mcp-server-polarionSAFE
MCP server for Polarion ALM — read and write documents, work items, test runs, traceability links, and comments from any MCP-compatible AI assistant
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Talk to your Polarion — AI reads, writes, and reorganizes documents, work items, test runs, and traceability links.
Features · Quickstart · Tools · Example Prompts · Setup
[](https://github.com/devemberx/mcp-server-polarion/actions/workflows/ci.yml) [](https://github.com/devemberx/mcp-server-polarion/actions/workflows/publish.yml) [](https://pypi.org/project/mcp-server-polarion/) [](https://www.python.org/) [](LICENSE)
A Model Context Protocol (MCP) server for Polarion ALM, built for real-world instances: every write supports dry_run, guards validate fields and enum values before anything is committed, and requests are paced to a rate cap you configure for your instance — so an AI assistant can work on production data without surprises.
Features
- 46 tools covering read and write across documents, work items, test runs, traceability links, comments, and attachments.
- Read — render documents as Markdown, search with Lucene or SQL, walk incoming/outgoing links, resolve enum options.
- Write — create and update work items, documents, and test runs, manage links, reorganize document str
931e08238e30OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-polarion --env POLARION_TOKEN=${POLARION_TOKEN} -- None mcp-server-polarion==0.0.0Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_html_recipes | read | Fetch the required HTML templates for tables, captions, links, and |
get_sql_query_recipes | read | Fetch copy-paste SQL recipes for the list_work_items SQL:(...) prefix. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (6)
"threat_names": ["prompt_injection", "exfil"],
assert "| danger_tool | HIGH | 3 | prompt_injection, exfil |" in out
"flags 🇰🇷 and family 👨👩👧 sequences", # regional indicators + ZWJ
.github/assets/demo.gif
description: Full feature-development pipeline for this repo — isolated worktree, spec, implementation plan, TDD build, quality gates, then a review→fix loop that only stops when review passes. Each s
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass.
931e08238e30full audit observations/trust-audit/mcp-server/devemberx__mcp-server-polarion.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 931e08238e30 | SAFE | B | 89 | first audit |
Questions
What is the mcp-server-polarion MCP server?
MCP server for Polarion ALM — read and write documents, work items, test runs, traceability links, and comments from any MCP-compatible AI assistant
What tools does mcp-server-polarion expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is mcp-server-polarion safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does mcp-server-polarion need?
It reads POLARION_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does mcp-server-polarion run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-server-polarion.
How current is this page?
The grade is for one exact copy of the source (931e08238e30), read on 2026-10-10. The repository is watched and re-audited when it changes.