Arm's official MCP server for porting and tuning software on Arm — semantic docs search, codebase migration scanning, container architecture checks and LLVM-MCA assembly analysis.
2 views
Qase MCP Server
by Qase
Released
v2.4.1
MIT
Summary
Qase test management over MCP: 36 task-oriented tools for cases, runs, results, defects and QQL search, hosted at mcp.qase.io or self-run with your own API token.
Features
- 36 task-oriented tools consolidated from v1's 83, for lower token use and better tool choice
- Composite tools for CI reporting, defect triage and regression run setup
- QQL search across cases, runs, results, defects and plans
- qase_project_context returns suites, milestones, environments, users and custom fields in one call
- Hosted at mcp.qase.io (Enterprise plan) or self-run with QASE_API_TOKEN
- Two-tier tenant-safe cache, connection pooling, retry with backoff, and a qase_api REST escape hatch
Installation
Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.
Description
Qase is a test management platform, and its official MCP server is a good example of a second-generation integration — it was rebuilt rather than extended. Version 2 consolidates v1's 83 tools down to 36 task-oriented ones (37 counting qase_discover_tools), explicitly to cut token usage and improve the accuracy with which a model picks the right call.
The consolidation shows up as composite tools that collapse a multi-step workflow into one call: qase_ci_report posts a batch of CI results, qase_triage_defect turns a failure into a defect, and there are equivalents for setting up a regression run. qase_project_context bootstraps an agent in a single call, returning a project's suites, milestones, environments, users and custom fields. Search runs through QQL, Qase's own query language, across cases, runs, results, defects and plans. Secondary tools stay hidden behind tool discovery so the default list stays short, and qase_api is an escape hatch to any REST endpoint the typed tools do not cover.
Test case review is supported — an agent can propose new cases or changes, assign reviewers and track status — with approving and merging deliberately left to the UI.
Two ways to run it. The hosted server at https://mcp.qase.io/mcp needs only a Qase login, but requires the Enterprise plan and a workspace on Qase's main cloud; on any other plan or a dedicated instance you run it yourself with npm install -g @qase/mcp-server and your own QASE_API_TOKEN, which works everywhere. Operationally it carries a two-tier tenant-safe cache (in-memory plus optional Redis), connection pooling and retry with backoff. MIT licensed, developed at qase-tms/qase-mcp-server.
Related MCP Servers
Official AntV MCP server that turns a description of your data into a rendered chart — 26 visualization types from bar and line to sankey, mind-map, fishbone and geographic maps.
1 views
Context-compression MCP server that shrinks tool outputs, logs, files and RAG chunks before they reach the model, cutting 60-95% of tokens on JSON payloads.
3 views
Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.
2 views