Provides GitHub issue triage tools for searching issues, summarizing issue context with comments, and drafting comments with a gated confirm flag before posting.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@gh-triage-mcp find open issues labeled bug"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Three MCP tools for GitHub issue triage. TypeScript. Stdio.
Most GitHub MCPs wrap REST 1:1 and dump the JSON. Same pass rate, much more context. HN measured 5× on that pattern. This server returns what the next call needs: number, owner, repo, a short body, a suggested action.
draft_comment does not POST unless confirm=true.
Tool | Returns | Writes? |
| short list + | no |
| that plus last five comments | no |
| the draft; posts only with | gated |
Related MCP server: mcp-gitpro
Twenty synthetic issues. Shaped vs raw dump.
Next call fillable | ~tokens | |
raw REST | 0/20 | 12350 |
this server | 20/20 | 4227 |
2.92× fewer tokens. Not a model score. npm run eval fails the build if that ratio collapses.
Failure modes: evals/failure_modes.md.
npm install
npm test
npm run eval
npm run build{
"mcpServers": {
"gh-triage": {
"command": "node",
"args": ["/absolute/path/to/gh-triage-mcp/dist/index.js"],
"env": { "GITHUB_TOKEN": "ghp_..." }
}
}
}Node 20+. Token optional for public read; required to comment.
Live: https://01a05643-d6bf-7a9d-9634-4f367e3a2682.skydive.app/gh_triage_mcp
pip install -r requirements.txt
streamlit run app.pyDoes not call GitHub. Side-by-side dump vs shaped payload.
Not in this repo: labels, assignees, closing, projects. Use github/github-mcp-server if you need the kitchen sink.
MIT. Ashley Gross, 2026.
Draft a comment on an issue. Does not post unless confirm=true. Always show the draft to a human first.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | Markdown comment body | |
| repo | Yes | owner/name | |
| number | Yes | Issue number | |
| confirm | No | Must be true to actually POST. Default false (dry run). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does well by disclosing the dry-run behavior, the confirmation gate for posting, and the human-review requirement. These are meaningful behavioral traits beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, with the core purpose front-loaded and the crucial caveats stated immediately after. Every phrase earns its place and there is no redundant or vague wording.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description adequately covers purpose, dry-run semantics, and the human-in-the-loop step, which is enough to invoke the tool correctly. It does not describe the return value or what happens after confirmation, but those are minor gaps given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description references the confirm flag but otherwise does not add parameter meaning beyond what the input schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb and resource: 'Draft a comment on an issue.' It also clarifies this is not a posting operation unless confirmed, which distinguishes it from any posting sibling and from the search/summarize siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states when to use the tool implicitly and adds critical usage constraints: 'Does not post unless confirm=true' and 'Always show the draft to a human first.' It does not explicitly name alternatives, but the intended workflow is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search GitHub issues. Returns a short, LLM-shaped list: number, url, labels, owner/repo, and a suggested next action. Not a raw REST dump. Scope with repo=owner/name when you know it.
| Name | Required | Description | Default |
|---|---|---|---|
| repo | No | Optional owner/name to scope the search | |
| limit | No | Max results, default 8 | |
| query | Yes | GitHub issue search syntax, e.g. 'crash in login' or 'label:bug' | |
| state | No | Filter by issue state |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and uses it well by disclosing that the result is a curated, LLM-shaped list with specific fields and a suggested next action, and by explicitly noting it is 'Not a raw REST dump.' It does not mention auth, rate limits, or default behavior, but the disclosed output behavior is unusually informative for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short sentences, each earning its place: the verb-resource statement, the output-shape disclosure, the anti-REST-dump differentiator, and the scoping tip. Information is front-loaded and there is no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Because there is no output schema, the description compensates by enumerating the returned fields and the suggested next action, which is essential for an agent deciding whether the tool's output is adequate. Combined with the fully described input schema, this is close to complete; only minor details like result ordering or default state are absent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents all four parameters. The description adds only mild reinforcement for the repo parameter ('Scope with repo=owner/name when you know it') and does not elaborate on query/limit/state beyond the schema, matching the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Search GitHub issues') and describes the distinctive LLM-shaped return format, making the tool's core function clear. It does not explicitly differentiate from siblings summarize_issue and draft_comment, but the search verb and output description are enough to separate it from those actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Offers practical scoping guidance ('Scope with repo=owner/name when you know it'), which implies how to narrow a search. It does not state when to choose search_issues over summarize_issue or draft_comment, nor does it give exclusions, leaving the choice between siblings implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Load one issue and its recent comments, shaped for triage: excerpts, labels, and the owner/repo/number you need to comment. Use this before draft_comment.
| Name | Required | Description | Default |
|---|---|---|---|
| repo | Yes | owner/name | |
| number | Yes | Issue number |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. 'Load' strongly implies a read-only retrieval, and the description adds useful detail about the shaped output (excerpts, labels, owner/repo/number). It does not mention limits, errors, or authentication, so it is transparent but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, with the core behavior front-loaded and the workflow hint at the end. Every word contributes meaning, and there is no filler or repetition of schema fields.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter read tool with no output schema, the description still explains the purpose, the output shape, and the intended next step. It could be more explicit about the exact response format or comment count, but it provides enough context for an agent to invoke it correctly in the triage workflow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already documents both parameters (repo as owner/name, number as issue number), and schema coverage is 100%. The description only repeats the owner/repo/number concept without adding new syntactical or semantic detail beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('Load one issue and its recent comments') and frames the output for triage, listing concrete contents: excerpts, labels, owner/repo/number. It clearly distinguishes this from search_issues (which searches) and draft_comment (which follows it), so an agent can tell exactly what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit sequencing guidance with 'Use this before draft_comment,' making the intended workflow clear. It does not explicitly state when not to use it or compare with search_issues, so it lacks full exclusionary guidance, but the intended context is evident.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0draft_commentsearch_issuessummarize_issueScored across 3 tools
Each tool has a clearly distinct role: search_issues finds issues, summarize_issue loads details and comments, and draft_comment creates a proposed response. There is no meaningful overlap or ambiguous boundary between them.
All tool names follow a consistent verb_noun pattern in snake_case: search_issues, summarize_issue, draft_comment. The naming style is uniform and predictable across the entire server.
Three tools form a tight, well-scoped set for an issue triage workflow: find, understand, and draft a response. The count is neither too sparse nor excessive for the stated purpose.
The server covers the full triage lifecycle: discovering relevant issues, reading issue context with comments, and drafting a comment with optional posting. There are no obvious dead ends for the intended use case.
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
