@nahisaho/musubix-mcp-server

Add a traceability link between two artifacts (requirements, designs, code, tests).

Query the traceability database to find artifacts and their relationships.

Traverse the knowledge graph from a starting entity

Analyze the impact of changing an artifact. Returns all affected artifacts with impact scores.

Verify a precondition expression using Z3 SMT solver. Checks if the precondition is satisfiable or unsatisfiable.

Verify a Hoare triple {P} C {Q} using Z3 SMT solver. Checks if the postcondition Q holds after executing C when precondition P is satisfied.

Convert an EARS (Easy Approach to Requirements Syntax) requirement to SMT-LIB2 formula for formal verification.

Start file watching and auto-validation. Monitors files for changes and runs lint/test/security automatically.

Stop the active file watching session.

Get the status of active watch sessions.

Run specified tasks immediately on given files without waiting for changes.

Get accumulated issues report from watch session.

Create a new Architecture Decision Record (ADR)

List all ADRs with optional filters

Get a specific ADR by ID

Accept a proposed ADR

Deprecate an ADR, optionally marking it as superseded

Search ADRs by keyword

Find ADRs related to a requirement

Generate or update the ADR index file

Analyze a message for persona drift indicators. Based on arXiv:2601.10387 research. Returns drift score (0.0-1.0), detected triggers, domain classification, and intervention recommendations. Use this to check if user messages may cause AI persona drift away from assistant role.

Start a new persona monitoring session. Returns session ID and initial state. Sessions track drift history, intervention count, and domain classification over time.

Get current status of a monitoring session including drift score, trend, and intervention count.

End a monitoring session and get final metrics summary including average drift, max drift, and total interventions.

Get identity reinforcement prompt for the current session state. Types: 'identity' (core assistant traits), 'recovery' (after drift), 'refresh' (periodic). Based on Assistant traits from arXiv:2601.10387 Figure 3, Table 2.

Get current Assistant Axis configuration including drift thresholds, phase monitoring levels, and intervention limits.

Check monitoring level and frequency for a specific workflow phase. Based on research finding: "Coding and writing tasks keep models firmly in Assistant territory" - requirements/design: HIGH (100%) - tasks: MEDIUM (75%) - implementation: LOW (50%) - done: OFF (0%)

Learn patterns from observed code. Part of the Wake phase of Wake-Sleep learning.

Consolidate and optimize the pattern library. Part of the Sleep phase of Wake-Sleep learning.

Query relationships between patterns in the knowledge graph.

Search for patterns by various criteria.

Get statistics about the pattern learning system.

Import learned patterns into the ontology knowledge graph for semantic reasoning.

Export the pattern knowledge graph as Turtle RDF.

Validate a project against all registered policies

List all registered policies

Get details of a specific policy

Check a specific file against relevant policies

Add or update an entity in the knowledge graph

Get an entity from the knowledge graph by ID

Delete an entity from the knowledge graph

Add a relation between two entities

Query entities from the knowledge graph with filters

Parse a CodeQL SARIF 2.1.0 report file and extract security findings with CWE mappings.

Aggregate multiple CodeQL scan results into a unified report with statistics.

Look up CWE information including Japanese explanations and recommended fixes.

List all known CWE entries, optionally filtered by category or severity.

Get a summary of security findings from parsed SARIF data.

Get fix suggestions for security findings based on CWE information.