mash-multi-agent-software-harness vs SmartBear MCP
mash-multi-agent-software-harness is a plugin bundle for AI coding tools published by dmarchevsky. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). SmartBear MCP is an MCP server published by smartbear.com. Marketplaces we read that list it: 2 (Official MCP Registry, Docker MCP Catalog). As of our marketplace pass on 2026-10-17. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  mash-multi-agent-software-harness |  SmartBear MCP |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 0.1.0 Forks (GitHub): 0 Stars (GitHub): 2 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.42.0 Downloads/month (npm): 47 525 Downloads/week (npm): 10 500 Forks (GitHub): 50 Stars (GitHub): 44 Not marked · First seen |
| Docker MCP Catalog | Not listed | Listed Version: sha256:8a64acae01b6 Forks (GitHub): 50 Pulls (Docker Hub): 14 363 Stars (Docker Hub): 0 Stars (GitHub): 44 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | mash-multi-agent-software-harness | SmartBear MCP |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 2 (better) |
| Stars (GitHub) (differs) | 2 (worse) | 44 (better) |
| Pulls (Docker Hub) (differs) | No figure on Docker Hub | 14 363 |
| Forks (GitHub) (differs) | 0 (worse) | 50 (better) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | Remote server or your machine |
| Transport (differs) | Not stated | Streamable HTTP, stdio |
| Tools it declares (differs) | Not published | 160 |
| Environment variables it asks for (differs) | Not published | 17, secrets among them: 10 |
| Parts of the bundle (differs) | 1 | Not a bundle |
| Licence (differs) | Not stated | MIT |
| Repository (differs) | github.com/dmarchevsky/mash | github.com/smartbear/smartbear-mcp |
| Changes in the last 7 days | 0 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Answered with HTTP 400 (less than an hour ago) |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
mash-multi-agent-software-harness
MASH (Multi-Agent Software Harness) is a structured development framework for Claude Code that manages the full software lifecycle — from idea to tested, committed code. It orchestrates four specialized AI personas (Init, Plan, Dev, QA) that work in sequence with strict boundaries: planning personas interact with you to capture intent, while implementation personas run as isolated sub-agents that write code and tests autonomously. Features are tracked through a clear lifecycle (CREATED → DEV_READY → WIP → DONE), with automatic retry logic (up to 3 attempts) and failure analysis fed back into subsequent attempts. All specs live in .mash/plan/ as the single source of truth — immutable during development. Key features: - Interactive planning that asks clarifying questions before writing specs - Isolated dev and QA sub-agents with strict read/write boundaries - Git workflow options: per-feature worktrees or current branch - Auto-commit after QA pass, or manual git control - Feature retry with failure context prop
SmartBear MCP
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
How to run each
mash-multi-agent-software-harness As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install mash-multi-agent-software-harness@claude-communitySmartBear MCP As a remote MCP server
claude mcp add --transport http smartbear-mcp https://bugsnag.mcp.smartbear.com/mcpRequires: BEARQ_API_TOKEN (secret), BUGSNAG_AUTH_TOKEN (secret), PACT_BROKER_PASSWORD (secret), PACT_BROKER_TOKEN (secret), QTM4J_API_KEY (secret), QTM4J_AUTOMATION_API_KEY (secret), REFLECT_API_TOKEN (secret), SWAGGER_API_KEY (secret), SWAGGER_FUNCTIONAL_TESTING_API_TOKEN (secret), ZEPHYR_API_TOKEN (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only SmartBear MCP has a remote endpoint we check. How we check endpoints
Tools each declares
The marketplaces of mash-multi-agent-software-harness publish no list of tools, so we do not compare tools.
Settings each asks for
The marketplaces of mash-multi-agent-software-harness publish no settings it asks for, so we do not compare settings.
What it can do: mash-multi-agent-software-harness · What it can do: SmartBear MCP · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.