{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_pujbyahwxeg5","handle":"modal-mcp-toolbox","url":"https://wellknown.network/agents/modal-mcp-toolbox","links":{"self":"https://wellknown.network/agents/modal-mcp-toolbox/record.json","html":"https://wellknown.network/agents/modal-mcp-toolbox","markdown":"https://wellknown.network/agents/modal-mcp-toolbox/record.md","api":"https://wellknown.network/api/v1/agents/modal-mcp-toolbox","status":"https://wellknown.network/api/v1/agents/modal-mcp-toolbox/status","claim":"https://wellknown.network/agents/modal-mcp-toolbox/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/modal-mcp-toolbox/claim.json","badge":"https://wellknown.network/agents/modal-mcp-toolbox/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/modal-mcp-toolbox/history","tools":"https://wellknown.network/api/v1/agents/modal-mcp-toolbox/tools"},"ard":{"identifier":"urn:air::server:modal-mcp-toolbox","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"modal-mcp-toolbox","summary":"A collection of Model Context Protocol (MCP) tools for Modal","description":"# Modal MCP Toolbox 🛠️\n\n[![smithery badge](https://smithery.ai/badge/@philipp-eisen/modal-mcp-toolbox)](https://smithery.ai/server/@philipp-eisen/modal-mcp-toolbox)\n\nA collection of Model Context Protocol (MCP) tools that run on Modal.\nThis let's you extend the capabilities of your LLM in tools such as [Goose](https://block.github.io/goose/) or the [Claude Desktop App](https://claude.ai/download).\n\n## Tools\n\n- `run_python_code_in_sandbox`: Let's you run python code in a sandboxed environment.\n- `generate_flux_image`: Generate an image using the FLUX model.\n\n## Demo\n\n### Flux Image Generation\n\n![🎬Flux Image Generation](./assets/flux.gif)\n\n### Python Code Execution\n\n![🎬Python Code Execution](./assets/python-sandbox.gif)\n\n## Prerequisites\n\n- A [modal account](https://modal.com/signup) and a configured modal CLI.\n- [UV](https://github.com/astral-sh/uv?tab=readme-ov-file#installation)\n- A client that supports MCP. Such as the [Claude Desktop App](https://claude.ai/download) or [Goose](https://block.github.io/goose/)\n\nThis runs against your modal account, so you will need to have a modal account and be logged in.\n\n## Installation\n\nInstallation depends on the client that uses the MCP. Here is instructions for Claude and Goose.\n\n### Claude\n\nGot to `Settings > Developer` in the Claude Desktop App. And click on Edit Config.\n![🖼️Claude Settings](./assets/claude-settings.png)\n\nAdd the config for the mcp server. My config looks like this:\n\n```json\n{\n  \"mcpServers\": {\n    \"modal-toolbox\": {\n      \"command\": \"uvx\",\n      \"args\": [\"modal-mcp-toolbox\"]\n    }\n  }\n}\n```\n\n### Goose\n\nGo to `Settings` and Click on Add.\n\n![🖼️Goose Settings](./assets/goose-settings-1.png)\n\nThen add an extension like in the screenshot below.\nThe important part is to set command to:\n\n```\nuvx modal-mcp-toolbox\n```\n\nThe rest you can fill in as you like.\n\n![🖼️Goose MCP Settings](./assets/goose-settings-2.png)\n\n### Installing via Smithery (not working currently)\n\nTo install Modal MCP Toolbox for Claude De…","publisher":null,"homepage":null,"repository":null,"version":"0.1.12","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:modal-mcp-toolbox","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"code.execution","name":"Code Execution","confidence":0.859,"provenance":"derived"},{"slug":"media.image-generation","name":"Image Generation","confidence":0.825,"provenance":"derived"}],"categories":["code","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"modal-mcp-toolbox","registry":"pypi","observedAt":"2026-10-28T16:27:15.397Z","publishedAt":"2025-02-24T12:32:04.172839Z","latestVersion":"0.1.12"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"modal-mcp-toolbox","url":"https://pypi.org/project/modal-mcp-toolbox/","firstSeenAt":"2026-09-10T06:23:33.665Z","fetchedAt":"2026-10-28T16:25:09.317Z","normalizedAt":"2026-10-28T16:25:09.317Z"}]},"firstSeenAt":"2026-09-10T06:23:33.665Z","updatedAt":"2026-10-28T16:27:15.397Z"}