The Christensen MCP Server acts as a strategic advisor that applies Clayton Christensen's management frameworks to analyze business decisions and provide theory-grounded insights.
Core Capabilities:
Strategic Decision Analysis: Use the analyze_decision tool to evaluate business decisions (market entry, product development, competitive positioning) through four key frameworks: Jobs-to-Be-Done, Disruption Theory, Capabilities-Processes-Priorities, and Resource Dependence. Receive structured insights including framework-specific analysis, case study patterns, theory-based predictions, and diagnostic questions.
Case Study Pattern Matching: Use the case_study tool to match your situation against canonical Christensen case studies (Steel Mini-Mills, Disk Drives, Milkshake, Honda Motorcycles, Intel Microprocessors) to identify patterns of low-end disruption, new-market disruption, emergent strategy, and capability migration.
Framework Learning: Use the get_framework tool to access detailed explanations of each framework at different detail levels (summary, full, or questions-only) to deepen understanding and learn when to apply each theoretical lens.
Persona-Driven Advisory: Get strategic insights in Christensen's voice with theory-grounded reasoning, humility-based predictions ("the theory suggests..."), customer-centric analysis focused on jobs-to-be-done, and consideration of organizational constraints and resource dependencies.
Integration with Claude: Connect to Claude Desktop or Claude Code to enable Claude to act as a Christensen-style strategic advisor, using MCP tools to ground analysis in theory while applying nuanced reasoning.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Christensen MCP Server Analyze our pivot to the enterprise market using disruption theory."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Clayton Christensen persona agent for strategic advisory, implemented as an MCP (Model Context Protocol) server.
Apply disruption theory, jobs-to-be-done, and capabilities analysis to your business decisions.
This MCP server gives Claude the ability to analyze decisions through Clayton Christensen's frameworks:
Jobs-to-Be-Done: What job is the customer hiring your product to do?
Disruption Theory: Is this sustaining or disruptive? Who are the non-consumers?
Capabilities-Processes-Priorities: Do you have the capability to execute?
Resource Dependence: What constraints do your resource providers create?
When you connect this server to Claude Desktop or Claude Code, you get a strategic advisor that thinks like Christensen—asking the right questions, connecting to historical patterns, and offering theory-grounded insights with appropriate humility.
Related MCP server: Boundary MCP
# Clone the repository
git clone https://github.com/m2ai-mcp-servers/mcp-christensen.git
cd mcp-christensen
# Install dependencies
npm install
# Build
npm run buildAdd to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on Mac or %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"christensen": {
"command": "node",
"args": ["/path/to/christensen-mcp/dist/index.js"]
}
}
}Add to your project's .mcp.json:
{
"mcpServers": {
"christensen": {
"command": "node",
"args": ["./path/to/christensen-mcp/dist/index.js"]
}
}
}analyze_decisionFull strategic analysis using all Christensen frameworks.
Use the analyze_decision tool to evaluate: Should we pursue enterprise customers or focus on SMBs?Parameters:
decision (required): The business decision to analyze
context: Additional context about your situation
organization: Your org type, size, industry, current focus
market: Incumbents, competitors, customer segments
focusAreas: Specific frameworks to apply (jtbd, disruption, cpp, resource-dependence)
case_studyExplore Christensen's canonical case studies and match them to your situation.
Use the case_study tool to find patterns matching: We're a low-cost entrant being ignored by incumbentsAvailable cases:
steel_minimills: Low-end disruption with asymmetric motivation
disk_drives: New-market disruption with different value network
milkshake: Jobs-to-be-done discovery through circumstance
honda_motorcycles: Emergent strategy through market learning
intel_microprocessors: Capability migration through process investment
get_frameworkLearn about any Christensen framework in detail.
Use the get_framework tool with framework: jtbd and detail: fullFrameworks: jtbd, disruption, cpp, resource-dependence, all
Detail levels: summary, full, questions-only
You: I'm trying to decide whether to build individual AI agents or invest in a factory process for creating them. Can you analyze this using Christensen's frameworks?
Claude: Uses analyze_decision tool
Let me think through this using Christensen's frameworks...
Jobs-to-Be-Done: What job are your customers hiring an AI agent to do? If they need specialized expertise (functional), confidence in the advice (emotional), and credibility (social), individual high-quality agents might serve that job better. But if they need to create their own agents quickly, the factory serves a different job entirely.
The Intel Pattern: I'm reminded of Intel's pivot from memory to microprocessors. The insight wasn't about resources—Japanese firms could acquire those. It was about processes. Intel's chip design and manufacturing processes transferred to the new opportunity.
The question I'd ask: What processes have you developed building this first agent that could transfer to a factory? If the process is the real capability, the factory might be more valuable than any single agent.
You: We're entering a market with a simpler, cheaper product. Incumbents seem happy to ignore us.
Claude: Uses case_study tool
This matches the Steel Mini-Mills pattern closely.
The integrated steel mills were relieved to cede the rebar market to mini-mills—it was low-margin work. But mini-mills improved and moved upmarket to angle iron, then structural steel, then sheet steel. At each tier, the integrated mills rationally retreated.
