Ontomics
未申請Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concepts, naming conventions, and vocabulary queryable via MCP.
インストール
claude mcp add -s user ontomics -- ontomics未申請リスティング
このMCPサーバーはあなたのものですか？
このリスティングは公開情報から自動的にインデックスされました。申請することで、ページの編集、互換性の設定、成長ツールのアンロックができます。2分以内に完了します。
このサーバーを申請するツール（19個）
check_naming
Check an identifier against project conventions; suggests the canonical form
compact_context
Assemble tiered context (concepts + logic) for a symbol, optimized for LLM consumption
concept_map
Show which modules contain which domain concepts
describe_file
Overview of a file's entities, concepts, and relationships
describe_logic
Get the behavioral description, body text, and logic cluster membership for a function
describe_symbol
Get the signature, docstring, and relationships for a function or class
export_domain_pack
Export domain knowledge as portable YAML for use in other repos
find_similar_logic
Find functions with behaviorally similar implementations, ranked by embedding similarity
list_concepts
List the top domain concepts by frequency
list_conventions
List all detected naming patterns (prefixes, suffixes, conversions)
list_entities
List code entities (classes, functions) filtered by concept, role, or kind
locate_concept
Find the key signatures, classes, and files for a concept
ontology_diff
Show new, changed, or removed domain concepts since a git ref
query_concept
Find all variants, related concepts, and occurrences of a term
suggest_name
Generate an identifier name that fits the project's vocabulary
trace_concept
Trace how a concept flows through the codebase via call chains
trace_type
Trace how a specific type propagates across files and call sites
type_flows
Show dominant types and how data flows through the codebase
vocabulary_health
Measure convention coverage, naming consistency, and cluster cohesion