llmtrim MCP server

by fkiene·io.github.fkiene/llmtrim·v0.13.4

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

A92/100grade A

What users say

No reviews yet

Safety scan

A92/100

Adoption

Established

236 stars220 downloads/wk

Reviews

Nobody has reviewed llmtrim yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

No tool declarations could be read from the package source. They show once the server is installed.

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

no findings

Code scan3 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 3 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Runs npx -y @llmtrim/cli on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add llmtrim -- npx -y @llmtrim/cli

Is llmtrim MCP server safe?: Yes, by our scan: it is graded A (92/100). Read the llmtrim safety report
How do I install llmtrim?: It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does llmtrim need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is llmtrim maintained?: The last commit was 3 days ago (2026-09-16). The latest release is v0.13.4.
What can I use instead of llmtrim?: Servers from other publishers that do the same job: prompt-protection MCP server, MCP Server and Agent-Native Analytics MCP server. Compare all llmtrim alternatives.

Same job from other publishers: the closest match first, then the best rated.

prompt-protection
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
not reviewed
Growing
A
MCP Server
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
not reviewed
Growing
B
Agent-Native Analytics
Agent-Native Amplitude/Mixpanel - connect data sources, prompt for charts
not reviewed
Established
A
mcptoon
Zero-dependency MCP client: one synced config for every agent, 581-token listings, not 71,929.
not reviewed
Established
A
Image
AI image generation and editing with prompt optimization and quality presets
not reviewed
Established
B