1. Conduid
  2. AI
  3. Toolkit
MCP server · AI

Toolkit

A bootstrap template for an MCP Server instance

67Good

Scored 3 hours ago · breakdown

About Toolkit

Toolkit is an MCP server published by eyelock in the AI category: a bootstrap template for an MCP Server instance.

The repository has 1 stars and 0 forks, with the last commit 3 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/eyelock/mcp-toolkit

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Toolkit

Powered by Claude · Grounded in docs

I know everything about Toolkit. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 3 hours ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • ✓Tests presentA test suite exists in the repository.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

v0.1.0Release v0.1.0 · 7 Jan 2026Release v0.1.0

README

MCP Toolkit

A TypeScript monorepo template for building production-ready Model Context Protocol (MCP) servers with full specification coverage.

Note: This is a personal hobby project developed in spare time. It's functional and tested, but expect rough edges. Contributions welcome!

What is MCP Toolkit?

MCP Toolkit provides:

Component Purpose
Template Clone and customize to build your own MCP server
Reference Implementation Working examples of MCP spec features (tools, resources, prompts, sampling, elicitation)
Hook System Contextual LLM guidance through lifecycle hooks
Testing Harness Utilities for testing MCP tools and workflows

Quick Start

# Clone the template
git clone https://github.com/eyelock/mcp-toolkit.git my-mcp-server
cd my-mcp-server

# Remove git history and customize
rm -rf .git
./bin/setup.sh

# Build and run
pnpm install
pnpm build
pnpm test

Features

  • Dual Interface: MCP server + CLI share the same business logic
  • Multiple Transports: stdio (Claude Desktop) and HTTP/SSE (web)
  • Type-Safe: Zod schemas as single source of truth
  • Full MCP Spec Coverage: Tools, resources, prompts, sampling, elicitation, logging, pagination
  • Hook System: Contextual guidance for LLM workflows
  • Monorepo: pnpm workspaces + Turborepo for fast builds
  • Tested: Comprehensive test coverage with Vitest

Project Structure

mcp-toolkit/
├── packages/
│   ├── mcp/        # MCP server implementation
│   ├── core/       # Hook system and registry
│   ├── toolkit/    # Demo workflows (optional, deletable)
│   ├── model/      # Zod schemas
│   ├── cli/        # CLI commands (OCLIF)
│   └── testing/    # Test utilities
├── docs/           # Full documentation
└── bin/            # Setup and dev scripts

Documentation

Claude Code Integration

MCP Toolkit includes .mcp.json for immediate Claude Code integration:

pnpm build
claude
# Approve 'mcp-toolkit-stdio' when prompted

Development

make help          # Show all targets
make rebuild       # Clean rebuild with lint & test
make mcp           # Run with MCP Inspector

Requirements

  • Node.js 20+
  • pnpm (via corepack enable)

Acknowledgments

Contributing

See CONTRIBUTING.md for guidelines. Issues and PRs welcome!

License

MIT

README fetched from the repository 3 hours ago. The original is authoritative.

Questions

About Toolkit

How do I install Toolkit?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Toolkit safe to use with an AI agent?

Its trust score is 67 out of 100 (good). It passes 5 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Toolkit still maintained?

Yes — the last commit was 3 days ago. The repository has 1 stars and 0 forks and 7 open issues.