What does provenance-aware priority handling do?

It prevents untrusted RAG, tool, and assistant content from gaining protected priority solely through imperative or safety-critical wording.

Does LLMSlim prevent prompt injection?

No. It mitigates compression-induced instruction elevation and applications still need defense in depth.

Does LLMSlim require remote calls?

The default extractive strategy runs locally. Rewrite and hybrid strategies use a caller-supplied provider.

All documentation

Guides & Strategies 4 min readUpdated September 2026

MCP catalogs and agent hosts

Read complete tool contracts while keeping execution in your host.

Install an optional integration

MCP and Agents extras require Python 3.10 or newer. Base text compression remains available without these SDKs.

terminal

pip install 'llmslim[mcp]==0.5.0'
# For the optional Agents SDK bridge:
pip install 'llmslim[agents]==0.5.0'

List, plan, and hydrate

Configure a trusted endpoint explicitly. HTTP is allowed only for localhost development; remote endpoints require HTTPS. Stdio sources accept an executable and literal argument list. Plans default to the full catalog.

catalog.py

import asyncio
from llmslim.mcp import MCPToolCatalogSource, plan_catalog_context, hydrate_plan

async def main():
    source = MCPToolCatalogSource.from_streamable_http(
        'http://127.0.0.1:8000/mcp', source_id='local-tools'
    )
    snapshot = await source.list_tools()
    plan = plan_catalog_context(snapshot)
    schemas = hydrate_plan(snapshot, plan)
    print(len(schemas), plan.metrics.catalog_tokens)

asyncio.run(main())

Freshness and host ownership

The shortest page TTL governs the full snapshot. Private entries are isolated by the caller's cache principal; only explicitly public responses may be shared. Use source.refresh() or source.invalidate() when your host learns a catalog changed. Hydration rejects a plan from a different catalog fingerprint.

Selection is not permission

Never use rankings or fingerprints as authorization. Keep provider credentials and execution policy in the host. Live-model task success is not established by the offline integration benchmark.

Frequently asked questions

Getting Started

Install an optional integration

List, plan, and hydrate

Freshness and host ownership

Does this execute MCP tools?

Does the default save schema tokens?