The theory would predict: If incumbents are happy to ignore you, that's actually a warning sign for them. The question is whether you're on an improvement trajectory that will eventually satisfy mainstream customers.
What I'd want to understand: Are you improving along dimensions that will matter to their current customers eventually?
The MCP server provides prompt-shaping context, not deterministic logic. When you call a tool:
The server structures your decision using Christensen's frameworks
It matches relevant case studies and diagnostic questions
It provides Christensen's voice characteristics and phrases
Claude applies the reasoning with the persona's analytical approach
This design lets Claude do what it does best—nuanced reasoning and judgment—while the MCP tools ensure the analysis stays grounded in Christensen's theory.
The agent is designed to maintain high fidelity to Christensen's actual thinking:
Must include:
Reference to specific frameworks (JTBD, disruption, CPP)
Questions about the customer's job to be done
Humility about predictions ("the theory suggests...")
Connection to historical case studies
Consideration of organizational constraints
Must avoid:
Overconfident predictions
Dismissing incumbents as stupid (they're rational!)
Generic business advice without theory grounding
Run npm test to validate outputs against these fidelity markers.
# Build TypeScript
npm run build
# Watch mode
npm run dev
# Run validation tests
npm test
# Test with MCP Inspector
npm run inspectorchristensen-mcp/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── persona-loader.ts # YAML persona parser
│ ├── personas/
│ │ └── christensen.yaml # Core persona definition
│ ├── frameworks/
│ │ ├── types.ts # Shared types
│ │ ├── jobs-to-be-done.ts # JTBD framework
│ │ ├── disruption.ts # Disruption theory
│ │ └── capabilities.ts # CPP + Resource Dependence
│ ├── tools/
│ │ ├── analyze-decision.ts # Main analysis tool
│ │ ├── case-study.ts # Case study explorer
│ │ └── get-framework.ts # Framework reference
│ └── validation/
│ ├── fidelity-check.ts # Output validation
│ └── test-decisions.ts # Test cases
├── docs/
│ ├── BUILD_LOG.md # Development process journal
│ └── CHRISTENSEN_SPEC.md # Persona specification
└── dist/ # Compiled JavaScriptThis agent was built as a proof-of-concept for a persona agent factory. The BUILD_LOG.md documents the entire process so future agents can be built faster.
Key patterns extracted:
Persona YAML structure: identity, voice, frameworks, validation
Framework module pattern: questions, prompts, voice phrases
Fidelity validation: automated testing against persona markers
Built on Clayton Christensen's work, including:
The Innovator's Dilemma (1997)
The Innovator's Solution (2003)
Competing Against Luck (2016)
This is an educational tool meant to help apply Christensen's publicly available frameworks. It is not affiliated with or endorsed by the Christensen Institute.
MIT
Built with Claude Code as a demonstration of MCP server development and persona agent architecture.
Analyze a business decision using Clayton Christensen's frameworks.
Applies Jobs-to-Be-Done, Disruption Theory, Capabilities-Processes-Priorities, and Resource Dependence analysis to provide strategic insight.
Returns a structured analysis with:
Framework-specific insights
Relevant case study patterns
Theory-based predictions (with appropriate uncertainty)
Key questions for deeper understanding
Use this when facing strategic decisions about:
Market entry or expansion
Product development priorities
Competitive positioning
Organizational capability assessment
Innovation strategy
| Name | Required | Description | Default |
|---|---|---|---|
| decision | Yes | The business decision or situation to analyze | |
| context | No | Additional context about the organization, market, or situation | |
| organization | No | ||
| market | No | ||
| focusAreas | No | Specific frameworks to focus on (default: all) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It describes the structured output format and analytical approach but lacks details about computational requirements, processing time, rate limits, or error conditions. The behavioral disclosure is adequate but incomplete for a complex analytical tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections for purpose, methodology, output format, and usage guidelines. It's appropriately sized for a complex tool, though some sentences could be more direct. Every section adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex analytical tool with 5 parameters, nested objects, no annotations, and no output schema, the description provides good purpose and usage context but lacks details about the analysis process, limitations, or what constitutes a valid 'decision' input. It's minimally adequate but leaves gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 60% schema description coverage, the description doesn't add parameter-specific information beyond what's in the schema. It mentions frameworks but doesn't explain parameter relationships or provide examples of valid inputs. The baseline score reflects adequate but not enhanced parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as analyzing business decisions using specific Clayton Christensen frameworks (Jobs-to-Be-Done, Disruption Theory, etc.). It distinguishes from sibling tools 'case_study' and 'get_framework' by focusing on strategic analysis rather than retrieving case studies or framework definitions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool, listing five specific strategic decision scenarios (market entry, product development, competitive positioning, etc.). This gives clear context for when this analysis tool is appropriate versus its siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find and explore Christensen's canonical case studies.
