AI & media / llmtrim
llmtrim
io.github.fkiene/llmtrim · v0.13.4
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
Description supplied by the publisher in the MCP Registry. We have not tested this server.
Install
npx -y @llmtrim/cli mcpAssembled from the package metadata in the official MCP Registry (including any subcommand or flag the publisher lists). Some publishers do not list the subcommand that starts MCP mode, so confirm the command in the README, along with any required configuration and credentials, before connecting it to real data.
Signals
| GitHub stars | 245 |
| npm weekly downloads | 0 |
| Last push | 15d ago |
| Licence | MPL-2.0 |
| Open issues | 3 |
| SECURITY.md | Yes |
| Language | Rust |
| Latest version published | 2026-09-08 |
Signals captured from GitHub, npm and the official MCP Registry on October 15, 2026. See the scoring method.
Similar servers compare all →
DevProjex
Score 81Read-only MCP server that turns a folder or repository into redacted, token-efficient context.
deepseek
Score 89MCP server for DeepSeek AI with chat, reasoning, sessions, function calling, and cost tracking
token-optimizer-mcp
Score 88Context-window optimization: caching, compression & smart file tools that cut tokens 60-90%.