calling-mcp-tools-via-subprocess SKILL.md skillA

calling-mcp-tools-via-subprocess from andreaswasita/copilot-agents-dojo is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add andreaswasita/copilot-agents-dojo/calling-mcp-tools-via-subprocess@git:20260519.40bb110

Pins git:20260519.40bb110 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
andreaswasita/copilot-agents-dojo
Path
optional-skills/calling-mcp-tools-via-subprocess/SKILL.md
Versions recorded
1
Latest version
git:20260519.40bb110, committed May 19, 2026
Size
5,242 bytes
Repository stars
55
License
MIT

Bypasses a flaky MCP broker by spawning the server directly.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Calling MCP Tools via Subprocess Skill

Bypasses a flaky MCP broker by spawning the server binary directly and speaking JSON-RPC over stdio, using the dojo helpers `mcp/scripts/mcp-subprocess.js` and `mcp-subprocess.ps1`. Does NOT replace `using-mcp` for normal operation — broker is the fast path; subprocess is the reliable fallback.

## When to Use

- Broker shows the server as connected but `tools/call` hangs or times out.
- Building a script (CI job, scheduled refresh, batch backfill) that needs MCP data without an IDE.
- Deterministic agent workflows that must succeed regardless of client flakiness.
- Diagnosing whether a problem is in the broker or in the server itself.
- User says "broker stuck", "tools not loading", "tools_changed notice".

## Prerequisites

- The dojo helpers `mcp/scripts/mcp-subprocess.js` and `mcp/scripts/mcp-subprocess.ps1`.
- The MCP server binary resolvable (npm install or known path).
- Node 18+ on the path.
- Required auth context set in env BEFORE spawning (e.g. `az login`, `gh auth`).
- The `powershell` Copilot tool to run the helper.

## How to Run

```text
1. Resolve the server binary path.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_2j6m6aqsd6k66kqd/a0c9964a3cedf264c8ca6ca0d547cd678ea9b01b86894bb6e68c75e132ad3dee.json

Then /plugin install calling-mcp-tools-via-subprocess@markdownregistry-2j6m6aqsd6k66kqd in Claude Code. It installs git:20260519.40bb110, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add andreaswasita/copilot-agents-dojo/calling-mcp-tools-via-subprocess@sha256:a0c9964a3cedf264

The line at the top of this page pins the label git:20260519.40bb110, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2j6m6aqsd6k66kqd.svg)](https://markdownregistry.com/a/art_2j6m6aqsd6k66kqd)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in andreaswasita/copilot-agents-dojo/calling-mcp-tools-via-subprocess since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of calling-mcp-tools-via-subprocess from somewhere else? Ask it: where did my calling-mcp-tools-via-subprocess come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on May 19, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260519.40bb110 latest2026-05-19 40bb110 5,242 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5242 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

andreaswasita/copilot-agents-dojo · 55 stars · license MIT · pushed 2026-09-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2j6m6aqsd6k66kqd
GET https://markdownregistry.com/api/v1/resolve?ref=andreaswasita/copilot-agents-dojo/calling-mcp-tools-via-subprocess
GET https://markdownregistry.com/api/v1/blob/a0c9964a3cedf264c8ca6ca0d547cd678ea9b01b86894bb6e68c75e132ad3dee

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from andreaswasita/copilot-agents-dojo

copilot-instructions.md
andreaswasita/copilot-agents-dojo · .github/copilot-instructions.md
git:20260608.2eecb66 · audit A · 55 stars
AGENTS.md AGENTS.md file
andreaswasita/copilot-agents-dojo · AGENTS.md
git:20260608.2eecb66 · audit A · 55 stars
building-mcp-servers SKILL.md skill
andreaswasita/copilot-agents-dojo · optional-skills/building-mcp-servers/SKILL.md · Authors an MCP server with the official SDK and gates.
git:20260519.40bb110 · audit A · 55 stars
using-mcp SKILL.md skill
andreaswasita/copilot-agents-dojo · optional-skills/using-mcp/SKILL.md · Wires MCP servers into a Copilot client and verifies them.
git:20260519.40bb110 · audit A · 55 stars
writing-skills SKILL.md skill
andreaswasita/copilot-agents-dojo · optional-skills/writing-skills/SKILL.md · Authors new SKILL.md files that conform to the dojo spec.
git:20260519.40bb110 · audit A · 55 stars
architecture-sketching SKILL.md skill
andreaswasita/copilot-agents-dojo · skills/architecture-sketching/SKILL.md · Defines types and boundaries before implementation.
git:20260907.96d5d9d · audit A · 55 stars
autonomous-bug-fix SKILL.md skill
andreaswasita/copilot-agents-dojo · skills/autonomous-bug-fix/SKILL.md · Reproduces, diagnoses, fixes, and verifies bugs unaided.
git:20260519.40bb110 · audit A · 55 stars
behavioral-foundation SKILL.md skill
andreaswasita/copilot-agents-dojo · skills/behavioral-foundation/SKILL.md · Surfaces the dojo's non-negotiable prime directives.
git:20260606.e73f502 · audit A · 55 stars
brainstorming SKILL.md skill
andreaswasita/copilot-agents-dojo · skills/brainstorming/SKILL.md · Refines rough ideas into approved designs before code.
git:20260519.40bb110 · audit A · 55 stars
code-review SKILL.md skill
andreaswasita/copilot-agents-dojo · skills/code-review/SKILL.md · Reviews diffs by severity to produce actionable feedback.
git:20260519.40bb110 · audit A · 55 stars
codebase-onboarding SKILL.md skill
andreaswasita/copilot-agents-dojo · skills/codebase-onboarding/SKILL.md · Maps an unfamiliar repo before touching its code.
git:20260519.40bb110 · audit A · 55 stars
debugging SKILL.md skill
andreaswasita/copilot-agents-dojo · skills/debugging/SKILL.md · Systematic root-cause investigation for hard bugs.
git:20260519.40bb110 · audit A · 55 stars

Every file in andreaswasita/copilot-agents-dojo

Browse by kind, by grade A, or by owner.