omnitrix MCP server
Commit Nov 14, 2026Delegates tasks from Claude Code to your existing AI subscriptions and API keys to optimize quota usage and model selection.
Also known as MdHashim1011/omnitrix
- Stars
- 2
- Tools
- 6
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 14, 2026
- License
- Apache-2.0
What is omnitrix MCP?
omnitrix delegates tasks from Claude Code to your existing AI subscriptions and API keys to optimize quota usage and model selection. It exposes 6 tools, such as pool_status, route_preview, dispatch.
Summary generated from the project's README
About omnitrix MCP server
Developers using Claude Code can optimize their model usage and credit consumption by delegating specific tasks to other AI subscriptions and API keys. Instead of performing every step itself, Claude acts as a manager that divides a large job into smaller tasks and assigns them to the most suitable provider based on availability, cost, and task type. This setup allows you to use existing ChatGPT Plus subscriptions via Codex, Gemini for large logs, DeepSeek for reasoning, or local Ollama models for private work.
The system runs locally as an MCP server and integrates directly into your Claude Code session. It manages a pool of accounts, tracking remaining quota and rate limits through a dashboard or a status line. To protect privacy, tasks are private by default, and sensitive work can be restricted to local providers. The routing engine uses a scoring system that considers model suitability, remaining quota, and past performance to select the best worker for each job.
What you can do with it
- 1Distribute complex coding tasksAssign different parts of a development project to various models to save Claude credits.
- 2Process large datasets with GeminiUse Gemini to handle the heavy lifting of reading massive log files.
- 3Execute private reasoning tasksRoute sensitive or secret work to local models to ensure data privacy.
- 4Monitor AI subscription limitsTrack the remaining quota and reset times for multiple AI accounts from a single dashboard.
Written from the project's README. Every use case is checked against a quote from it.
omnitrix MCP tools 6
Detected from the READMEpool_statusroute_previewdispatchget_resultsread_outputrate_result
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemdhashim1011/omnitrix is public and reachablegithub.com/mdhashim1011/omnitrix ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/mdhashim1011/omnitrix ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model6 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubomnitrix
Claude plans the work, and your other AI accounts carry it out.
I built omnitrix because I repeatedly ran out of Claude credits while the ChatGPT Plus and Gemini subscriptions that my friends and I pay for remained largely unused.
omnitrix is built for the frontier-model subscriptions and API keys you already pay for, and it runs inside your existing Claude Code session. Claude remains in charge: it divides the job into tasks and reviews the results. omnitrix sends each task to an account that suits the work and still has quota available. For example, it can use Codex on your ChatGPT plan for code edits, Gemini for reading very large logs, DeepSeek or Kimi for reasoning and review, or a local model for private work. It also supports any service that implements the OpenAI or Anthropic API.
You can monitor the pool without leaving Claude Code. The status line shows up to four accounts with their remaining quota or status, and omnitrix instructs Claude to check the same data before it assigns work. Claude reads short results instead of performing every step itself, which uses less of your Claude usage limit.
Installation
omnitrix requires Node.js 20 or later.
npm install -g https://github.com/MdHashim1011/omnitrix/releases/latest/download/omnitrix.tgz
Quick start
omnitrix providers
omnitrix add ollama
omnitrix add deepseek --key-env DEEPSEEK_API_KEY
omnitrix add codex --label "My ChatGPT Plus" --login
omnitrix test deepseek
omnitrix setup-claude
These commands list the available providers, add your local Ollama models and a DeepSeek key, sign in to Codex with your ChatGPT plan, confirm that DeepSeek responds, and register omnitrix with Claude Code as both an MCP server and a status line.
Restart Claude Code and give it a substantial task, such as "add tests for the billing module and document the API". Claude receives the omnitrix tools along with brief instructions on when to delegate work.
How tasks are routed
Every task that Claude sends has a type, such as code, review or bulk work, and a privacy level. omnitrix first excludes any account that cannot accept the task at that moment because it is:
- disabled or signed out
- cooling down after a rate limit
- out of quota for the current window
- not permitted to receive private work
Each remaining account receives a score based on four factors: how well the model fits the task, how much quota remains, what the model costs, and how often its past work was accepted. The highest-scoring account receives the task. If that call fails, the next account in the ranking takes over without any action from Claude.
