MCP Servers

codex-okf

MCP server that integrates OpenAI Codex with Open Knowledge Format (OKF), enabling knowledge bundle validation, capture, diffing, and workflow automation through natural language.

README

codex-okf

OpenAI Codex plugin for Open Knowledge Format (OKF) v0.1.

Full parity with opencode-okf / claude-okf / pi-okf:

Feature	Mechanism
Init / update / compact workflows	Bundled skill (`skills/okf`)
`okf_validate`, `okf_capture`, `okf_diff`	MCP server (`.mcp.json`)
Validate-on-edit	`PostToolUse` hooks on apply_patch/Edit/Write
Session hint when bundle exists	`SessionStart` hook
CLI	`scripts/okf.mjs`

Install (local marketplace)

cd /Users/kaishin/Developer/Spikes/codex-okf
npm install

# Personal marketplace entry
mkdir -p ~/.agents/plugins ~/.codex/plugins
ln -sfn /Users/kaishin/Developer/Spikes/codex-okf ~/.codex/plugins/okf

Create or merge ~/.agents/plugins/marketplace.json:

{
  "name": "local-kaishin",
  "interface": { "displayName": "Local (Kaishin)" },
  "plugins": [
    {
      "name": "okf",
      "source": { "source": "local", "path": "./.codex/plugins/okf" },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Developer Tools"
    }
  ]
}

Then in Codex / ChatGPT desktop: Plugins → your local marketplace → install OKF.

Trust plugin hooks when prompted (/hooks in CLI) so validate-on-edit runs.

Remove any old skill-only symlink if present:

rm -f ~/.agents/skills/okf

Usage

$okf or ask about OKF / knowledge bundles
MCP tools: okf_validate, okf_capture, okf_diff
CLI:

node scripts/okf.mjs validate
node scripts/okf.mjs diff origin/main
node scripts/okf.mjs capture --summary "…" --decision "…"
node scripts/okf.mjs init

Workflow hard args (same as siblings):

update                 # full repo
update diff [ref]
update session
compact
compact all [aggressive]

Layout

.codex-plugin/plugin.json
.mcp.json
hooks/{hooks.json,post-edit-validate.mjs,session-start.mjs}
skills/okf/
scripts/{okf.mjs,mcp-server.mjs,lib/*}

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.

Official

Featured

TypeScript

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.

Official

Featured

Local

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.

Official

Featured

TypeScript

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.

Official

Featured

Python

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

E2B

Using MCP to run code via e2b.

Official

Featured

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.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured