Does Contorium execute actions or modify my environment?
No. Contorium does not execute actions, install tools, or take control of the development workflow. It only observes, understands, and suggests.
Contorium MCP Server
@ContoriumLabs
基本情報
Contorium MCP Server について
Runtime Cognitive Cortex for AI coding workflows.
Contorium MCP Server の設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"contorium": {
"command": "npx",
"args": [
"@contorium/mcp"
],
"env": {
"CONTORIUM_WORKSPACE": "/path/to/project"
}
}
}
}Contorium MCP Server のツール
118[Cognitive Overlay] Read MCP mode A/B. Contorium MCP mode (v2): A = Core Runtime DEFAULT (pure observation — project, task, feed) B = Cognitive Overlay (A + skill suggestions + model presets + external search)
[Cognitive Overlay] Switch MCP mode A/B. Does NOT change runtime core behavior — overlay only. Contorium MCP mode (v2): A = Core Runtime DEFAULT (pure observation — project, task, feed) B = Cognitive Overlay (A + skill suggestions + model presets + external search)
[Cognitive Overlay · Mode B only] Full insight bundle: intent, skills, tools, model preset. Read-only — never installs or executes.
[Cognitive Overlay · Mode B only] Skill discovery from local registry + GitHub/NPM search. Display-only links — no auto install.
[Cognitive Overlay · Mode B only] Task mode preset (SMART/FAST/REASON/CODE/LOCAL) — strategy hint only, NOT a model recommendation system.
[Legacy alias · prefer record_project_intent] Record user direction overlay for cognition. Requires user_input. Does not execute work.
[Write · Intent] Record project direction for intent/why layers (human → system). Requires user_input. Prefer capture_focus for simple current-task updates.
[Inspect · Composite] One-shot cognition snapshot (governance + handoff + state). Prefer ask_project or inspect_* for targeted reads; use this for a broad diagnostic dump.
[Inspect] Derived cognitive projection (.contora/cognitive/). Prefer inspect_state / inspect_intent for PIL facts.
[Inspect] Recent guard / change-log records. Optional limit (1–50, default 20). Prefer get_recent_events for cognitive timeline.
[Legacy] Decision provenance context — prefer get_decision_context.
[Decision Provenance · read] Project state, git, and latest decision snapshot.
[Governance V4 · fast] Resolve diff/file/project into primary, related, risk, and dependency scopes. mode: auto | strict | minimal (not "project"). Prefer before a SLOW derive_decision_provenance when scoping a single file.
[SLOW · ~2–3 min · Prefer once] Derive decision provenance (review → decision → scope → trace). Records only — no code execution. Pass active_file + mode=advisory + persist=false for lighter runs. Do NOT also call aliases in the same turn (derive_decision_trace / decision_snapshot / run_governance_cycle / build_decision_provenance / trace_governance_cycle). Prefer get_decision_context or ask_project for quick reads.
[SLOW · Alias · prefer derive_decision_provenance] Same handler — avoid calling both in one turn.
[SLOW · Alias · prefer derive_decision_provenance] Same derive cycle (persist=true only if you need a written snapshot) — not a separate API.
[SLOW · Legacy · prefer derive_decision_provenance] Same heavy cycle — do not call for ordinary Q&A.
[SLOW · Legacy · prefer derive_decision_provenance] Same heavy cycle. Not task execution. Avoid unless caller already uses this name.
[SLOW · Legacy · prefer derive_decision_provenance] Same heavy cycle — alias only.
[Prefer · Inject] Build structured AI context from decision provenance (no autonomous action). Call after derive_decision_provenance when injecting governance context.
[Legacy alias] Same as synthesize_context_payload.
[Decision Provenance · read] Export decision / scope / trace appendix for AI context.
[Legacy alias] Same as export_decision_provenance.
[SLOW · Ready] Verify Decision Provenance layer is initialized (~10–20s). Call before derive_decision_provenance on a fresh workspace; skip if already initialized this session.
[SLOW · Legacy · prefer inspect_cognition_ready] Same ready check (~10–20s).
[SLOW · Legacy · prefer inspect_cognition_ready] Same ready check (~10–20s).
[SLOW · Legacy · prefer inspect_cognition_ready] Same ready check (~10–20s). Avoid unless caller already uses this name.
[Project Intelligence · inspect] Cross-tool project identity (.contora/identity/project_identity.json).