Code tasks go only to agent CLIs that can edit files. Each task runs on a new branch in its own git worktree, so two workers never share a checkout.
An account's concurrency limit applies to all omnitrix processes on the same computer, such as the MCP server, the dashboard and the command line. A job waits in the queue until the account has a free slot. The limit does not apply across different computers.
A request to an API model may take up to 2 minutes for a small task, 5 minutes for a medium one and 10 minutes for a large one, and never longer than the job limit set with omnitrix settings --timeout. Agent CLIs such as Codex may use the whole job limit, because they work in many steps. When a model times out or returns a server error, only that model is paused for 5 minutes, and the job continues on other accounts or models.
Skill scores begin as an estimate based on the model's name. You can set them yourself, and omnitrix also adjusts its ranking over time: when Claude accepts or rejects a result, the model's record for that type of task is updated.
omnitrix models deepseek
omnitrix model deepseek deepseek-v4-pro --coding 9 --reasoning 9
omnitrix route --type review "check this diff for auth bugs"
Monitoring quota
The dashboard, shown with example data. Run omnitrix dashboard to open your own.
The dashboard shows each account's name, owner, usage today and the quota remaining in each tracked window. In Claude Code, the status line gives a compact summary of up to four accounts. The Claude figures at the end appear when Claude Code provides them, which it does on Pro and Max plans:
omnitrix 5/6 ready · codex-main 38% · deepseek 788 left · kimi wait · groq-free 36% │ Claude 5h 34% 7d 12%
Most subscriptions neither publish exact limits nor provide a way to query the remaining allowance, so omnitrix states the source of each figure. For a ChatGPT plan, it queries Codex directly and shows the percentage remaining in the 5-hour and 7-day windows, along with the time each window resets. This query ignores any API key exported in your environment, so the figures always belong to the account's own plan. When a provider sends rate-limit headers, omnitrix displays those values. In all other cases, it counts the requests and tokens it has sent against the limits you configured. A 429 or 402 response from the provider always overrides the count.
Privacy
Tasks are private by default, which keeps them away from accounts flagged as possibly training on prompts. omnitrix flags Mistral and the Gemini API by default, and you can flag any other account with omnitrix set <id> --trains-on-data. A task marked secret runs only on local providers such as Ollama. omnitrix sends data only to the providers you connect, and it collects no telemetry.
Connecting accounts
| Account type | Command |
|---|---|
| ChatGPT plan through Codex | omnitrix add codex --login |
| Your own Claude subscription | omnitrix add claude-code --login |
| An API key | omnitrix add kimi --key-env MOONSHOT_API_KEY |
| Gemini | omnitrix add gemini --key-env GEMINI_API_KEY with a key from Google AI Studio. A Google AI Pro sign-in works only through antigravity, which is experimental. |
| A coding plan (GLM, Kimi, MiniMax) | omnitrix add claude-code --base-url https://api.z.ai/api/anthropic --key-env ZAI_API_KEY |
| A local model | omnitrix add ollama (LM Studio, llama.cpp and vLLM are also supported) |
| Any other service | omnitrix add custom-openai --base-url https://host/v1 --key-env MY_KEY --model my-model |
Run omnitrix providers for the full list. Each CLI account has its own profile folder, so two Codex logins never mix. Keys are stored in ~/.omnitrix/secrets.json. If you use --key-env, omnitrix does not store the key at all.
To track a limit, specify it when you add the account or later with omnitrix set:
omnitrix set codex-main --r5h 120 # requests per 5 hours
omnitrix set groq-free --rpm 30 --rpd 1000
omnitrix set deepseek --tpd 4000000 # tokens per day
The available options are --rpm (requests per minute), --r5h (requests per 5 hours), --rpd (requests per day), --rpw (requests per week), --tpd (tokens per day) and --tpm (tokens per month).
