// MCP TOOL REFERENCE

SPECLOCK - AI CONSTRAINT ENGINE TOOLS

44 tools from the SpecLock - AI Constraint Engine MCP Server, categorised by risk level.

View the SpecLock - AI Constraint Engine policy → Token cost: 2,048 tokens →

// ALL 44 SPECLOCK - AI CONSTRAINT ENGINE TOOLS

READ 10 tools

Read speclock_check_conflict Check if a proposed action conflicts with any active SpecLock. In hard mode, blocks above threshold. Read speclock_check_typed Check proposed values against typed constraints. Read speclock_detect_drift Scan recent changes for constraint violations. Read speclock_get_changes Get recent file changes tracked by SpecLock. Read speclock_get_context THE KEY TOOL. Returns the full structured context pack. Read speclock_get_events Get the event log, optionally filtered by type. Read speclock_list_typed_locks List all typed constraints with current thresholds. Read speclock_override_history Show lock override history. Read speclock_repo_status Get current git repository status. Read speclock_verify_audit Verify the integrity of the HMAC audit chain.

WRITE 29 tools

Write speclock_add_decision Record an architectural or design decision. Write speclock_add_lock Add a non-negotiable constraint (SpecLock). Write speclock_add_note Add a pinned note for reference. Write speclock_add_typed_lock Add typed constraint (numerical/range/state/temporal). Write speclock_apply_template Apply a pre-built constraint template (nextjs, react, express, supabase, stripe, security-hardened). Write speclock_audit Audit staged files against active locks. Write speclock_auto_guard Auto-guard files related to lock keywords. Write speclock_blast_radius Calculate blast radius — transitive dependents, impact %, depth. Write speclock_checkpoint Create a named git tag checkpoint for easy rollback. Write speclock_export_compliance Generate compliance reports (SOC 2, HIPAA, CSV). Write speclock_guard_file Add SPECLOCK-GUARD header to lock specific files. Write speclock_health Health check with completeness score and multi-agent timeline. Write speclock_init Initialize SpecLock in the current project directory. Write speclock_log_change Manually log a significant change. Write speclock_map_locks Map active locks to actual code files via the dependency graph. Write speclock_override_lock Override a lock with justification. Logged to audit trail. Write speclock_policy_evaluate Evaluate policy-as-code rules against proposed actions. Write speclock_policy_manage Policy CRUD: list, add, remove policy rules. Write speclock_report Violation report — how many times SpecLock blocked changes. Write speclock_review_patch ALLOW/WARN/BLOCK verdict — combines semantic conflict + lock-file mapping + blast radius. Write speclock_review_patch_diff Diff-native review — parses actual diffs for interface breaks, protected symbols, dependency drift, schema ... Write speclock_semantic_audit Semantic pre-commit: analyzes code changes vs locks. Write speclock_session_summary End the current session and record what was accomplished. Write speclock_set_deploy_facts Record deployment configuration facts. Write speclock_set_enforcement Set enforcement mode: advisory (warn) or hard (block). Write speclock_set_goal Set or update the project goal. Write speclock_suggest_locks AI-powered lock suggestions based on project patterns. Write speclock_telemetry Opt-in usage analytics summary. Write speclock_update_threshold Update typed lock thresholds dynamically.

DESTRUCTIVE 1 tools

Destructive speclock_remove_lock Remove (deactivate) a SpecLock by its ID.

EXECUTE 4 tools

Execute speclock_build_graph Build/refresh code dependency graph from imports (JS/TS/Python). Execute speclock_compile_spec Compile natural language (PRDs, READMEs) into structured constraints via Gemini Flash. Execute speclock_parse_diff Parse unified diff into structured changes — imports, exports, symbols, routes, schema detection. Execute speclock_session_briefing Start a new session and get a full briefing.

// FAQ

How many tools does the SpecLock - AI Constraint Engine MCP server have? +

The SpecLock - AI Constraint Engine MCP server exposes 44 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on SpecLock - AI Constraint Engine tools? +

Route the SpecLock - AI Constraint Engine server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do SpecLock - AI Constraint Engine tools fall into? +

SpecLock - AI Constraint Engine tools are categorised as Read (10), Write (29), Destructive (1), Execute (4). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.