[Project Intelligence · inspect] Decision provenance graph + latest governance decision record.
[Project Intelligence · inspect] Why layer (.contora/intent/why.json).
[Project Intelligence · inspect] Intent graph (.contora/intent/intent_graph.json).
[Dimension · TIMELINE · inspect] Structured evolution history (.contora/timeline/project_timeline.json). Descriptive — not a log dump.
[Dimension · IMPACT · inspect] Scope and propagation model (.contora/graph/impact_graph.json). Descriptive — not risk prediction.
[Dimension · CONFIDENCE · inspect] Trustworthiness of recorded intelligence (.contora/confidence/confidence_index.json).
[Legacy alias] Same as get_confidence_index.
[System · PROVENANCE · inspect] Trace-back chains WHY → DECISION → INTENT → TIMELINE (.contora/provenance/provenance_chain.json).
[System · EVOLUTION · inspect] Structured transformation chains (.contora/evolution/evolution_graph.json). Not chronological timeline.
[v1.1.3 · inspect] Intelligence completeness, weighted health_score, knowledge_coverage (.contora/intelligence/health.json). Measures asset completeness — not project quality.
[v1.1.3 · inspect] Append-only decision log (.contora/decision/decision_log.json). Records selected alternatives — not recommendations.
[Legacy alias · prefer transfer_context] Compressed Cognitive Snapshot (~300–800 tokens).
[Legacy alias · prefer transfer_intelligence] Full Project Intelligence export (~8000 tokens).
[PIL · Inspect] Workspace state — state.json, status, built project state. Call first when grounding on current focus/stage. Prefer ask_project for NL questions.
[PIL · Inspect · Prefer] vNext intent graph (.contora/intent/intent_graph.json). Prefer over legacy get_intent_graph / get_project_intent_graph.
[PIL · Inspect · Prefer] Decision provenance + governance decision + decision log. Prefer over get_decision_graph / get_project_decision for a full decision picture.
[PIL · Inspect] Project evolution timeline (TIMELINE dimension).
[PIL · Inspect] Change-neighborhood graph (.contora/graph.json).
[PIL · Inspect] Confidence index (CONFIDENCE dimension).
[PIL · Inspect] Project intelligence health metrics.
[PIL · Inspect] Why layer — feature rationale records.
[PIL · Inspect] Impact graph (IMPACT dimension).
[PIL · Inspect] Evolution graph — structured transformation chains (EVOLUTION system).
[PIL · Inspect] Provenance chain — WHY → DECISION → INTENT trace-back (PROVENANCE system).
[Legacy alias · prefer transfer_project mode=context] Intelligence Transfer Context (~300–800 tokens).
[Legacy alias · prefer transfer_project mode=intelligence] Full Intelligence Transfer (~8000 tokens).
[Legacy alias · prefer transfer_project mode=handoff] Compact handoff (~100–300 tokens) for new-chat continuity.
[Legacy alias · prefer transfer_handoff] Same as transfer_handoff.
[PIL · Capture · Write] Set current project focus (state.json currentTask). Side effect: persists focus.
[PIL · Capture · Write] Append a timestamped note to state.json. Side effect: persists note.
[PIL · Capture · Write] Record a decision (append-only log). Side effect: persists decision. Requires selected; optional reason / intent_id / decision_id.
[PIL · Evolution] Detect project-state transitions and enqueue pending decisions for human review. Does NOT auto-commit. Call after significant architectural changes or sync. Ingests git working-tree changes as ChangeEvents first.
[PIL · Evolution] Record a file ChangeEvent into the active Task Session (MCP tool-result bridge). Prefer after write/edit tools; does not Accept Decision.
[PIL · Inspect · Prefer] List pending decisions awaiting human review (.contora/lifecycle/pending-decisions/). AI may read; must NOT auto-commit.
[Legacy alias · prefer inspect_pending_decisions] Same as inspect_pending_decisions(status=waiting_review).
[PIL · Lifecycle · Prefer] Review pending decision queue or one pending_id. AI may read; must NOT auto-accept. Prefer before commit_decision.
[PIL · Capture · Write] Accept Decision — promotes a pending decision into ADR (.contora/decisions/). Reasoning State accept (not Git commit). REQUIRES user_confirmed=true after explicit human confirmation. Agents must NOT auto-accept.
[PIL · Write] Mark a pending decision as ignored after human decline. Requires pending_id.
