Analysis MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
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.
๐ง 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 analysisEach 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 componentscompare_positions- Multi-perspective ideological analysisapply_lens- Analyze through 9 frameworks (historical, economic, etc.)get_trace- Retrieve previous analysis plans
๐ Prompt Chaining Tools (NEW):
apply_operation- Apply 15+ analytical operations to any contentchain_analysis- Chain operations on previous LLM outputslist_available_operations- Browse all available operations
15+ Analytical Operations:
Deconstructive:
extract_assumptions- Find implicit/explicit assumptionsidentify_contradictions- Spot logical tensionsfind_fallacies- Detect rhetorical manipulation
Constructive:
steelman_argument- Build strongest versionfind_analogies- Identify relevant precedentsextract_principles- Derive universal patterns
Synthetic:
synthesize_perspectives- Merge viewpointselevate_abstraction- Raise to higher conceptsground_in_specifics- Add concrete examples
Meta-analytical:
identify_gaps- Find missing elementscheck_coherence- Verify logical consistencysuggest_next_step- Recommend next operation
Transformative:
convert_to_dialogue- Reframe as Socratic dialogueextract_counterfactuals- Generate what-if scenariosmap_dependencies- Chart logical dependencies
Quick Start with Claude Desktop
Install via uvx (recommended):
Edit your Claude Desktop config file:
MacOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%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"
]
}
}
}Restart Claude Desktop
Verify installation: Look for the ๐ 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.serverFor 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"
}
}
}
}๐ 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 claimWorkflow 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 missingWorkflow 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 operation๐ก Why This Approach?
Traditional Analysis: One-shot, limited depth
"Analyze X" โ Single output โ DoneChained 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 understandingBenefits:
โ Build complexity incrementally - Each operation adds a layer
โ Provider-agnostic - Works with any LLM
โ No API keys needed - Server never calls external LLMs
โ Fully traceable - Every step logged with trace_id
โ Self-guided -
suggest_next_stepoperation recommends what to do nextโ 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 identifiertool- Which tool was calledinput- Original parametersoutline- Structured analysis plannext_prompt- The prompt for LLM executiontimestamp- When it was created
Use get_trace(trace_id) to retrieve any previous analysis plan.
Troubleshooting
Server not connecting?
Verify
uvxis installed:pip install uvxCheck Claude Desktop logs (Help โ View Logs)
Ensure your config JSON is valid
Tools not appearing?
Restart Claude Desktop after config changes
Check the ๐ icon shows "analysis-mcp" as connected
Contributing
Pull requests welcome! Please run tests before submitting:
pytest -vTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
This server cannot be deployed
Maintenance
Related MCP Connectors
A governed, nonclinical reasoning system that helps people and AI agents make sense of difficult moments and choose a grounded next step. Use Clarity OS for overthinking, emotional activation, uncertainty, decision friction, conflicting priorities, repeating patterns, or difficult conversations. It returns structured, safety-governed clarity while preserving uncertainty, personal agency, and appropriate nonclinical boundaries.
Native Clarity decision mapping, MindScan episode reflection, and read-only evidence tools.
Turn grounded AI answers into trusted comparisons, plans, timelines, and decision views.
Calibrated world model for AI agents. 40 tools: world state, markets, trading. Kalshi + Polymarket.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables analysis of claims, validation of sources, and detection of manipulation using multiple epistemological frameworks to ensure credible and ethical information.323MIT
- AlicenseAqualityBmaintenanceEnables structural framing analysis of documents, identifying perspectives, omissions, and reader positioning, with numerical claim verification against authoritative sources.2Apache 2.0
- AlicenseAqualityDmaintenanceProvides structured thinking with step-by-step reasoning and steel-manning verification for AI agents, backed by cognitive science research.247 npm1MIT
- AlicenseAqualityDmaintenanceEnables 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.142 npm2Apache 2.0