions in your analysis
   
3. chain_analysis(previous_output, "identify_contradictions")
   โ†’ Spot tensions in the argument
   
4. chain_analysis(previous_output, "steelman_argument")
   โ†’ Build strongest version of the claim
   
5. chain_analysis(previous_output, "suggest_next_step")
   โ†’ Get recommendation for deeper analysis

Each step builds on the last, creating layered, sophisticated thinking.

Related MCP server: frame-check-mcp

Features

Core Analytical Tools:

  • deconstruct_claim - Break down claims into components

  • compare_positions - Multi-perspective ideological analysis

  • apply_lens - Analyze through 9 frameworks (historical, economic, etc.)

  • get_trace - Retrieve previous analysis plans

๐Ÿ”— Prompt Chaining Tools (NEW):

  • apply_operation - Apply 15+ analytical operations to any content

  • chain_analysis - Chain operations on previous LLM outputs

  • list_available_operations - Browse all available operations

15+ Analytical Operations:

Deconstructive:

  • extract_assumptions - Find implicit/explicit assumptions

  • identify_contradictions - Spot logical tensions

  • find_fallacies - Detect rhetorical manipulation

Constructive:

  • steelman_argument - Build strongest version

  • find_analogies - Identify relevant precedents

  • extract_principles - Derive universal patterns

Synthetic:

  • synthesize_perspectives - Merge viewpoints

  • elevate_abstraction - Raise to higher concepts

  • ground_in_specifics - Add concrete examples

Meta-analytical:

  • identify_gaps - Find missing elements

  • check_coherence - Verify logical consistency

  • suggest_next_step - Recommend next operation

Transformative:

  • convert_to_dialogue - Reframe as Socratic dialogue

  • extract_counterfactuals - Generate what-if scenarios

  • map_dependencies - Chart logical dependencies

Quick Start with Claude Desktop

  1. Install via uvx (recommended):

Edit your Claude Desktop config file:

  • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add this to the mcpServers section:

{
  "mcpServers": {
    "analysis-mcp": {
      "command": "uvx",
      "args": [
        "git+https://github.com/YOUR_USERNAME/analysis_mcp",
        "analysis-mcp"
      ]
    }
  }
}
  1. Restart Claude Desktop

  2. Verify installation: Look for the ๐Ÿ”Œ icon in Claude Desktop showing the analysis-mcp server is connected

Alternative: Local Development Installation

If you want to modify the code or run it locally:

# Clone the repo
git clone https://github.com/YOUR_USERNAME/analysis_mcp.git
cd analysis_mcp

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install in editable mode
pip install -e ".[dev]"

# Run tests
pytest -v

# Run server directly (for testing)
python -m analysis_mcp.server

For local development in Claude Desktop, update your config to point to the local path:

{
  "mcpServers": {
    "analysis-mcp": {
      "command": "python",
      "args": [
        "-m",
        "analysis_mcp.server"
      ],
      "cwd": "/absolute/path/to/analysis_mcp",
      "env": {
        "PYTHONPATH": "/absolute/path/to/analysis_mcp/src"
      }
    }
  }
}

๐Ÿ”„ Example Workflows

Workflow 1: Deep Claim Analysis

1. "Analyze: AI will replace all jobs in 10 years"
   โ†’ deconstruct_claim()
   โ†’ Get: assumptions, evidence, implications

2. "Now extract the assumptions from that analysis"
   โ†’ chain_analysis(prev, "extract_assumptions")
   โ†’ Get: implicit assumptions revealed

3. "Find contradictions in those assumptions"
   โ†’ chain_analysis(prev, "identify_contradictions")
   โ†’ Get: logical tensions

4. "Steelman the strongest version"
   โ†’ chain_analysis(prev, "steelman_argument")
   โ†’ Get: most defensible claim

Workflow 2: Multi-Lens Synthesis

1. apply_lens("Fed raises rates", "economic")
   โ†’ Economic analysis

2. apply_lens("Fed raises rates", "political")  
   โ†’ Political analysis

3. apply_operation(both_outputs, "synthesize_perspectives")
   โ†’ Unified framework

4. chain_analysis(synthesis, "identify_gaps")
   โ†’ Find what's missing

Workflow 3: Iterative Refinement

1. compare_positions("Climate policy")
   โ†’ Multi-perspective view

2. chain_analysis(output, "elevate_abstraction")
   โ†’ Broader systemic patterns

3. chain_analysis(output, "ground_in_specifics")
   โ†’ Concrete examples added

4. chain_analysis(output, "check_coherence")
   โ†’ Verify consistency

5. chain_analysis(output, "suggest_next_step")
   โ†’ AI recommends next operation

๐Ÿ’ก Why This Approach?

Traditional Analysis: One-shot, limited depth

"Analyze X" โ†’ Single output โ†’ Done

Chained Analysis: Iterative, building complexity

"Analyze X" 
โ†’ deconstruct 
โ†’ extract assumptions 
โ†’ find contradictions 
โ†’ steelman argument 
โ†’ identify gaps
โ†’ synthesize
= Deep, multi-layered understanding

Benefits:

  • โœ… Build complexity incrementally - Each operation adds a layer

  • โœ… Provider-agnostic - Works with any LLM

  • โœ… No API keys needed - Server never calls external LLMs

  • โœ… Fully traceable - Every step logged with trace_id

  • โœ… Self-guided - suggest_next_step operation recommends what to do next

  • โœ… Composable - Mix with other MCP tools (Wikipedia, web search, etc.)

Available Lenses

  • historical - Compare to precedents and patterns

  • economic - Analyze resource flows and incentives

  • geopolitical - Examine power balances and strategy

  • psychological - Identify biases and manipulation

  • technological - Explore tech's role and impact

  • sociocultural - Analyze identity and narratives

  • philosophical - Apply ethical frameworks

  • systems - Map feedback loops and leverage points

  • media - Deconstruct framing and agenda-setting

Trace Storage

Analysis plans are logged to ~/.analysis_mcp/traces/ as JSON files. Each trace contains:

  • trace_id - Unique identifier

  • tool - Which tool was called

  • input - Original parameters

  • outline - Structured analysis plan

  • next_prompt - The prompt for LLM execution

  • timestamp - When it was created

Use get_trace(trace_id) to retrieve any previous analysis plan.

Troubleshooting

Server not connecting?

  • Verify uvx is installed: pip install uvx

  • Check Claude Desktop logs (Help โ†’ View Logs)

  • Ensure your config JSON is valid

Tools not appearing?

  • Restart Claude Desktop after config changes

  • Check the ๐Ÿ”Œ icon shows "analysis-mcp" as connected

Contributing

Pull requests welcome! Please run tests before submitting:

pytest -v

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables structural framing analysis of documents, identifying perspectives, omissions, and reader positioning, with numerical claim verification against authoritative sources.
      2
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      Enables users to stress-test decisions and plans with structured contrarian analysis, surfacing blind spots, hidden assumptions, and failure scenarios through multiple modes such as counter, probe, redteam, and premortem.
      1
      42 npm
      2
      Apache 2.0