trust-mcp

trust-mcp is a command for Claude Code from smrafiz/claude-supercharger. It costs 0 tokens per session (266 once invoked), scanned A, original, MIT.

A command for managing which external tool servers may request passwords, tokens, or API keys through credential forms. It can show the trusted list, add a server, or remove one.

In plain words
What is it for?
Use it to review trusted servers, trust a known server, or remove a server's permission to request credentials.
Why use it?
It adds a deliberate approval step before a server can present a credential request, helping prevent unexpected requests from being accepted.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

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 supercharger plugin — 37 commands, 10 agents, 28 hooks shipped together

Good fit Use it to review trusted servers, trust a known server, or remove a server's permission to request credentials.

Compare 6 commands 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 smrafiz/claude-supercharger
Claude Code
/plugin install supercharger

Made for: Claude Code.

Or install supercharger, the plugin that ships this one along with the rest of its 37 commands, 10 agents, 28 hooks.

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 trust-mcp

README.md
[![agentmods](https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/trust-mcp/github.svg)](https://agentmods.dev/commands/smrafiz/claude-supercharger/trust-mcp)
Your own site
<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/trust-mcp"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/trust-mcp/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 trust-mcp

Your own site · 80×15
<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/trust-mcp"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/trust-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 266 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 $0.00000 $0.00266
Opus 5 $0.00000 $0.00133
Sonnet 5 $0.00000 $0.00053
Haiku 4.5 $0.00000 $0.00027

Measured 12d ago against content hash 9013598998ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

trust-mcp 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 12d 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.

commands/trust-mcp.md · 19 lines

What it actually says

Trust an MCP server to request credentials via Elicitation forms. Argument: $ARGUMENTS (a server name, or --list, or --remove <server>)

Supercharger's elicitation-guard declines any MCP server that asks for a password / token / API-key — in a form field or in the prompt text — via an Elicitation dialog, unless that server is trusted. Use this command to trust a server you recognize (e.g. your own database or GitHub MCP) so its legitimate credential prompts go through.

Run it:

bash ${CLAUDE_PLUGIN_ROOT}/tools/trust-mcp.sh $ARGUMENTS

Then report the tool's output verbatim.

  • No argument → show the current trusted list and the usage.
  • /trust-mcp <server> → trust that server (matches the MCP server name the guard sees).
  • /trust-mcp --list → list trusted servers.
  • /trust-mcp --remove <server> → untrust a server.

Security note: only trust servers you recognize. A trusted server can request credential fields without being declined — that is the entire protection you are turning off for it. If you didn't expect a credential prompt, do NOT trust the server; investigate it instead.

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. 12d ago First seen · 19 lines · 0 tokens per session scan A 9013598998ac

Subscribe to this mod's changes

trust-mcp is a command published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 266 tokens. 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 2026-08-30.