# One-click via badge or manual:
uvx jcodemunch-mcp

{
  "mcpServers": {
    "jcodemunch": {
      "command": "uvx",
      "args": ["jcodemunch-mcp"]
    }
  }
}

# Install via uvx
uvx jcodemunch-mcp

# Or use the jcm CLI helper
jcm install claude-code

{
  "mcpServers": {
    "jcodemunch": {
      "command": "uvx",
      "args": ["jcodemunch-mcp"]
    }
  }
}

# Install the jcm CLI
pip install jcodemunch-mcp

# Or use uvx
uvx jcodemunch-mcp

{
  // Index settings
  "index_path": ".jcodemunch/index",
  "excluded_patterns": [
    "node_modules/**",
    "venv/**",
    ".git/**",
    "*.pyc",
    "__pycache__/**"
  ],
  
  // Token budget defaults
  "default_token_budget": 8000,
  "max_token_budget": 16000,
  
  // Compact format (MUNCH) - saves 45.5% tokens on average
  "compact_format_enabled": true,
  "compact_format_threshold": 0.15, // Use compact if ≥15% savings
  
  // Semantic search (optional, requires sentence-transformers)
  "semantic_search_enabled": false,
  "embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
  
  // Tool configuration
  "disabled_tools": [],  // Disable specific tools if needed
  
  // Language support
  "supported_languages": [
    "python", "javascript", "typescript", "go", "rust",
    "java", "c", "cpp", "c_sharp", "ruby", "php"
  ]
}

# Via MCP tool call
index_repository(
    path="/path/to/repo",
    force_reindex=False  # Set True to rebuild from scratch
)

get_index_info()
# Returns: stats, file count, symbol count, last indexed time

find_symbols(
    query="get_user",
    limit=10,
    file_pattern="*.py",  # Optional filter
    format="auto"  # auto|compact|json
)

find_implementations(
    symbol="UserService.authenticate",
    include_lsp=True,  # LSP dispatch
    include_hierarchy=True,  # Class hierarchy
    include_duck_typed=True,  # Duck-typed matches
    include_decorators=True  # Decorator handlers
)

get_symbol_content(
    identifier="UserService.authenticate",
    include_docstring=True,
    include_decorators=True,
    format="auto"
)

get_ranked_context(
    query="authentication logic",
    token_budget=4000,
    include_imports=True,
    include_references=True,
    format="auto"
)
# Returns: ranked symbols within budget, total tokens used

assemble_task_context(
    task="fix bug in user authentication where tokens expire too early",
    token_budget=8000,
    session_id="fix-auth-bug-001"  # Optional session tracking
)
# Auto-classifies intent (bug_fix, feature, refactor, etc.)
# Extracts anchor symbols from task description
# Runs appropriate tool sequence under budget

find_references(
    identifier="get_user",
    include_calls=True,
    include_imports=True,
    format="auto"
)

find_importers(
    target="services.auth",
    format="auto"
)

get_blast_radius(
    identifier="User.email",
    max_depth=3,
    include_source=True,  # Include source snippets
    format="auto"
)

get_class_hierarchy(
    class_name="BaseModel",
    direction="both",  # up|down|both
    format="auto"
)

find_dead_code(
    scope="all",  # all|file|module
    include_private=True,
    format="auto"
)

get_untested_symbols(
    scope="all",
    min_complexity=5,  # Focus on complex code
    format="auto"
)

find_similar_symbols(
    threshold=0.8,  # Similarity threshold (0-1)
    min_cluster_size=2,
    use_semantic=True,  # Requires semantic search enabled
    use_structural=True,
    use_behavioral=True,  # Callee Jaccard
    format="auto"
)
# Returns: clusters with canonical pick + consolidation verdict

check_delete_safe(
    identifier="legacy_auth_handler",
    format="auto"
)
# Returns: composite verdict + ranked blockers + recommended action

get_symbol_importance(
    limit=20,
    scope="all",  # all|file|module
    format="auto"
)