These cases illustrate key patterns from disruption theory:
Steel Mini-Mills: Low-end disruption
Disk Drives: New-market disruption
Milkshake: Jobs-to-be-done
Honda Motorcycles: Emergent strategy
Intel: Capability migration
Use this to:
Find patterns matching your current situation
Deep-dive into a specific case study
Learn the lessons and common misapplications
Get diagnostic questions for your situation
| Name | Required | Description | Default |
|---|---|---|---|
| situation | Yes | Description of the current situation to match against case studies | |
| observedSignals | No | Specific patterns or signals observed | |
| caseName | No | Request a specific case study by name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes what the tool does but lacks behavioral details: no information about permissions needed, rate limits, response format, whether it's a read-only or mutating operation, or how results are returned. For a tool with 3 parameters and no annotation coverage, this is a significant gap in behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with clear sections: purpose statement, examples of cases, and use cases. Every sentence earns its place by providing value. Could be slightly more concise by combining some bullet points, but overall efficient and front-loaded with the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 3 parameters with 100% schema coverage but no annotations and no output schema, the description provides good purpose and usage context but lacks behavioral transparency. It adequately covers what the tool does and when to use it, but doesn't address how it behaves, what it returns, or implementation details. For a tool with no output schema, some indication of return format would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema. It mentions 'match against case studies' which aligns with the 'situation' parameter, but provides no additional syntax, format, or usage details for parameters. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Find and explore Christensen's canonical case studies' with specific examples listed. It distinguishes from siblings by focusing on case studies rather than decision analysis or frameworks, though it doesn't explicitly name the sibling tools. The verb+resource combination is clear but could be more specific about the action (find/explore vs. analyze).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'Use this to:' section provides clear context for when to use this tool: finding patterns matching current situations, deep-diving into specific cases, learning lessons, and getting diagnostic questions. It doesn't explicitly mention when NOT to use it or name alternative tools (like analyze_decision or get_framework), but the use cases are well-defined and practical.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get information about Christensen's strategic frameworks.
Available frameworks:
jtbd: Jobs-to-Be-Done theory
disruption: Disruption Theory
cpp: Capabilities-Processes-Priorities
resource-dependence: Resource Dependence Theory
all: Overview of all frameworks
Detail levels:
summary: Core concepts and when to use
full: Complete framework with questions and examples
questions-only: Just the diagnostic questions
| Name | Required | Description | Default |
|---|---|---|---|
| framework | Yes | Which framework to retrieve | |
| detail | No | Level of detail (default: summary) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes what the tool returns (framework information with varying detail levels) but does not cover aspects like error handling, response format, or any limitations (e.g., data freshness, access restrictions). It adds useful context on available options but misses broader behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose, followed by structured lists of frameworks and detail levels. Every sentence earns its place by providing essential information without redundancy. It is appropriately sized for a tool with two parameters and clear options, making it efficient and easy to scan.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (2 parameters with enums) and no output schema or annotations, the description is partially complete. It covers the purpose and parameter semantics well but lacks details on return values, error conditions, or integration with sibling tools. For a read-only informational tool, this is adequate but has clear gaps in contextual guidance.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the baseline is 3. The description adds significant value by explaining the semantics of parameter options: it clarifies what each framework acronym stands for (e.g., 'jtbd: Jobs-to-Be-Done theory') and defines the meaning of detail levels (e.g., 'summary: Core concepts and when to use'). This goes beyond the schema's enum lists, enhancing understanding of parameter choices.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool's purpose as 'Get information about Christensen's strategic frameworks,' which is a clear verb+resource combination. It distinguishes itself from sibling tools (analyze_decision, case_study) by focusing on retrieving framework information rather than analysis or case studies, making the purpose specific and well-differentiated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides implied usage guidance by listing available frameworks and detail levels, suggesting when to use specific options. However, it lacks explicit guidance on when to choose this tool over alternatives like analyze_decision or case_study, and does not mention any prerequisites or exclusions, leaving the context somewhat incomplete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
analyze_decisioncase_studyget_frameworkScored across 3 tools
Each tool has a clearly distinct purpose with no overlap: analyze_decision applies frameworks to real-world decisions, case_study explores historical examples, and get_framework provides theoretical information. The descriptions reinforce these distinct roles, making misselection unlikely.
All tools follow a consistent verb_noun pattern (analyze_decision, case_study, get_framework) with clear, descriptive names that align with their functions. There are no deviations in naming conventions.
With 3 tools, this server is well-scoped for its purpose of providing strategic insights using Christensen's theories. Each tool earns its place by covering distinct aspects: analysis, case studies, and framework details, without being too sparse or bloated.
The tool set covers the core needs for applying Christensen's frameworks: analysis, case study reference, and framework information. A minor gap exists in lacking tools for interactive or iterative refinement of analyses, but agents can work around this by combining tools effectively.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI agent for business strategy and business design — run strategy missions and 15 analyses.
End-to-end agent-managed company brain. Docs, diagrams, plans, Knowledge Graph. Lean & affordable.
Expert knowledge base for sales, negotiation, strategy, operations, and risk.
Evidence-backed opportunity intelligence for small businesses, built for authorised AI agents.
