Agentic MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | Yes | Your GitHub token with repo, workflow, issues, and pull_requests permissions | |
| ANTHROPIC_API_KEY | Yes | Your Anthropic API key | |
| GITHUB_REPOSITORY | Yes | GitHub repository in owner/repo format | |
| GITHUB_REPOSITORY_PATH | Yes | Absolute path to your repository |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| agentic_codegen_executeC | CodeGenAgent実行 - AI駆動コード生成・テスト自動生成 |
| agentic_review_executeC | ReviewAgent実行 - 静的解析・セキュリティスキャン・品質判定 |
| agentic_issue_analyzeC | IssueAgent実行 - Issue内容AI分析・Label自動付与 |
| agentic_pr_createC | PRAgent実行 - PR自動作成・説明文AI生成 |
| agentic_coordinator_decomposeC | CoordinatorAgent実行 - タスク分解（DAG構築）・Agent選定 |
| agentic_kpi_collectC | KPI収集・ダッシュボード生成 |
| agentic_metrics_viewC | 識学理論KPIダッシュボード表示 |
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 7 tools
Most tools have distinct purposes targeting different aspects of agentic workflows (code generation, task decomposition, issue analysis, KPI collection, PR creation, and code review). However, 'agentic_kpi_collect' and 'agentic_metrics_view' have some potential overlap around KPI/dashboard functionality that could cause minor confusion.
All tools follow a perfectly consistent 'agentic_[domain]_[action]' naming pattern with underscores. The structure is predictable and uniform across all seven tools, making them easy to parse and understand as a set.
Seven tools is an appropriate number for an agentic workflow server covering code generation, task coordination, issue management, metrics, and PR/review operations. Each tool appears to serve a distinct role without being overwhelming or insufficient for the domain.
The toolset covers key agentic workflow areas well: code generation, task decomposition, issue analysis, metrics collection/display, PR creation, and code review. A minor gap exists in lifecycle coverage—there's no tool for updating or managing existing PRs/issues beyond creation and review, but agents can likely work around this.