Intelligent token optimization achieving 95%+ reduction through caching, compression, and 80+ tools
MCPpedia last refreshed this data
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-ooples-token-optimizer-mcp": {
"args": [
"-y",
"semantic-release"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
This repository uses GitHub Actions for automated CI/CD with comprehensive quality gates, automated releases, and dependency management.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'semantic-release' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
Exposure of Sensitive Information to an Unauthorized Actor in semantic-release
### Impact _What kind of vulnerability is it? Who is impacted?_ Secrets that would normally be masked by semantic-release can be accidentally disclosed if they contain characters that are excluded from uri encoding by [encodeURI](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/encodeURI). Occurrence is further limited to execution contexts where push access to the related repository is not available without modifying the repository url to inject credentials. ##
Secret disclosure when containing characters that become URI encoded
### Impact Secrets that would normally be masked by `semantic-release` can be accidentally disclosed if they contain characters that become encoded when included in a URL. ### Patches Fixed in v17.2.3 ### Workarounds Secrets that do not contain characters that become encoded when included in a URL are already masked properly.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml
Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.
Dynamic problem-solving through sequential thought chains
Persistent memory using a knowledge graph
Compact, efficient, and extensible long-term memory for LLM agents.
MCP Security Weekly
Get CVE alerts and security updates for io.github.ooples/token-optimizer-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Give Codex, Claude, Cursor, and other MCP clients more room to think with cached context, compact diffs, smart tools, and visible token-savings reports.
Token Optimizer is a local Model Context Protocol server. It reduces the text sent back into an agent's context by caching large payloads, returning diffs on repeated reads, filtering noisy command output, and recording the result of every measurable optimization.
Every client launches the same stdio server—npx -y @ooples/token-optimizer-mcp@latest—but each client has its own instruction and lifecycle APIs. The ready-made integrations below use those native APIs; they do not pretend Claude Code's seven-phase PowerShell hook system is portable unchanged.
| Client | Fastest MCP setup | Best-experience integration |
|---|---|---|
| Codex | codex mcp add token-optimizer -- npx -y @ooples/token-optimizer-mcp@latest | Codex plugin: MCP + skill + lifecycle hooks |
| Claude Code | claude mcp add --transport stdio --scope user token-optimizer -- npx -y @ooples/token-optimizer-mcp@latest | Claude plugin: MCP + skill + large-read hook |
| GitHub Copilot CLI | copilot mcp add token-optimizer -- npx -y @ooples/token-optimizer-mcp@latest | AGENTS.md + repository lifecycle hooks |
| Gemini CLI | gemini mcp add --scope user token-optimizer npx -y @ooples/token-optimizer-mcp@latest | Gemini extension: MCP + context + lifecycle hooks |
| OpenCode | Add the mcp block below to opencode.json | AGENTS.md + local plugin + compaction preservation |
For the best experience, install the Codex plugin. It bundles the MCP server, the token-optimization skill, session guidance, and a large-read hook:
codex plugin marketplace add ooples/token-optimizer-mcp
codex plugin add token-optimizer@token-optimizer
Review and trust the bundled hooks with /hooks, then start a new conversation. If you prefer an MCP-only installation, use:
codex mcp add token-optimizer -- npx -y @ooples/token-optimizer-mcp@latest
On Windows, if PowerShell blocks the codex.ps1 shim, use the command launcher directly:
codex.cmd mcp add token-optimizer -- npx -y @ooples/token-optimizer-mcp@latest
This writes the server to ~/.codex/config.toml. Codex CLI, the Codex IDE extension, and the Codex app on the same host share that configuration.
codex mcp get token-optimizer
codex mcp list
![Codex MCP list showing token-optimizer installed and enabled](https://raw.githubusercontent.com/ooples/token-optimizer-mcp/HEAD/./docs/assets/codex-mcp-installed.