forgespec-mcp
Forgespec MCP facilitates Spec-Driven Development (SDD) by providing tools for contract validation, task board management, and advisory file locking. It enables multi-agent AI systems to coordinate complex workflows through a structured nine-phase development pipeline with built-in dependency tracking.
README
forgespec-mcp
MCP Server for Spec-Driven Development (SDD) — contract validation, task board management, and file reservation for multi-agent AI systems.
Works with any MCP-compatible client: Claude Code, Codex CLI, Gemini CLI, OpenClaw, and more.
Features
- SDD Contract Validation — Enforce typed contracts across a 9-phase development pipeline
- Task Board — SQLite-backed task management with dependency tracking and auto-unblocking
- File Reservation — Advisory file locking to prevent multi-agent conflicts
Quick Start
Using npx (no installation required)
npx -y forgespec-mcp
Install globally
npm install -g forgespec-mcp
Configuration
Claude Code
claude mcp add forgespec --transport stdio -- npx -y forgespec-mcp
Codex CLI (~/.codex/config.toml)
[mcp_servers.forgespec]
command = "npx"
args = ["-y", "forgespec-mcp"]
Gemini CLI (settings.json)
{
"mcpServers": {
"forgespec": {
"command": "npx",
"args": ["-y", "forgespec-mcp"]
}
}
}
OpenClaw (openclaw.json)
mcp: {
servers: {
forgespec: { command: "npx", args: ["-y", "forgespec-mcp"] }
}
}
Tools
SDD Contract Tools
| Tool | Description |
|---|---|
sdd_validate |
Validate an SDD contract against phase schema |
sdd_save |
Validate and persist a contract |
sdd_history |
Get phase transition history for a project |
sdd_phases |
Get all phases with transitions and confidence thresholds |
Task Board Tools
| Tool | Description |
|---|---|
board_create |
Create a new task board |
board_status |
Get board status with tasks grouped by status |
board_list |
List all boards |
task_add |
Add a task with priority, spec ref, and acceptance criteria |
task_claim |
Claim a task (checks dependencies) |
task_update |
Update task status (auto-unblocks dependents) |
task_unblocked |
List tasks ready to work on |
File Reservation Tools
| Tool | Description |
|---|---|
file_reserve |
Reserve files/globs with TTL |
file_check |
Check for conflicts |
file_release |
Release reservations |
SDD Pipeline
The 9-phase Spec-Driven Development lifecycle:
init → explore → propose → spec → design → tasks → apply → verify → archive
Each phase has confidence thresholds and allowed transitions enforced by the contract validator.
| Phase | Confidence Threshold | Can Transition To |
|---|---|---|
| init | 0.5 | explore, propose |
| explore | 0.5 | propose, spec |
| propose | 0.7 | spec, design, init |
| spec | 0.8 | design, tasks |
| design | 0.7 | tasks, spec |
| tasks | 0.8 | apply |
| apply | 0.6 | verify, tasks |
| verify | 0.9 | archive, apply |
| archive | 0.9 | — |
Environment Variables
| Variable | Default | Description |
|---|---|---|
FORGESPEC_DIR |
~/.forgespec |
Database directory |
FORGESPEC_DB |
~/.forgespec/forgespec.db |
Full database path |
Development
git clone https://github.com/lleontor705/forgespec-mcp.git
cd forgespec-mcp
npm install
npm run dev # Run with tsx (hot reload)
npm test # Run tests
npm run build # Compile TypeScript
npm run inspect # Open MCP Inspector
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.