---
title: "fitr"
description: "Capture local AI candidates, interpret measured evidence, and expose read-only role summaries through MCP."
canonical: https://agentpluginsdirectory.com/plugins/fitr
last-updated: 2026-10-21
---

# fitr
Capture local AI candidates, interpret measured evidence, and expose read-only role summaries through MCP.
- Slug: fitr
- Publisher: blisspixel
- Repository: https://github.com/blisspixel/fitr
- Manifest: plugins/fitr/plugin.json
- Version: 0.11.10
- Category (editorial): other
- Skills: 1 (fitr-evidence)
- MCP servers: 1 (fitr-evidence)
- Stars: 0
- Repository created: 2026-08-19
- Repository last pushed: 2026-10-21
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/fitr
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What fitr does, in the publisher's words

Your tailor for local AI.

Start with a model. Find the configuration that fits your machine, your work, and your priorities. fitr measures the fit, tests the output, and keeps the evidence behind each choice.

Model names and public leaderboards do not answer the local questions. Will this artifact fit at the context you need? Is the runtime really using the accelerator? Are tool calls reaching the tool channel? Is the faster quant still correct? Does a candidate complete a bounded workflow when another system independently verifies the result?

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/blisspixel/fitr/HEAD/README.md

## Skills

- fitr-evidence: Capture candidate models in fitr and interpret local fit, workload, and decision evidence when choosing a configuration for a specific role.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- fitr-evidence: transport: stdio; command: fitr mcp serve

Read from the plugin's own mcp.json. Environment variable names only, never values.