A command for testing an MCP server locally with MCP Inspector. MCP Inspector is a tool that lets developers discover and call the tools exposed by an MCP server.

Use it to start the local server, connect to its MCP endpoint, inspect available tools, test normal and edge-case inputs, check OAuth, and record pass or fail results.

It helps find incorrect tool descriptions, parameters, responses, error handling, and authentication before deployment.

test-mcp — Command for Claude Code by superbenefit

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/superbenefit/sb-marketplace

Made for: Claude Code.

Or install cloudflare-dev, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 3 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/superbenefit/sb-marketplace/test-mcp/github.svg)](https://agentmods.dev/commands/superbenefit/sb-marketplace/test-mcp)

Your own site

<a href="https://agentmods.dev/commands/superbenefit/sb-marketplace/test-mcp"><img src="https://agentmods.dev/badge/commands/superbenefit/sb-marketplace/test-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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/superbenefit/sb-marketplace/test-mcp"><img src="https://agentmods.dev/badge/commands/superbenefit/sb-marketplace/test-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 377 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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.00377
Opus 5	$0.00006	$0.00188
Sonnet 5	$0.00003	$0.00075
Haiku 4.5	$0.00001	$0.00038

Measured 8d ago against content hash ebfbeab3305e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

test-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 8d 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.

cloudflare-dev/commands/test-mcp.md · 56 lines

What it actually says

Test MCP Server

Test the MCP server implementation using the MCP Inspector.

Steps

Start the dev server:
```
npm run dev
```
Launch MCP Inspector (in a new terminal):
```
npx @modelcontextprotocol/inspector
```
Connect to the MCP endpoint:
- Default URL: http://localhost:8787/mcp
- If using custom port/path from $ARGUMENTS, connect to that instead
Verify tool discovery:
- List all available tools
- Confirm each tool has a description and parameter schema
- Check that tool names match expectations
Test each tool:
- Invoke with valid parameters and verify responses
- Invoke with edge cases (empty strings, missing optional params)
- Verify error responses include isError: true
Test authentication (if OAuth configured):
- Verify unauthenticated requests are rejected
- Test the OAuth flow end-to-end
- Verify getMcpAuthContext() returns user identity
Report results:
- List all tools tested with pass/fail status
- Note any unexpected behaviors or errors
- Suggest fixes for any failures

Usage

/test-mcp $ARGUMENTS

$ARGUMENTS optionally specifies the endpoint. Examples:

/test-mcp - Test at default http://localhost:8787/mcp
/test-mcp http://localhost:8788/mcp - Custom port
/test-mcp /sse - Test SSE endpoint (legacy)

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.

8d ago First seen · 56 lines · 13 tokens per session scan A ebfbeab3305e

Subscribe to this mod's changes

test-mcp is a command published in the GitHub repository superbenefit/sb-marketplace (5 stars, last pushed 7mo ago), licensed CC0-1.0. It adds 13 tokens to every session and 377 once invoked, about $0.0001 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.

Testing

verify

Run repository verification using the verification-loop skill.

cloudnative-co/claude-code-starter-kit · 9 tokens

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

test-mcp