Gridline
OfficialThis server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
@gridlinegpu/mcp
Gridline's MCP server. It lets an AI agent (Claude Code, Claude Desktop or any other MCP client) fine-tune, evaluate and batch open models through Gridline's OpenAI-compatible API, with no GPUs, containers or sandboxes to manage.
Pricing: https://gridlinegpu.com/pricing
API base URL:
https://api.gridlinegpu.com/openai/v1
Install
You need Node.js 18 or later and a Gridline API key (create one in the dashboard at https://gridlinegpu.com/dashboard). The server runs over stdio:
npx -y @gridlinegpu/mcpClaude Code
claude mcp add gridline --scope user --env GRIDLINE_TOKEN=$GRIDLINE_TOKEN -- npx -y @gridlinegpu/mcp--scope user makes the server available in every project; leave it out to add it to the current
project only. Check it with claude mcp list, or /mcp inside Claude Code.
Cursor
Add the server to ~/.cursor/mcp.json (every project) or .cursor/mcp.json in a project's root
(that project only), then enable it under Cursor Settings → MCP:
{
"mcpServers": {
"gridline": {
"command": "npx",
"args": ["-y", "@gridlinegpu/mcp"],
"env": { "GRIDLINE_TOKEN": "<your Gridline API key>" }
}
}
}Claude Desktop
Open Settings → Developer → Edit Config, which opens claude_desktop_config.json
(~/Library/Application Support/Claude/claude_desktop_config.json on macOS,
%APPDATA%\Claude\claude_desktop_config.json on Windows). Add the server under mcpServers, save,
and restart Claude Desktop:
{
"mcpServers": {
"gridline": {
"command": "npx",
"args": ["-y", "@gridlinegpu/mcp"],
"env": { "GRIDLINE_TOKEN": "<your Gridline API key>" }
}
}
}Claude Desktop starts npx itself, so Node.js 18 or later has to be installed where it can find it.
Any other MCP client with a JSON config
The same block works in any client that reads an mcpServers config:
{
"mcpServers": {
"gridline": {
"command": "npx",
"args": ["-y", "@gridlinegpu/mcp"],
"env": { "GRIDLINE_TOKEN": "<your Gridline API key>" }
}
}
}Its name in the official MCP Registry is io.github.GridlineGPU/mcp (see server.json in this
folder).
Related MCP server: Tuning Engines
Environment
Variable | Required | Meaning |
| yes | Your Gridline API key. Sent only as the |
| no | Overrides the API base URL. Must be https. |
Spending credit: confirm_spend
Three tools spend credit: create_fine_tune, create_batch and create_eval_run (unless
dry_run is true). Each refuses, and sends nothing, unless the call carries
confirm_spend: true. An agent has to read the quote or the price first, so it cannot spend by
accident; tell your agent to report the cost before it confirms. Every other tool is free. Fine-tunes
are charged per training token and batches per input and output token, each with its minimum: see
https://gridlinegpu.com/pricing.
Tools
Tool | Spends credit | What it does |
| no | Base models you can batch or fine-tune on, and your |
| no | Your credit balance and recent charges. |
| no | Upload a local JSONL file (purpose |
| yes | Start a LoRA, QLoRA or DPO fine-tuning job. |
| no | Your fine-tuning jobs. |
| no | A job's status, its quote and its |
| no | A job's progress and loss. |
| no | Cancel a fine-tuning job. |
| yes | Run a batch on a base model or your |
| no | A batch's status, counts and output file ids. |
| no | Cancel a batch. |
| no | Save a batch's output or error file to a local path. |
| no | Define an eval: its item schema and graders. |
| yes | Run an eval, or quote it with |
| no | A run's status and per-grader results. |
| no | A run's graded rows. |
| no | Export an |
| no | A merged-weights export's status and files. |
| no | A short-lived download URL for one merged file. |
A worked loop
Ask your agent, for example: "Fine-tune qwen2.5-7b-instruct on ./train.jsonl, compare it with the base on ./eval.jsonl, and run ./requests.jsonl as a batch on whichever scores higher. Tell me what each paid step will cost before you run it." It uploads the files, starts the fine-tune, quotes and runs an eval on both models, then batches on the better one and downloads the results.
Licence
MIT: see LICENSE. Use of Gridline's API is subject to Gridline's terms
(https://gridlinegpu.com/terms). The bundled third-party packages and their licences are listed in
THIRD_PARTY_NOTICES.md.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.
Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.
Run Together AI chat, embeddings and images; manage fine-tunes, batches and endpoints.
Image, video, music and text generation across 100+ models through one endpoint.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides a universal bridge to interact with any OpenAI-compatible LLM API (local or cloud), enabling model testing, benchmarking, quality evaluation, and chat operations with performance metrics.8MIT
- AlicenseAqualityAmaintenanceOwn your sovereign AI model. Domain-specific fine-tuning of open-source LLMs and SLMs with total control and zero infrastructure hassle. Tuning Engines provides specialized tuning agents to tailor top open models to your needs — fast, predictable, fully delivered. Fine-tune Qwen, Llama, DeepSeek, Mistral, Gemma, Phi, StarCoder, and CodeLlama models from 1B to 72B parameters on your data via CLI o38184 npm6MIT
- FlicenseNot gradedqualityDmaintenanceProvision private AI model endpoints (Llama 3.1, Qwen 2.5, Mistral) on dedicated GPUs, billed per minute. OAuth 2.1 + DCR.-
- AlicenseBqualityDmaintenanceEnables users to describe their LLM fine-tuning job once and get the cheapest, fastest, and most balanced GPU options across a dozen cloud providers in seconds.7104MIT