update_spec · Speclib MCP: Risk & Policy

WHAT IT DOES

What update_spec does on Speclib

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

WHY IT NEEDS A POLICY

Why update_spec needs a policy

This tool modifies existing specifications by replacing their content, which qualifies as Write category (creates or modifies data reversibly). It is not Destructive because changes can be reviewed and are not irreversible. Severity is medium because unauthorized spec modifications could corrupt documentation but are subject to owner review and approval before taking effect.

From the tool's definition Tool description states 'Update an existing spec' and 'replacing the entire spec', indicating modification of data. For non-owners, it creates a 'pending revision' rather than direct overwrite, which is a reversible change subject to review.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_spec Rate-limited

update_spec 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.

View as policy code

policy.json

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

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Speclib, so you can run agents against it safely.

FAQ

Questions about update_spec

What does the update_spec tool do? +

Update an existing spec. Content must be a full frontmatter+body markdown document replacing the entire spec. If you are not the owner, this creates a pending revision for the owner to review. Requires SPECLIB_API_TOKEN. It is categorised as a Write tool in the Speclib MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_spec? +

Register the Speclib MCP server in PolicyLayer and add a rule for update_spec: 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 Speclib. Nothing to install.

What risk level is update_spec? +

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

Can I rate-limit update_spec? +

Yes. Add a rate_limit block to the update_spec 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 update_spec completely? +

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

update_spec is provided by the Speclib MCP server (rang501/speclib-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.