sdd_checkpoint

THE RISK

Medium Risk

Why sdd_checkpoint needs a policy

This tool creates snapshots of specification artifacts. While it does not delete or overwrite existing artifacts (ruling out Destructive), and does not execute code or external operations (ruling out Execute), it does create and store new data structures (checkpoints) in the system. This is a Write operation since it adds reversible data to the checkpoint system.

From the tool's definition Creates a named snapshot of all spec artifacts (CONSTITUTION.md, SPECIFICATION.md, DESIGN.md, TASKS.md, etc.) - the tool persists new checkpoint data that can be retrieved and restored, representing a write operation that modifies the system state by adding a…

Documented attack patterns abuse exactly the kind of access sdd_checkpoint gives an agent:

POLICY

How to control sdd_checkpoint

PolicyLayer is an MCP gateway — it sits between your AI agents and Specky, and nothing reaches the server without passing your rules. This is the rule we recommend for sdd_checkpoint:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sdd_checkpoint": {
      "limits": [
        {
          "counter": "sdd_checkpoint_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

sdd_checkpoint stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Specky — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Specky tools

Execute sdd_validate_iac Generates a validation payload for Terraform MCP (plan/validate) or Azure MCP (template va Execute sdd_advance_phase Validates that the current phase Execute sdd_setup_local_env Detects the project tech stack and generates a Docker-based local development environment Write sdd_run_analysis Reads all spec files, generates ANALYSIS.md with traceability matrix and coverage report, Write sdd_auto_pipeline FULLY AUTOMATED: Reads a meeting transcript, extracts requirements, and runs the complete Write sdd_compliance_check Validates specification and design against a compliance framework (HIPAA, SOC2, GDPR, PCI- Write sdd_cross_analyze Cross-artifact consistency analysis: checks alignment between SPECIFICATION.md, DESIGN.md, Write sdd_verify_tasks Reads TASKS.md and checks code_paths for implementation evidence. Detects phantom completi

All 56 Specky tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about sdd_checkpoint

What does the sdd_checkpoint tool do? +

Creates a named snapshot of all spec artifacts (CONSTITUTION.md, SPECIFICATION.md, DESIGN.md, TASKS.md, etc.). It is categorised as a Write tool in the Specky MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sdd_checkpoint? +

Register the Specky MCP server in PolicyLayer and add a rule for sdd_checkpoint: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Specky. Nothing to install.

What risk level is sdd_checkpoint? +

sdd_checkpoint is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit sdd_checkpoint? +

Yes. Add a rate_limit block to the sdd_checkpoint rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block sdd_checkpoint completely? +

Set action: deny in the PolicyLayer policy for sdd_checkpoint. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides sdd_checkpoint? +

sdd_checkpoint is provided by the Specky MCP server (paulasilvatech/specky). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Specky tool call.

Start from Specky, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →