← Index

Ticket AI

io.github.syrian963/ticket-ai-mcpv0.1.1Other

Measures tickets against the ones your team already shipped: sections, length, labels, duplicates.

The current version, v0.1.1, was published to the official MCP registry on 2026-09-11. It is distributed as ticket-ai-mcp on PyPI, filed under Other by this index, and declares 11 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using Ticket AI in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-09-11).

Contracts can change after screening, with no version bump. The gate pins Ticket AI’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Related: how to trust an MCP server · screen before install · silent contract drift

Environment variables
TICKET_AI_TRACKER
required

Which tracker to read: gitlab, jira or github.

TICKET_AI_PROJECT
required

The project to measure. A GitLab path like acme/shop or its numeric id, a Jira project key like PROJ, or a GitHub owner/repo.

TICKET_AI_GITLAB_URL

Base URL of the GitLab instance, for example https://gitlab.example.com. Required when the tracker is gitlab.

TICKET_AI_GITLAB_TOKEN
secret

GitLab personal access token. The read_api scope is enough; nothing here writes.

TICKET_AI_JIRA_URL

Base URL of the Jira instance. Cloud or self-hosted Server and Data Center; which one is detected from the instance.

TICKET_AI_JIRA_EMAIL

Account email, for Jira Cloud's basic auth. Leave unset for a public board or for a Server personal access token.

TICKET_AI_JIRA_TOKEN
secret

Jira API token from id.atlassian.com, or a Server personal access token on its own. Leave unset to read a public instance anonymously.

TICKET_AI_GITHUB_TOKEN
secret

GitHub token with read access to the repository's issues.

TICKET_AI_REPO

Checkout to search when gathering context for a subject. Defaults to the working directory, which on a wrong guess produces confident nonsense - the report names the directory it searched.

TICKET_AI_TICKET_LANGUAGE

Force the language tickets should be written in, overriding what was measured in the corpus. Leave unset unless the board is mid-switch: a measurement beats a setting.

TICKET_AI_CACHE_DIR

Where the learned profile is kept between runs. Defaults to .ticket-ai/ under the working directory.

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
20
installability
25
documentation
15
stability
5
Alternatives in Other