Medium Risk

sdd_auto_pipeline

FULLY AUTOMATED: Reads a meeting transcript, extracts requirements, and runs the complete SDD pipeline in one call. Creates CONSTITUTION.md, SPECIFICATION.md, DESIGN.md, TASKS.md, and ANALYSIS.md from a single transcript file. Supports VTT (Teams), SRT (Zoom), TXT, and MD formats.

How to control sdd_auto_pipeline ↓

What sdd_auto_pipeline does on Specky

AI agents use sdd_auto_pipeline to create or update resources in Specky — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Specky environment.

Medium Risk

Why sdd_auto_pipeline needs a policy

The tool reads input (a transcript file) and creates multiple new files as output artifacts. This is a Write operation — it generates and writes several project files. While it reads a source file, its primary effect is creating new documents.

From the tool's definition Creates CONSTITUTION.md, SPECIFICATION.md, DESIGN.md, TASKS.md, and ANALYSIS.md from a single transcript file

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

How to control sdd_auto_pipeline

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_auto_pipeline:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "sdd_auto_pipeline": {
      "limits": [
        {
          "counter": "sdd_auto_pipeline_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

sdd_auto_pipeline 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.

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

Free to start. No card required.

Related tools and policies

Go deeper

Questions about sdd_auto_pipeline

What does the sdd_auto_pipeline tool do? +

FULLY AUTOMATED: Reads a meeting transcript, extracts requirements, and runs the complete SDD pipeline in one call. Creates CONSTITUTION.md, SPECIFICATION.md, DESIGN.md, TASKS.md, and ANALYSIS.md from a single transcript file. Supports VTT (Teams), SRT (Zoom), TXT, and MD formats. 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_auto_pipeline? +

Register the Specky MCP server in PolicyLayer and add a rule for sdd_auto_pipeline: 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_auto_pipeline? +

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

Can I rate-limit sdd_auto_pipeline? +

Yes. Add a rate_limit block to the sdd_auto_pipeline 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_auto_pipeline completely? +

Set action: deny in the PolicyLayer policy for sdd_auto_pipeline. 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_auto_pipeline? +

sdd_auto_pipeline 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.

Free to start. No card required.

56 Specky tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.