Log inSubmit server
Agentic SDLC MCP logo

Agentic SDLC MCP

Adds GitHub-aware SDLC governance, security checks, evidence reports, and preview-first issue creation for coding agents.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Agentic SDLC MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "agentic-sdlc-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agentic-sdlc-mcp"
      ],
      "env": {
        "GITHUB_TOKEN": "YOUR_VALUE_HERE",
        "GITHUB_OWNER": "YOUR_VALUE_HERE",
        "GITHUB_REPO": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 13 tools correctly (18d ago).

Overview

Agentic SDLC MCP MCP server connects AI coding agents to bounded GitHub repository evidence and SDLC governance checks. Its 13 MCP tools read repository metadata, policies, pull requests, checks, security signals, and release information, while issue creation is preview-first. Use it when agents need structured plans, quality gates, security findings, handoff packets, or release evidence instead of relying on unstated repository conventions. It does not write code, merge pull requests, deploy software, or create releases.

Use cases

  • Inspect an unfamiliar repository before assigning work to an agent
  • Prepare risk-aware plans for authentication, payment, migration, or infrastructure changes
  • Audit pull request gates, branch protection, and workflow permissions
  • Assess security and release readiness before human approval
  • Package repository evidence for agent handoffs or decision records

Key features

  • Bounded GitHub repository context
  • Risk-aware work-item planning
  • Preview-first GitHub issue creation
  • Pull request quality and security reviews
  • Branch protection and workflow permission audits
  • Release, handoff, and evidence packets

Tools13

What Agentic SDLC MCP lets your agent do. Expand a tool for its parameters.

Verified live~6.5k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

11/15 checks healthy over the last 90d

What it can do

From the 13 tools this server returned when we ran it; 13 declare their own safety hints.

Handles credentials · 5Makes network requests · 13Read-only tools · 13
Unusual tool instructions. 1 tool description contain text aimed at the AI model rather than at you (reaches for local secrets). Read the tool descriptions before connecting.
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age106 days
Maintainers1

Observed 2026-10-21 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 1d ago via OSV.dev · agentic-sdlc-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads311Package downloads in the last 30 days.
Last commit25d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed13Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Agentic SDLC MCP works

What Agentic SDLC MCP does

The Agentic SDLC MCP MCP server gives AI coding agents a structured view of GitHub repositories and the evidence surrounding software delivery decisions. It can collect repository instructions, scripts, workflows, open issues, pull requests, policy information, checks, reviews, branch controls, security alerts, and release signals.

The output is intended for decision support rather than autonomous delivery. Depending on the tool, the server produces repository briefings, risk-aware work plans, pull request summaries, gate assessments, security findings, handoff packets, or evidence snapshots. Twelve tools are read-only. create_issue_set is the only GitHub write-capable tool and previews the proposed issue changes before creation.

How it works

The MCP client sends tool requests to the server over the default stdio transport. The server queries GitHub evidence and returns bounded reports that identify missing information, policy obligations, blockers, provenance, freshness, or human approval points. Repository changes remain in the coding agent’s normal environment, while merge, release, and deployment decisions stay with the team.

A typical workflow starts with repo_context, followed by plan_from_context or prepare_work_item. Before a pull request reaches human review, an agent can combine create_pr_summary, quality_gate_status, and review_pr_against_standard. Governance audits can use branch protection and workflow permission checks, while release work can combine security triage with release readiness checks. agent_handoff_packet and sdlc_evidence_packet preserve bounded context for later work or archival.

Setup and configuration

The Agentic SDLC MCP MCP server requires Node.js 22 or newer. Run it directly with npx -y agentic-sdlc-mcp, or install it globally with npm and invoke agentic-sdlc-mcp. Configure the server in an MCP client using the command and arguments for the npm package.

Set GITHUB_TOKEN through the client’s secret or environment configuration. GITHUB_OWNER and GITHUB_REPO can provide default repository coordinates, but tool calls may supply repository details explicitly. A local configure command can store settings in ~/.agentic-sdlc-mcp.json; the documented guidance limits that approach to a trusted, single-user workstation because it may store the GitHub token.

Start verification with the read-only repo_context tool. Review the requested GitHub permissions and every configuration change before enabling issue creation.

Tools and capabilities

Available capabilities include:

  • Reading bounded repository context and generating plans from it.
  • Preparing feature, bug, security, authentication, payment, migration, or infrastructure work with risk considerations.
  • Drafting GitHub issue sets and previewing the write before creation.
  • Summarizing pull requests and evaluating checks, reviews, ownership, labels, and branch protection evidence.
  • Reviewing patches for credential-construction patterns, aliases, decoding, interpolation, and authentication-header sinks.
  • Auditing GitHub Actions workflow permissions and repository branch or ruleset controls.
  • Summarizing security alerts and assessing release blockers, changelog status, rollback needs, and CI evidence.
  • Creating agent handoff packets and versioned evidence packets with provenance, completeness, freshness, and content digests.

Limitations and notes

The Agentic SDLC MCP MCP server does not modify source code, merge pull requests, force-push, create releases, or deploy software. It is not a replacement for human security review or organizational approval.

Its findings depend on the GitHub evidence available to the configured token and repository. Patch heuristics and scanner results are presented with distinctions between trusted evidence, bounded observations, and unverified gaps; a passing CI signal alone is not treated as complete release or merge evidence. The write boundary is intentionally narrow: issue creation is preview-first, and the remaining listed tools are read-only.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Agentic SDLC MCP

Agentic SDLC MCP is an MCP server that connects AI coding agents to GitHub repository evidence and SDLC governance checks. Its main tools read repository context, prepare work items, assess pull requests and quality gates, audit security and permissions, check release readiness, create preview-first issue sets, and package evidence for handoffs.

Install it with Node.js 22 or newer by running `npx -y agentic-sdlc-mcp`, or install it globally with `npm install -g agentic-sdlc-mcp`. Add the command to your MCP client configuration and provide the GitHub token through the client’s secret or environment settings.

Yes, the README names Cursor as a supported MCP client. Configure it to launch the package with `npx -y agentic-sdlc-mcp`, then inject `GITHUB_TOKEN` through Cursor’s environment or secret configuration. `GITHUB_OWNER` and `GITHUB_REPO` are optional repository defaults.

Yes, `create_issue_set` can create GitHub issues, but it previews the proposed changes first. The other listed tools are read-only. Review the preview and requested permissions before allowing issue creation, and use read-only `repo_context` to verify the connection initially.

No, it does not deploy software, merge pull requests, force-push, create releases, or write code. It supplies repository context, governance findings, quality evidence, security observations, and release reports so agents and human reviewers can make those decisions.

Related MCP servers

All in Version Control All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAgentic SDLC MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/agentic-sdlc-mcp?style=directory)](https://allmcps.com/mcp/agentic-sdlc-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/agentic-sdlc-mcp"><img src="https://allmcps.com/api/badge/agentic-sdlc-mcp?style=directory" alt="Agentic SDLC MCP on AllMCPs" /></a>