release-announcer-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LAYOUT_DOCTOR_CHROMIUM | No | Path to a Chromium-based browser executable. Use this to avoid downloading Chromium via Playwright and instead use an existing installation, e.g., Google Chrome or Microsoft Edge. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_repo_infoA | Fetch public information about a GitHub repository: description, topics, license, stars, latest release (tag + notes), README content, and root file list. Use this when you need raw facts about a repository before writing about it or checking it. Args:
Returns: structured JSON with repo metadata, latestRelease (or null), readme text (truncated at 12000 chars), and rootFiles. Errors: returns a clear message for unknown repos (404) and API rate limits (retry later or set GITHUB_TOKEN env var). |
| check_publish_readinessA | Run a pre-publication checklist against a public GitHub repository and report pass/warn/fail per item. Checks: LICENSE present (MIT expected), README present with setup instructions and usage examples, GitHub Release created, 3+ Topics set, About description set, .gitignore present. Args:
Returns: a Markdown checklist report plus structured JSON ({ repo, passed, total, items: [{id, label, status, detail}] }). Each failing item includes a concrete fix suggestion. |
| build_announcement_briefA | Gather a repository's facts (README, latest release notes, metadata) and return a complete writing brief: source material plus strict per-target writing instructions. The calling LLM then writes the final draft texts from this brief. Targets available:
Args:
Returns: a Markdown brief. After calling this tool, write the requested draft texts following the brief's rules exactly. All output is draft-only for human review — never post anywhere automatically. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: fetch_repo_info retrieves raw repo data, check_publish_readiness runs a checklist, and build_announcement_brief creates a writing brief. There is no overlap in functionality.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., fetch_repo_info, check_publish_readiness, build_announcement_brief). The naming is predictable and uniform.
With only 3 tools, the server is at the lower bound of the typical 3-15 range. While the domain is specific, the tool set feels slightly thin for a release announcer, missing tools for actual posting or scheduling.
The tools cover fetching, readiness checking, and brief creation, but lack tools for final draft generation or posting. Important lifecycle steps like creating releases or publishing announcements are absent, leading to significant gaps.