Agentic SDLC MCP Server

Agentic SDLC governance and security controls for AI coding agents working with GitHub.

Local serverstdio

What is the Agentic SDLC MCP MCP server?

If you already use Agentic SDLC MCP, the agentic sdlc mcp mcp server is the piece that lets your assistant work with it directly. Agentic SDLC governance and security controls for AI coding agents working with GitHub.

What the server does

Governance and evidence controls for AI coding agents working in real GitHub repositories.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • repo_context — An agent needs repository facts before planning
  • plan_from_context — A goal needs an SDLC plan and issue drafts
  • prepare_work_item — An agent is about to implement a GitHub Issue
  • create_issue_set — A reviewed plan should become GitHub Issues
  • create_pr_summary — A pull request needs a reviewable overview
  • quality_gate_status — A team needs real merge-gate evidence
  • review_pr_against_standard — A pull request needs SDLC and security review
  • branch_protection_status — A team needs branch and ruleset visibility
  • workflow_permissions_audit — GitHub Actions token permissions need review
  • security_triage — Release or incident work needs GitHub security alerts
  • release_readiness_check — A human is deciding whether to publish
  • agent_handoff_packet — Another agent must continue the work

Credentials and setup notes

Configuration is passed through the environment: GITHUB_TOKEN, GITHUB_OWNER, GITHUB_REPO. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

Installation goes through your MCP client rather than a global install: point it at agentic-sdlc-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Where it fits

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agentic SDLC MCP's toolset — repo_context, plan_from_context, prepare_work_item and 10 more — is a fair guide to whether it matches your workflow. It is maintained by SakuraCianna; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agentic SDLC MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
repo_contextAn agent needs repository facts before planning
plan_from_contextA goal needs an SDLC plan and issue drafts
prepare_work_itemAn agent is about to implement a GitHub Issue
create_issue_setA reviewed plan should become GitHub Issues
create_pr_summaryA pull request needs a reviewable overview
quality_gate_statusA team needs real merge-gate evidence
review_pr_against_standardA pull request needs SDLC and security review
branch_protection_statusA team needs branch and ruleset visibility
workflow_permissions_auditGitHub Actions token permissions need review
security_triageRelease or incident work needs GitHub security alerts
release_readiness_checkA human is deciding whether to publish
agent_handoff_packetAnother agent must continue the work
sdlc_evidence_packetA workflow decision needs a portable evidence snapshot

How to install the Agentic SDLC MCP MCP server

{
  "mcpServers": {
    "agentic-sdlc": {
      "command": "npx",
      "args": ["-y", "agentic-sdlc-mcp"],
      "env": {
        "GITHUB_TOKEN": "your-value",
        "GITHUB_OWNER": "your-value",
        "GITHUB_REPO": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
GITHUB_TOKENCredential the server authenticates with.Yes
GITHUB_OWNERConfiguration value read at startup.Optional
GITHUB_REPOConfiguration value read at startup.Optional

Example prompts to try

  • Use Agentic SDLC MCP to repo context.
  • Use Agentic SDLC MCP to plan from context.
  • Use Agentic SDLC MCP to prepare work item.

Frequently asked questions

It connects Agentic SDLC MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (repo_context, plan_from_context, prepare_work_item, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentic SDLC MCP directly.