TinyAssets MCP server
Commit Nov 12, 2026Connects any model source to build and run customizable agent files and skills through a single MCP interface.
Also known as Jonnyton/Workflow
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.0
- Last commit
- Nov 12, 2026
- License
- MIT
What is TinyAssets MCP?
TinyAssets connects any model source to build and run customizable agent files and skills through a single MCP interface.
Summary generated from the project's README
About TinyAssets MCP server
TinyAssets provides a single MCP interface that allows users to connect their own model subscriptions to build and run customizable agent files and skills. Instead of providing a model itself, the platform acts as plumbing that reaches any engine through one door. This setup enables a consistent agent definition across different providers without requiring provider-specific code.
Users interact with the system via a web app, an Android app currently in closed testing, or by adding the MCP connector as a custom connector in Claude or ChatGPT. The agent's capabilities are defined by editable files, skills, and packages. Because the system relies on the user's own engine, such as a provider's CLI or an existing main agent, it functions as a layer around the engine to manage state and configuration.
What you can do with it
- 1Connect existing model subscriptionsA developer can link their own AI provider keys to use as the engine for custom agents.
- 2Create custom agent filesUsers can build unique agent behaviors by editing specific files and skills.
- 3Integrate with major AI platformsYou can add this server as a custom connector within Claude or ChatGPT interfaces.
- 4Standardize agent definitionsDevelopers can use one agent definition that works across various different engines.
Written from the project's README. Every use case is checked against a quote from it.
How to install TinyAssets MCP
Formats verified 10 Nov 2026Install TinyAssets MCP in Claude Code
$ claude mcp add --transport http workflow https://tinyassets.io/mcp-directoryInstall TinyAssets MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"workflow": {
"url": "https://tinyassets.io/mcp-directory"
}
}
}Install TinyAssets MCP in VS Code
.vscode/mcp.json
{
"servers": {
"workflow": {
"type": "http",
"url": "https://tinyassets.io/mcp-directory"
}
}
}Install TinyAssets MCP in Codex
~/.codex/config.toml
[mcp_servers.workflow] url = "https://tinyassets.io/mcp-directory"
Install TinyAssets MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"workflow": {
"httpUrl": "https://tinyassets.io/mcp-directory"
}
}
}README
View on GitHubTinyAssets
An agent of your own in the chat bubble: connect any model source, then build what you need from there.
Try it
The hosted app is the supported way in. Android is in a closed Google Play test, not a public store listing. The steps, what to expect, and how to report a bug are in docs/getting-started/testers.md.
- Web app: https://tinyassets.io/app
- Start page (web, Claude or ChatGPT connector, Android, desktop): https://tinyassets.io/start/
- Android closed test: https://play.google.com/apps/testing/io.tinyassets.app
You connect your own model subscription. This project does not supply a model. What is free, and what is not built yet, is on https://tinyassets.io/fine-print/.
Running the production server on your own machine is not a supported install. Status: docs/getting-started/self-hosting.md.
Direction
The founder owns this section. To re-steer, replace a line; never add one beside it.
python scripts/sync_direction.py copies it verbatim into AGENTS.md.
- Product: a default bubble agent that continuously matches and beats the industry-leading main agents (Grok Bot, Muse, ChatGPT dots, Claude Duet), shipped as a starter package of agent files that runs on the user's own engine: their provider's unmodified CLI on their subscription or key, or their own main agent; users customize the agent's files and interface to build anything.
- Plumbing: an agent is files (
AGENTS.md, skills, MCP config, hooks) plus TinyAssets state, run by an unmodified engine (a provider's CLI in the user's sandbox, the user's main agent over MCP, or pi's CLI); TinyAssets is everything around the engine and reaches every engine through one MCP door; one agent definition for every engine; no provider-specific code: engine differences are data. - The agent's abilities are editable files, skills and packages. The platform does not build feature editors or pre-built features.
- Users connect any model source; default to their strongest connected source.
- Foundational patches are brought FORWARD, so pre-migration band-aids never delay positive architectural moves. Weigh the totality of pending work, so each module is always pursuing or maintaining its best architecture, and refactor and reorder the remaining work to get there. (Today that foundation is the clean-sheet platform, as one clean cutover:
platform/is the only path, one migration in a short maintenance window after a full backup, and the old stack, with its docs, skills and rules, is deleted in the same change.) - Ship live fast and verify live. LESS process: delete stale docs, tests and notes rather than adding more.
- Long-term goal: in both the Google Play and Apple App Store, and listed in the major agents' connector directories (Meta Muse, ChatGPT, Claude) so users find TinyAssets by search, not only as a custom connector, with growing downloads and positive reviews.
- 24/7 uptime with zero hosts online: every surface works with no host machine on.
No longer the direction: "a global goals engine", Goal ladders, and fantasy as the default domain. Where any older doc disagrees with this section, this section wins.
Links
- App: https://tinyassets.io/app
- MCP connector (add it as a custom connector in Claude or ChatGPT): https://tinyassets.io/mcp
- Testers: docs/getting-started/testers.md
- Live status (deployed sha, canary, providers): https://tinyassets.io/fine-print
Contributing
Python 3.11+. Tests run offline; providers are mocked, so no API keys are needed. How to contribute, and what this repo does not promise, is CONTRIBUTING.md.
git clone https://github.com/TinyAssets/TinyAssets.git
cd TinyAssets
python -m venv .venv && source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e ".[dev]"
python -m scripts.ci_structural_guards # the fast guards every PR runs
pytest -q tests/test_<area>.py # the tests your change touches
ruff check <changed files>
CI runs the rest. How work is done here: AGENTS.md.
License
MIT — see LICENSE. Built by Jonathan Farnsworth (jonathan.m.farnsworth@gmail.com, @Jonnyton); the only co-authors are the project's own AI agents.
TinyAssets MCP questions
How do I add TinyAssets MCP to Claude Code?
Run claude mcp add --transport http workflow https://tinyassets.io/mcp-directory in your terminal. Add --scope user to make it available in every project.
How do I add TinyAssets MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Do I need to pay for a model through TinyAssets?
No, you connect your own model subscription; the project does not supply a model.
Can I run the production server on my own computer?
Running the production server on your own machine is not a supported installation.
How do I use TinyAssets with Claude or ChatGPT?
You can add it as a custom connector in Claude or ChatGPT using the MCP connector.