SpecLock - AI Constraint Engine — Claude Code MCP server
The SpecLock - AI Constraint Engine MCP server stores project constraints, reviews proposed changes, and blocks conflicts. It fits AI coding workflows that need explicit guardrails.
no license 3,564 installs updated 2026-02-25
claude mcp add --transport http speclock https://speclock--sgroy10.run.toolsWhat SpecLock - AI Constraint Engine does
SpecLock keeps a project goal, design decisions, pinned notes, deployment facts, and non-negotiable constraints in one context store. Its 42 MCP tools can return that context, track changes, test a proposed action against active locks, and detect drift. Enforcement can warn or block.
The server also audits staged files, runs semantic checks before commits, records justified lock overrides, and creates named git checkpoints. It includes typed constraints, policy rules, an HMAC audit chain, compliance exports for SOC 2, HIPAA, and CSV, plus an import-based dependency graph for JS, TS, and Python. Converting PRDs or READMEs into structured constraints uses Gemini Flash. Hard mode blocks actions above its threshold, so rules need to match the project before enforcement is enabled.
What it helps with
- store non-negotiable project constraints
- check a proposed change against active locks
- spot requirement drift in recent changes
- audit staged files before a commit
- calculate the impact of a dependency change
Example prompts for the agent
- Initialize SpecLock in the current project with
speclock_init, then set the project goal. - Add a database schema constraint with
speclock_add_lockand check a proposed change usingspeclock_check_conflict. - Run a semantic review of the staged changes with
speclock_semantic_audit, then generate the result withspeclock_report.
How to install SpecLock - AI Constraint Engine
Platform CLI: remote server
claude mcp add --transport http speclock https://speclock--sgroy10.run.toolsPlatform CLI: remote server
codex mcp add speclock-ai-constraint-engine --url https://speclock--sgroy10.run.toolsConfig file
{
"mcpServers": {
"speclock-ai-constraint-engine": {
"url": "https://speclock--sgroy10.run.tools"
}
}
}Config file
{
"servers": {
"speclock-ai-constraint-engine": {
"type": "http",
"url": "https://speclock--sgroy10.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http speclock-ai-constraint-engine https://speclock--sgroy10.run.toolsStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about SpecLock - AI Constraint Engine
How do I install SpecLock - AI Constraint Engine in Claude Code?
Run claude mcp add --transport http speclock https://speclock--sgroy10.run.tools.
What does SpecLock - AI Constraint Engine do?
It stores project constraints and decisions, supplies structured context, reviews changes, and can block actions that violate active rules.
What is the difference between advisory and hard enforcement?
Advisory mode issues a warning when a rule is violated. Hard mode blocks actions that pass the configured threshold.