[PIL · Evolution · Prefer] Decision Evolution Graph + waiting pending + project-state fingerprint. How the project evolved decision-by-decision.
[PIL · Retrieval] Project background context for questions and exploration (decisions, constraints, evolution, state). For pre-edit agent work use prepare_execution_context instead. Read-only — does not Accept Decision.
[PIL · Retrieval · Prefer] Prepare minimal must-know context before the agent executes a task (Analyzer → Risk → Retrieval → Budget). Call immediately before architecture-sensitive edits. Read-only — does not Accept Decision.
[PIL · Retrieval] Explain why specific context items were included for a task. Read-only.
[CIL · Prefer for Q&A] Natural-language project question (what happened, why, impact, validity, next). Call when the user asks in plain language. Prefer over chaining multiple inspect_* tools. Does not execute work.
[CIL · History] Latest cognitive events (timeline + decision + why). Use for a short recent feed. Params: limit (default 12); optional range filters then applies limit. For a dated window with narrative blocks prefer get_project_history.
[CIL · History Explorer] Project history feed for a time range (formatted blocks). Use when the user asks what happened over a period. Params: range (default last_7_days); optional limit (default 24). For only the N newest events prefer get_recent_events.
[CIL · Decision Center] ADR-style decisions with Why / Risk / Alternatives. Use when listing or reviewing recorded decisions. Prefer ask_project for one-off “why was X decided”.
[CIL · Narrative] Combined story — goal, events, decisions, journey. Prefer transfer_project(mode=story) when exporting into a chat; use this to read the story payload in-place. Alias of kernel story (same as transfer_story).
[CIL · Suggestions only] Suggested next actions from focus, handoff, and intent. is_executable=false — never treat as orders to run. Prefer ask_project(“what should I do next?”) for NL.
[CIL · History] Cognitive events for a module or file path. Requires `module`. Use when asking about a specific area of the codebase.
[CIL · Impact] Blast radius / affected nodes for a module or file. Requires `module`. Prefer inspect_impact for PIL impact graph; use this for CIL module-centric impact.
[CIL · Evolution] Project growth roadmap narrative. Use for long-horizon “how did we get here / where next”.
[Legacy alias · prefer transfer_project mode=story or get_project_story] Same kernel story payload — not a separate Transfer pipeline.
[CIL · Decision Center] Decision DAG (.contora/decisions/graph.json). Prefer inspect_decision for PIL provenance + governance decision together.
[CIL · Time travel] Project snapshot nearest a date (YYYY-MM-DD) or latest if date omitted. Optional perspective: historical | retrospective.
[CIL · Health] Cognitive health score and warnings (missing WHY, stale ADR, conflicts). For decision lifecycle trust prefer get_knowledge_health; for PIL metrics prefer inspect_health.
[CIL · Knowledge] Everything related to an entity/topic (module name, feature, system). Requires `entity`. Prefer ask_project for open-ended questions.
[CIL · Compression] Compressed project essence. Prefer transfer_project(mode=essence) when exporting into a new chat.
[CIL · Replay] Cognitive evolution replay timeline. Use to reconstruct how understanding changed over sessions.
[CIL · DNA] Project identity fingerprint for handoff. Prefer transfer_project(mode=handoff) for session continuity payloads.
[CIL · Prefer for Transfer] Unified export into the current chat. mode: context (~300–800 tok) | intelligence (~8k) | story | essence | handoff. Prefer this over transfer_context / transfer_intelligence / transfer_handoff / transfer_story aliases.
[CIL · Onboarding] Suggested Ask Contorium questions. Call when starting exploration or the user asks what they can ask.
[CIL · Lifecycle · Prefer] Knowledge Health + per-decision trust (.contora/lifecycle/). Call when checking if decisions are still valid / project knowledge freshness.
[CIL · Lifecycle · Prefer] Decisions needing review (stale, expired, conflict, missing owner, invalidation). Call before trusting old ADRs; pair with set_decision_lifecycle_meta after human verify.
[CIL · Lifecycle · Write] Update decision owner, verification, or expiry → .contora/lifecycle/. Side effect: persists meta and refreshes knowledge lifecycle index. Requires decision_id.
[CIL · AI Layer] LLM explanation-layer status — enabled flag, provider, model, module switches, intent router mode. Does not expose API keys.
[CIL · AI Layer] Test LLM provider connectivity using workspace llm.json + api_key_env. Returns ok/latency/message.
