PM Release Notes MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JIRA_EMAIL | No | Email address associated with the Jira API token. | |
| GITHUB_TOKEN | No | GitHub fine-grained token with read access to issues and pull requests. Optional for public repositories. | |
| JIRA_BASE_URL | No | Base URL of your Jira Cloud instance, e.g. https://your-company.atlassian.net. | |
| JIRA_API_TOKEN | No | Jira Cloud API token. | |
| LINEAR_API_KEY | No | Linear personal API key. | |
| AZURE_DEVOPS_ORG | No | Azure DevOps organisation name, or its full URL for older *.visualstudio.com organisations. | |
| AZURE_DEVOPS_PAT | No | Azure DevOps personal access token with Work Items (Read) scope. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_work_itemsA | Read completed issues, work items and merged pull requests from GitHub, Jira, Linear or Azure DevOps for a date range, fix version or iteration. Read-only. |
| draft_release_notesA | Categorise shipped work into breaking changes, features, improvements, fixes and internal work, then draft Markdown release notes. Pass a tracker query (source plus filters) or a list of items. Returns the draft plus a review list of items it excluded or could not place. Nothing is published: the draft is for a human to review. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| polish_release_notes | Turn a categorised draft into customer-ready release notes without adding anything that did not ship. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools form a clean two-stage pipeline: fetch_work_items acquires raw data, draft_release_notes transforms it into Markdown. Their descriptions explicitly state inputs, outputs and read-only boundaries, leaving no realistic way to confuse them.
Both names follow the same snake_case verb_noun pattern (fetch_work_items, draft_release_notes) with domain-appropriate verbs. No mixing of conventions.
Two tools is thin for the surface implied — a release-notes workflow typically wants at least an export/save or re-draft step. The scope is coherent, but the set is minimal enough that it sits at the borderline.
Fetch plus draft covers the core read-to-draft lifecycle across GitHub, Jira, Linear and Azure DevOps, and the exclusion/review list closes the main dead end. The deliberate absence of any publish, save or edit/re-draft operation is a minor gap agents must work around manually.