MCP tools
omnitrix runs as an MCP server and gives Claude the following tools:
| Tool | Purpose |
|---|---|
pool_status |
Lists every account with its state, owner, models and remaining quota |
route_preview |
Shows which account would receive each task, and why, without running anything |
dispatch |
Sends up to 30 tasks at once and runs independent tasks in parallel |
get_results |
Waits for jobs and returns a short preview of each result |
read_output |
Reads a full result in pages when the preview is not sufficient |
rate_result |
Accepts or rejects a result so that the router can learn from it |
cancel_job, list_jobs |
Cancels a job or lists recent jobs |
The pool_status, dispatch and get_results tools declare output schemas, and their structured data contains everything their text shows. list_jobs also lists jobs that other omnitrix processes started, and cancel_job can cancel them.
A task can set effort to low, medium or high to ask a reasoning model to think less or more. omnitrix passes it to Codex and to OpenAI-compatible APIs such as Gemini; without it, each provider uses its own default. From the command line, use omnitrix run --effort high.
By default, previews are limited to 1,500 characters to keep Claude's token usage low; omnitrix settings --preview-chars changes the limit. Full outputs remain on disk.
Commands
omnitrix providers list the providers you can connect
omnitrix add <provider> connect an account
omnitrix login <id> sign in a CLI account in its own profile
omnitrix list show accounts, usage and remaining quota
omnitrix test <id> send a small request to check an account
omnitrix set <id> change limits, owner, key or concurrency
omnitrix enable|disable <id> enable or disable an account
omnitrix remove <id> remove an account (--purge also deletes its login)
omnitrix models <id> show model scores (--refresh queries the provider again)
omnitrix model <id> <model> set scores or prices, or --add or --remove a model
omnitrix route <prompt> show which model would receive a task
omnitrix run <prompt> run one task and print the answer
omnitrix settings set the mode, privacy, and pinned or banned providers
omnitrix dashboard open a live web dashboard on 127.0.0.1
omnitrix setup-claude register with Claude Code
omnitrix clean delete finished jobs and worktrees older than 14 days (branches are kept)
omnitrix doctor check the setup
omnitrix settings --mode saver prefers free and low-cost models, --mode quality prefers the strongest models, and --pin code=codex-main tries that account first for code tasks whenever it is eligible.
Provider terms
omnitrix uses only official CLIs and APIs with credentials that you enter yourself. It provides no means of importing another person's login.
OpenAI, Google and Anthropic all prohibit sharing a consumer account, so connect only accounts that you own. A friend who wishes to contribute should use an API key billed to them. Anthropic permits Claude subscriptions for ordinary individual use only. Google has suspended accounts that used Antigravity sign-in through third-party tools, so omnitrix marks Antigravity as experimental and recommends Gemini API keys instead. Free tiers are often limited per organization, so additional keys from the same organization provide no extra quota.
omnitrix is an independent project. It is not affiliated with OpenAI, Google, Anthropic or any other AI provider, or with Cartoon Network and Warner Bros. Discovery. Product names and trademarks belong to their respective owners.
Current limitations
Remaining quota is measured for ChatGPT plans. For other subscriptions it is an estimate, because those providers do not offer an API for it. The Codex and Claude Code drivers depend on the current flags of those tools and may need updating when the flags change. The other agent CLIs have been tested less thoroughly than Codex.
Roadmap
The next planned feature is friend nodes. A friend would run a small agent on their own computer with their own login and a daily cap that they can pause at any time, so their account never leaves their machine. Later plans include a second model to verify critical results, and drivers for Aider and Goose.
Development
git clone https://github.com/MdHashim1011/omnitrix.git
cd omnitrix
npm install
npm run build
npm test
The tests use fake providers and a fake agent CLI, so they require neither API keys nor network access.
License
Apache-2.0. Copyright 2026 Mohamed Hashim.
omnitrix MCP questions
What tools does omnitrix MCP provide?
It exposes 6 tools, including pool_status, route_preview, dispatch, get_results, read_output.
How does omnitrix route tasks to different models?
It scores accounts based on task type, privacy requirements, remaining quota, cost, and past performance to select the best model.
Can I use local models with omnitrix?
Yes, it supports local models through providers like Ollama, LM Studio, llama.cpp, and vLLM.
Does omnitrix collect my data or telemetry?
No, it sends data only to the providers you connect and collects no telemetry.
How does it handle privacy for sensitive tasks?
Tasks are private by default to avoid models that train on prompts, and 'secret' tasks are restricted to local providers.