Agent Qa MCP Server
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
Agent Qa scores 47 (Fair), licensed FSL-1.1-ALv2 and written in TypeScript. It installs as a local process. It does not declare tools yet. Filed under AI and memory. GitHub shows 910 stars. Install configs are generated for 10 clients. Being listed in the registry is not the same as being vendor-official.
Fair trust
47 of 100 from six public signals. Nobody can buy a point.
- License present: fsl-1.1-alv2.
License, quality and maintenance
License: Grade D
FSL-1.1-ALv2 is source-available, not open source: use is restricted.
How license is gradedQuality: Grade D
48/100 for listing completeness. Lost points: short README, no listed tools, no docs link.
How quality is graded
Where the 47 comes from
0 + 20 + 10 + 6 + 4 + 7 = 47. Each factor is capped, so no single signal can carry a listing.
Active in the official MCP registry, plus a known vendor namespace.
Registry: 0 of 30 points.How recently the repository saw a commit or release.
Maintenance: 20 of 20 points.GitHub stars and weekly downloads, on a log scale.
Popularity: 10 of 20 points.A clear, OSI-style open-source license.
License: 6 of 10 points.Not archived, a secure install path, a pinned version.
Security: 4 of 10 points.A real summary, a README with depth, listed tools.
Docs: 7 of 10 points.Install
Pick your client, copy the config, paste it in.
Needs Cursor or VS Code installed on this device. The button opens the app and asks you to confirm before it adds the server.
{ "mcpServers": { "vostride-agent-qa": { "command": "npx", "args": [ "-y", "agent-qa" ] } }}
Environment variables
This server does not declare environment variables.
Tools
All capabilitiesTools show up when the registry metadata or the repository README lists them. Public READMEs are read directly. A GitHub token is used only when one is already configured.
About
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
Frequently asked questions
What is Agent Qa MCP Server?
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
How do I install Agent Qa MCP Server in Claude Desktop, Cursor, or VS Code?
Pick your client in the Install section on this page and copy the generated config into the client's config file. Step-by-step guides: Claude Desktop, Cursor, and VS Code. Agent Qa MCP Server runs locally from the npm package agent-qa with the command npx -y agent-qa.
Is Agent Qa MCP Server free and open source?
Agent Qa MCP Server is released under the FSL-1.1-ALv2 license, which is not on MCPpedia's list of OSI-approved open-source licenses. Read the license terms before using it, especially commercially.
Does Agent Qa MCP Server support remote (HTTP) connections?
No remote endpoint is listed for Agent Qa MCP Server. It runs locally on your machine over stdio, started by your MCP client.
How is Agent Qa MCP Server's trust score calculated?
Agent Qa MCP Server scores 47 out of 100 (Fair). The score adds six capped public signals: registry status, maintenance, popularity, license, documentation, and security. Nobody can pay for points. Read the methodology for the full formula.
Reviews
No reviews yet—Be the first to review
No published reviews yet. Used it? Tell the next person how it went.
Sign inA verified email is required to review this server.
Add badge to your README
Paste either snippet into the repository README. The image links to this listing.
Manage this listing
Claim this serverRelated servers
projectmem
by riponcm · Python
Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.
misakanet
by ikalus1988 · Python
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
Bhived MCP
by artkeyai · TypeScript
Shared memory for AI agents: query proven fixes, avoid known mistakes, and find skills and MCPs.
Graphicle
by graphicle-ai · Rust
Code graph and project memory for coding agents, cited to exact files and lines, on your machine.
Compartment
by maxfreedompollard · Python
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
Mnemosyne
by 28naem-del · TypeScript
Evidence-tracked local memory MCP server: one SQLite file; corrections retire dependent memories.