agentmods.dev

test-mushi-mcp

A command that checks whether the Mushi MCP server is reachable and advertises the expected tools, resources, and prompts. Mushi is a service for collecting and investigating user bug reports.

In plain words
What is it for?
Use it to verify the server connection, confirm a project is available, inspect its status, read recent error logs, and diagnose missing or invalid Mushi settings.
Why use it?
It quickly separates connection, authentication, project-selection, and installation problems from problems in your code. It reports useful checks such as available tools, projects, SDK status, and recent pipeline errors.

Command

3 4d ago A scan 0 tokens original MIT
View the source file kensaurus/mushi-mushi
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.

agentmods
npx agentmods add commands/kensaurus/mushi-mushi/test-mushi-mcp
Clone the repo
git clone --depth 1 https://github.com/kensaurus/mushi-mushi
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 360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00360
Opus 5 $0.00000 $0.00180
Sonnet 5 $0.00000 $0.00072
Haiku 4.5 $0.00000 $0.00036

Measured yesterday against content hash e6dac2cbdd8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-mushi-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 yesterday.

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.

packages/cursor-plugin/commands/test-mushi-mcp.md · 25 lines

What it actually says

Test Mushi MCP

Verify that the Mushi MCP server is reachable and all expected tools/resources/prompts are advertised correctly.

Steps

  1. Call list_projects — confirm it returns at least one project and shows a valid name and id.
  2. Call get_recent_reports { limit: 1 } — confirm you get a valid response (even if empty).
  3. Call get_project_context { project_id: "<id from step 1>" } — confirm preflight and activation fields are present.
  4. Call get_pipeline_logs { project_id: "<id>", level: "error", limit: 5 } — confirm the response has an entries array.
  5. Report back:
    • ✅ Connected — {toolCount} tools available
    • ✅ list_projects returned {N} project(s)
    • ✅ get_recent_reports returned {N} report(s)
    • ✅ get_project_context shows SDK status: {heartbeat}
    • ✅ get_pipeline_logs returned {N} recent entries
    • ❌ Any errors encountered

Troubleshooting

  • UNAUTHENTICATED / 401: MUSHI_API_KEY is missing or invalid. Mint a new mcp:read key at your Mushi project settings.
  • PROJECT_REQUIRED: Set MUSHI_PROJECT_ID in your environment or pass project_id explicitly.
  • No tools listed: The MCP server binary may not be installed. Run npx @mushi-mushi/mcp manually to check.
  • Hosted HTTP 404: Verify the edge function URL in your mcp.json matches your Supabase project URL.
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. yesterday First seen · 25 lines · 0 tokens per session scan A e6dac2cbdd8f

Subscribe to this mod's changes

test-mushi-mcp is a command published in the GitHub repository kensaurus/mushi-mushi (3 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 360 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 2026-08-31.

Data and AIDebuggingTestingangularauto-fixbug-reportingclaude-codefeedback-widgetllm-ops
Related

Other commands, from other repositories

gh-issue-plan

This command provides guidance for both automated and manual GitHub issue workflows.

nrwl/nx · 0 tokens

commit

Create a git commit following Nx repository standards and validation requirements.

nrwl/nx · 0 tokens

issue-workflow-guide

If you need to work on an issue manually, use the /gh-issue-plan command for structured guidance following the same workflow patterns.

nrwl/nx · 0 tokens

migrate-example

Migra un ejemplo de Web Worker al dominio neutral y lo renderiza en los 5 themes (pipeline punta a punta con loop de design-review).

damiansire/web-worker-patterns · 30 tokens

plan

Run /plan — see .claude/commands/plan.md for the authoritative spec.

loiane/specs-driven-development-spring-angular · 18 tokens

pipeline

Use when you want to resolve all PR feedback autonomously in a single pass. Do NOT use for draft PRs or when you need manual control over individual fixes.

juanmhidalgo/claude-plugins · 33 tokens