MCP server for Compresh — production-grade context compression with Q-protective ranking, epistemic markers, and depth-aware adaptation
Reason this release was yanked:
Architectural realignment: TUL 1.0 layers moved server-side in 0.2.0. Use 0.2.0+.
Project description
compresh-mcp
MCP server for Compresh — production-grade context compression for LLM agent conversations.
Compresh adds Q-protective ranking, epistemic marker classification, and depth-aware adaptation on top of the open-source
tulbasecompression core. This is the paid tier distribution.
What's the difference vs tulbase-mcp?
| Feature | tulbase-mcp (free, open-source) |
compresh-mcp (paid) |
|---|---|---|
| Base LexRank summarization | ✅ | ✅ |
| Modality elision (code, terminal, JSON, stack traces) | ✅ | ✅ |
| Cold storage + fetch_compressed | ✅ | ✅ |
| Protection Zone (Claim 1e) | ✅ | ✅ |
| Q-protective sentence ranking (Q1–Q4 categorization) | ❌ | ✅ |
| Epistemic markers (VR/HR/CR/UC) | ❌ | ✅ |
| Semantic store (cross-turn Q3 dedup) | ❌ | ✅ |
| Saving telemetry to Compresh dashboard | ❌ | ✅ |
| Multi-device sync (planned) | ❌ | ✅ |
In Compresh's bench (Compresh-bench v1, 600-turn multi-model), Q-protective ranking adds 5–12 percentage points of equivalence preservation vs base LexRank at the same token savings — Pareto improvement.
Pricing
See https://compre.sh/pricing. Three tiers:
- Tier-A (integrated MCP/OAuth metadata, e.g. Cowork, Claude Code, Cursor): saving-share %25 on actual model cost
- Tier-B (family-level provider declaration): saving-share %25 on the family's cheapest model price
- Tier-C (anonymous / local LLM / free models): flat $0.20 per 1M saved input tokens
Every new user: $30 free credit (90-day expiry), $10 minimum budget (charged $7.5 after standard %25 discount).
Installation
pip install compresh-mcp
On first run, you'll be prompted for your Compresh API key. If you don't have an account, your browser opens to compre.sh/signup automatically.
MCP client configuration
Claude Code (~/.claude/mcp.json)
{
"mcpServers": {
"compresh": {
"command": "compresh-mcp",
"env": {
"COMPRESH_API_KEY": "sk-comp_...",
"COMPRESH_API_BASE": "https://api.compre.sh"
}
}
}
}
Cursor (~/.cursor/mcp.json)
Same structure as Claude Code.
Cowork
Cowork → Settings → Tools → MCP servers → Add:
- Command:
compresh-mcp - Environment:
COMPRESH_API_KEY=sk-comp_...
Tools exposed
Same four tools as tulbase-mcp, with enhanced behavior:
compress— Q-protective compression by default (protection_mode="balanced")fetch_compressed,list_compressed,stats— same interface
Plus paid-tier extras:
usage— current cycle budget, free credit balance, savings metrics
License
Business Source License 1.1 — see LICENSE. Production use permitted with valid Compresh API key. License automatically converts to MIT after 4 years (Year 2030).
Patents
Q-protective sentence ranking + Protection Zone are covered by TR-TPMK patent application 2026/007305 (Compresh Ltd, May 2026). A valid Compresh subscription grants implementation license.
Status
This repo is private during dogfood phase (May 2026). Public release scheduled for Q3 2026 alongside the Compresh dashboard MVP.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file compresh_mcp-0.1.0.tar.gz.
File metadata
- Download URL: compresh_mcp-0.1.0.tar.gz
- Upload date:
- Size: 79.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1571bd2426fa8a8f9bad35fb22d12807a9c0d5e2533d449e4235a0bac1f3a8db
|
|
| MD5 |
946fcae64d2786512abd093d445016a8
|
|
| BLAKE2b-256 |
2bf2e38fbdfdd7b3dd24a74b5ca0f04e3ca5260d1e8350f58a518491ca2477a5
|
File details
Details for the file compresh_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: compresh_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 89.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c7d0fad8c556d4d709ff1c1dac42869643aeffcfbf5613428403ec7359c37d29
|
|
| MD5 |
1860c0257f2b66f7f4a2712f474c7f2b
|
|
| BLAKE2b-256 |
8504343bf7e52d5aea022f335991521fe97c725b0d46cc2fd46230627ade9702
|