get_repo_map(
    token_budget=4000,
    signature_only=True,  # Just signatures, not full implementations
    format="auto"
)
# Returns: PageRank-ranked symbol overview within budget

get_dependency_cycles(
    format="auto"
)

get_hotspots(
    min_complexity=10,
    days_back=90,
    format="auto"
)

get_group_contracts(
    repos=["/path/to/repo1", "/path/to/repo2"],
    min_shared=2,  # Minimum repos sharing symbol
    format="auto"
)
# Returns: ranked contracts classified as:
# - de_facto_api (stable, high usage)
# - leaky_internal (unintended exposure)
# - dead_contract (no runtime hits)
# - version_skew (inconsistent across repos)

get_changed_symbols(
    base_ref="main",
    head_ref="feature-branch",
    format="auto"
)

# 1. Get task-oriented context
assemble_task_context(
    task="fix NullPointerException in payment processing",
    token_budget=6000,
    session_id="fix-payment-bug"
)

# 2. Find related code
find_symbols(
    query="payment process",
    limit=5
)

# 3. Get implementation + references
get_symbol_content(identifier="PaymentService.process")
find_references(identifier="PaymentService.process")

# 4. Check blast radius before fix
get_blast_radius(
    identifier="PaymentService.process",
    max_depth=2,
    include_source=True
)

# 1. Find dead code
dead_symbols = find_dead_code(scope="all", include_private=True)

# 2. For each dead symbol, verify safety
check_delete_safe(identifier="legacy_user_handler")

# 3. Get blast radius to confirm
get_blast_radius(identifier="legacy_user_handler", max_depth=1)

# 4. Find similar code that might be consolidated
find_similar_symbols(threshold=0.85, min_cluster_size=2)

# 1. Get high-level overview
get_repo_map(token_budget=3000, signature_only=True)

# 2. Find most important symbols
get_symbol_importance(limit=15)

# 3. Explore class hierarchies
get_class_hierarchy(class_name="BaseController", direction="down")

# 4. Get architectural overview
get_dependency_cycles()
get_hotspots(min_complexity=8, days_back=30)

# 1. Find where similar features are implemented
find_symbols(query="user authentication", limit=10)

# 2. Get ranked context for the task
assemble_task_context(
    task="add OAuth2 authentication alongside existing password auth",
    token_budget=8000
)

# 3. Find all authentication-related symbols
get_ranked_context(
    query="authentication oauth password",
    token_budget=5000,
    include_imports=True
)

# 4. Check who will be affected
find_importers(target="auth.handlers")

{
  "semantic_search_enabled": true,
  "embedding_model": "sentence-transformers/all-MiniLM-L6-v2"
}

pip install sentence-transformers torch

find_symbols(
    query="handles user authentication with tokens",
    use_semantic=True,  # Combines BM25 + embeddings
    limit=10
)

# dbt models as context
get_dbt_context(
    model_name="fct_orders",
    include_upstream=True,
    include_downstream=True
)

# Git context
get_changed_symbols(base_ref="main", head_ref="HEAD")

plan_turn(
    session_id="feature-impl-001",
    task="implement OAuth2",
    budget=10000
)

assemble_task_context(
    task="add Google OAuth provider",
    session_id="feature-impl-001",
    token_budget=6000
)

# Force reindex
index_repository(path=".", force_reindex=True)

# Install required dependencies
pip install sentence-transformers torch

# Use stricter filters
find_symbols(
    query="handler",
    file_pattern="**/controllers/*.py",
    limit=5
)

# Use smaller budget or signature-only mode
get_repo_map(token_budget=2000, signature_only=True)

// Add to config.jsonc
{
  "excluded_patterns": [
    "node_modules/**",
    "venv/**",
    "dist/**",
    "build/**",
    ".git/**"
  ]
}

# Install client-specific config
jcm install claude-code
jcm install cursor
jcm install windsurf

# Index current directory
jcm index .

# Search symbols
jcm search "UserService"

# Get symbol info
jcm info "UserService.authenticate"

# Check config
jcm config --validate