teardown-mcp-registration

teardown-mcp-registration is a skill for Claude Code from runverdict/sf-security-review-toolkit. It costs 85 tokens per session (3,990 once invoked), scanned A, original, Apache-2.0.

A cleanup procedure for removing every part of an MCP server registration from a temporary Salesforce organization. MCP is a way for an agent to connect to external tools.

In plain words
What is it for?
Use it before and after a deployed-package security audit to prepare a clean throwaway organization and remove the server registration in the required dependency order.
Why use it?
Partial removal can leave references and permissions behind, causing later audits or tool activation to fail.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sf-security-review-toolkit plugin — 14 skills, 1 hook shipped together

Good fit Use it before and after a deployed-package security audit to prepare a clean throwaway organization and remove the server registration in the required dependency order.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add runverdict/sf-security-review-toolkit
Claude Code
/plugin install sf-security-review-toolkit

Made for: Claude Code.

Or install sf-security-review-toolkit, the plugin that ships this one along with the rest of its 14 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for teardown-mcp-registration

README.md
[![agentmods](https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/teardown-mcp-registration/github.svg)](https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/teardown-mcp-registration)
Your own site
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/teardown-mcp-registration"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/teardown-mcp-registration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for teardown-mcp-registration

Your own site · 80×15
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/teardown-mcp-registration"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/teardown-mcp-registration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,990 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.03990
Opus 5 $0.00043 $0.01995
Sonnet 5 $0.00017 $0.00798
Haiku 4.5 $0.00009 $0.00399

Measured 11d ago against content hash d6a360e30fbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

teardown-mcp-registration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/teardown-mcp-registration/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teardown MCP Registration

Adapted from the author's ISV-lifecycle tranche contributed to mvogelgesang/sf-mcp-partner-toolkit (Apache-2.0); see CREDITS.md.

Remove every trace of an MCP server registration. Naive deletion attempts chain into setup object in use / referenced elsewhere errors — the components reference each other, and the order below is the one that works. One MCP registration per server per org, ever: an org carrying two registrations of the same server (same label, same tool names) breaks instantly, and the residue keeps poisoning runtime enablement even after partial cleanup.

Role in the autonomous deep audit

This skill bookends the deployed-org deep audit on both sides, and is opt-in and CLI-gated like the rest of it (invoked only when sf is authed and the operator opted into auditing the deployed package):

  • Clean-org provisioning (before install): ensures the throwaway target org is pristine — a contaminated org silently filters a correctly-installed package's tools, so an audit run there is worthless. The orchestrator routes here before /sf-security-review-toolkit:install-and-verify-package whenever the org has registration history.
  • Zero-residue teardown (after the audit): removes the package and every registration trace once the deployed-artifact evidence is captured — the uninstall half of the cycle the Salesforce reviewer also runs, so leftover-metadata and failed-handler problems surface here too.

Consumes: an authenticated target org from /sf-security-review-toolkit:bootstrap-cli-auth, and the registration/component names.

When to use

  • Before installing the package into any throwaway org that hand-registered the same MCP server, or that has registration history — /sf-security-review-toolkit:install-and-verify-package step 1 routes here when its contamination check finds a hand registration.
  • After the deployed-package audit, to tear the installed package and its registration down to nothing (the uninstall half of the reviewer's install/uninstall cycle).
  • Duplicate-registration recovery: a previously-working agent broke with tool validation failed while setting up the external MCP connection the moment a second registration of the same server appeared.
  • Contamination recovery when stale registry state from prior create/delete/rename cycles is silently filtering tools (the standalone agent-runtime diagnostic that pinpoints this lives in the sibling sf-mcp-partner-toolkit).

Read the full file on GitHub · 227 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 227 lines · 85 tokens per session scan A d6a360e30fbe

Subscribe to this mod's changes

teardown-mcp-registration is a skill published in the GitHub repository runverdict/sf-security-review-toolkit (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 3,990 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.