Store important coding context into Contorium memory (persisted under .contora/mcp/).
Search Contorium MCP memory entries by keyword.
Get a Contorium MCP memory entry by exact key.
Read Contorium workspace snapshot from .contora/state.json (current focus, notes, files, Git) written by the VS Code/Cursor extension.
Read Contorium v0.7 derived project understanding from .contora/intelligence/state-summary.json (written by the extension cognition layer).
[Legacy · prefer inspect_intent] Old intent graph at .contora/intent-graph/graph.json (not vNext). Use inspect_intent for .contora/intent/intent_graph.json.
Return ACTIVE / WEAKENING / PARTIAL intent nodes from the Contorium intent graph (compact summary for agents).
Read Contorium State Builder structured project state from .contora/state-builder/project-state.json (goal, stage, decisions, problems, next actions).
Read Contorium PROJECT SNAPSHOT markdown from .contora/state-builder/project-snapshot.md for cross-AI project continuity.
Read Contorium v2 unresolved state conflicts from .contora/state-engine/conflicts.json (audit only — system does not auto-resolve).
Read Contorium V3.1 change semantics from .contora/change.json (changed files + key symbol changes).
Read Contorium V3 change-neighborhood project graph from .contora/graph.json (functions, classes, imports around recent changes).
Read Contorium V3.1 Project Knowledge Graph from .contora/graph/knowledge.json (Intent → Module → File → Function + intent mappings).
Read Contorium V3.1 cognitive snapshot from .contora/graph/snapshot.json — compact summary for AI Handoff (top intents, hotspots, functions).
[Deprecated V3.1] Impact merged into handoff.json — returns impact_summary from handoff or legacy impact.json.
[Legacy · prefer inspect_intent] Compact intent summary artifact. Prefer inspect_intent (vNext graph) or ask_project for NL.
[Prefer · New chat] Call at the start of a new session: check if runtime handoff injection is pending. If pending=true, ask the user then call confirm_handoff_injection (Y) or skip_handoff_injection (N). Else use transfer_project(mode=context) if continuity is needed.
[Write · New chat] After user confirms (Y): write .contora/mcp.auto-context.md and mark injection done. Optional format: json | markdown | compact (default markdown). Side effect: persists context file.
[Write · New chat] User declined injection (N). Marks skip for this runtime session; get_project_handoff / transfer_project remain available on demand.
CHP v1 get_handoff — read unified AI handoff from Contorium Runtime (.contora/handoff.json + state). For new chats prefer get_handoff_injection_status → user confirm → confirm_handoff_injection.
Read Contorium V3.1 code evolution timeline from .contora/timeline.json (recent commits + symbol changes).
[MCP v1 standard] Recent file/function changes from .contora/change.json — alias of get_project_change.
[MCP v1 standard] Runtime understanding graph — call chains + impact from .contora/understanding_graph.json.
[MCP v1 standard] Runtime session view — bootstrap, dashboard worker, session marker (read-only).
概要
What is Contorium?
Contorium is a Runtime Cognitive Cortex for AI-assisted development that maintains awareness of workspace state, project history, runtime events, and development context. It follows the principle Observe → Understand → Suggest and provides a persistent runtime layer to help developers and AI assistants stay aligned throughout the development workflow.
How to use Contorium?
—
Key features of Contorium
- Observes workspace and development context continuously
- Does not execute actions or take control of the workflow
- Follows the Observe → Understand → Suggest cycle
- Provides persistent runtime awareness for AI systems
- Maintains continuity across files, terminals, and sessions
Use cases of Contorium
- Keeping AI assistants aware of ongoing project state and history
- Aligning developer and AI understanding during complex tasks
- Reducing context fragmentation across multiple development sessions
よくある質問
What principle does Contorium follow?
Contorium follows a simple three-step cycle: Observe → Understand → Suggest.
What kind of context does Contorium track?
It tracks workspace state, project history, runtime events, and overall development context to maintain a persistent cognitive layer.
How does Contorium differ from other AI coding assistants?
Unlike tools that directly perform actions, Contorium stays in a suggestion-only role, providing a runtime awareness layer rather than taking control of the environment.
「その他」の他のコンテンツ
Codelf
unbugA search tool helps dev to solve the naming things problem.
14.2K
Yuppsy
Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
P
PickFu MCP
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
23.2K
Blender
ahujasidOpen-source MCP to use Blender with any LLM
23.6K
コメント