declare_constraint — VaultCrux Memory Core MCP Tool
declare_constraint
(declare constraint) is one of 75 tools on the
VaultCrux Memory Core
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call declare_constraint from your client
- Claude Code VaultCrux Memory Core declare_constraint run in your project directory
- Claude Desktop VaultCrux Memory Core declare_constraint ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor VaultCrux Memory Core declare_constraint ~/.cursor/mcp.json
- VS Code VaultCrux Memory Core declare_constraint .vscode/mcp.json
- Zed VaultCrux Memory Core declare_constraint ~/.config/zed/settings.json
- Windsurf VaultCrux Memory Core declare_constraint ~/.codeium/windsurf/mcp_config.json
- Cline VaultCrux Memory Core declare_constraint ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI VaultCrux Memory Core declare_constraint ~/.gemini/settings.json
- Grok VaultCrux Memory Core declare_constraint .mcp.json (in your project root)
- ChatGPT VaultCrux Memory Core declare_constraint Settings → Connectors → Advanced → Developer mode
- Claude.ai VaultCrux Memory Core declare_constraint Settings → Connectors → Add custom connector
- LangChain VaultCrux Memory Core declare_constraint pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http vaultcrux-memory-core https://api.vaultcrux.com/memory-core/mcpOther tools on this server
- query_memory
- list_topics
- get_versioned_snapshot
- get_audit_trail
- check_claim
- memory_claim_check
- get_freshness_report
- memory_freshness_report
- get_contradictions
- get_decision_context
- get_causal_chain
- reconstruct_knowledge_state
- get_correction_chain
- get_decisions_on_stale_context
- record_decision_context
- get_pressure_status
- get_active_alerts
- get_signals_feed
- update_constraint
- get_constraints
- check_constraints
- verify_before_acting
- suggest_constraint
- checkpoint_decision_state
- get_checkpoints
- assess_coverage
- get_relevant_context
- escalate_with_context
- get_platform_capabilities
- admit_character_kernel_entry
- get_character_kernel
- assess_character_drift
- issue_passport
- get_passport
- sync_pull
- sync_push
- submit_skill
- promote_skill
- dismiss_skill
- retract_skill
- session_debrief
- get_domain_changelog
- get_my_tasks
- get_task_context
- log_progress
- register_external_service
- request_credentialed_call
- list_external_services
- enumerate_memory_facts
- build_timeline
- expand_hit_context
- assess_answerability
- derive_from_facts
- extract_facts_from_sessions
- compare_versions
- get_session_dossiers
- investigate_question
- submit_correction
- get_enrichment_status
- get_knowledge_gaps
- fill_gap
- declare_available_models
- get_escalation_recommendation
- get_incident_context
- get_architecture_rationale
- check_deploy_readiness
- get_operator_profile
- update_operator_profile
- run_elicitation
- answer_elicitation
- get_operating_rhythms
- assess_delegation_readiness
- provision_agent_context
- decompose_expertise
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.