MCP servers · akynzh

PASH Compression MCP Server (Standalone)

A standalone Model Context Protocol server that compresses large JSON tool responses with PASH compression and loads tools from a local manifest-based directory.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

This MCP server exposes external tools to MCP clients such as Cursor and Claude Desktop. It applies PASH compression to large JSON responses and returns a hash in place of the full payload, which the publisher states reduces LLM token use by about 87%. Tools are registered dynamically: the server scans a local mcp_engines directory and loads each tool from its manifest.json.

It suits developers who run MCP tools through a compatible client and want to limit the token cost of heavy tool output. The repository also contains a Cognitive Loop, a Product Judge for deterministic output validation, and heuristic routing, all described as implemented and tested. The publisher presents it as the cognitive core for the Odysseus interface, but the one-click Odysseus UI integration is listed as roadmap work still in development.

Setup means copying .env.example to .env and setting the paths, then creating the mcp_engines directory with a subfolder for each server containing its manifest.json and executable. The server runs in stdio mode and is intended to be used with clients that support it. The code has no dependencies on the internal Felix core, so it can be installed on its own.

Limitations and requirements

Requires a .env file configured from .env.example and an mcp_engines directory containing a manifest.json and executable for each MCP server. The server runs in stdio mode and connects to compatible clients. Developers changing the server code are asked to clean up processes by port; global process termination (taskkill /IM) is prohibited because it ends the agent session. Native one-click Odysseus UI integration is not yet available.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    io.github.AkynZH/pash-mcp-server

    Standalone MCP server with PASH compression. Saves ~87% LLM tokens via dynamic tool registration.

    v1.0.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026