Densely MCP Server

Lossless context compression for LLMs. Pack any text into 2x–8x fewer tokens with guaranteed byte-exact reconstruction - verified by sha256 on every decompress. It runs locally over stdio via the published package.

People who work with compression, context window and prompt engineering and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-13 · ★ 6 · #61 OF 106 MAINTAINED AI & ML · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Densely

Claude Code

claude mcp add alibaizhanov-densely -- uvx densely

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "alibaizhanov-densely": {
      "command": "uvx",
      "args": [
        "densely"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-08-07 - young repo, little track record yet

license MIT - declared in the repository

pypi package densely - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.alibaizhanov is GitHub-verified and matches the repo owner

03 · What Densely can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.2.1 · 2026-08-11

0.2.1 · Listed in the official MCP Registry (io.github.alibaizhanov/densely) - installable discovery via MCP clients; PulseMCP and other directories ingest from it · Measured on real-world data - live count_tokens…

04 · Who maintains Densely

densely is maintained by alibaizhanov. We track 2 MCP servers from alibaizhanov - 2 actively maintained, 202 combined GitHub stars, oldest repo from Feb 2026. Full record: all servers from alibaizhanov.

  1. mengram Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows ★ 196

05 · Facts

category
AI & ML - ranked #61 of 106 actively-maintained AI & ML servers as of 2026-09-18.
release cadence
1 release in the last 90 days (latest 2026-08-11)
registry
io.github.alibaizhanov/densely (active, first published 2026-08-11)
packages
pypi:densely

06 · Densely FAQ

What is Densely?

Lossless context compression for LLMs. Pack any text into 2x–8x fewer tokens with guaranteed byte-exact reconstruction - verified by sha256 on every decompress. It runs locally over stdio via the published package.

Is Densely still maintained?

Yes - as of 2026-09-18, its last commit was 2026-08-13 and it shipped 1 release in the last 90 days. We re-verify nightly.

How do I install Densely?

Run `uvx densely`. You can also paste the ready-made client config above.

Does Densely run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Densely