{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_fe5z6329vp7n","handle":"mle-kit-mcp","url":"https://wellknown.network/agents/mle-kit-mcp","links":{"self":"https://wellknown.network/agents/mle-kit-mcp/record.json","html":"https://wellknown.network/agents/mle-kit-mcp","markdown":"https://wellknown.network/agents/mle-kit-mcp/record.md","api":"https://wellknown.network/api/v1/agents/mle-kit-mcp","status":"https://wellknown.network/api/v1/agents/mle-kit-mcp/status","claim":"https://wellknown.network/agents/mle-kit-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mle-kit-mcp/claim.json","badge":"https://wellknown.network/agents/mle-kit-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mle-kit-mcp/history","tools":"https://wellknown.network/api/v1/agents/mle-kit-mcp/tools"},"ard":{"identifier":"urn:air::server:mle-kit-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mle-kit-mcp","summary":"MCP server that provides different tools for MLE","description":"# MLE kit MCP\n\n[![PyPI](https://img.shields.io/pypi/v/mle-kit-mcp?label=PyPI%20package)](https://pypi.org/project/mle-kit-mcp/)\n[![CI](https://github.com/IlyaGusev/mle_kit_mcp/actions/workflows/python.yml/badge.svg)](https://github.com/IlyaGusev/mle_kit_mcp/actions/workflows/python.yml)\n[![License](https://img.shields.io/github/license/IlyaGusev/mle_kit_mcp)](LICENSE)\n\nMCP server providing practical tools for ML engineering workflows, including local/remote bash, a text editor, file search, remote GPU helpers (via vast.ai), and an OpenRouter LLM proxy.\n\n### Features\n- **bash**: Run commands in an isolated Docker container mounted to your `WORKSPACE_DIR`.\n- **text_editor**: View and edit files and directories in your workspace with undo support.\n- **glob / grep**: Fast filename globbing and ripgrep-based content search.\n- **remote_bash / remote_text_editor / remote_download**: Execute and edit on a remote GPU machine and sync files to/from it.\n- **llm_proxy_local / llm_proxy_remote**: Launch an OpenAI-compatible proxy backed by OpenRouter locally (in the bash container) or on the remote GPU.\n\n## Requirements\n- Python 3.12+\n- Docker daemon available (for `bash` tool)\n- ripgrep (`rg`) installed on the host (for `grep` tool)\n- `WORKSPACE_DIR` should be set with a path to working directory\n- Optional (for remote GPU tools): a `VAST_AI_KEY` with billing set up on vast.ai\n- Optional (for LLM proxy tools): an `OPENROUTER_API_KEY`\n\n## Install\nUsing uv (recommended):\n```bash\nuv sync\n```\n\nOr standard pip install:\n```bash\npython -m venv .venv && . .venv/bin/activate\npip install -e .\n```\n\n## Run the MCP server\nSet a workspace directory and start the server. The MCP endpoint is served at `/mcp`.\n\n```bash \nWORKSPACE_DIR=/absolute/path/to/workdir uv run python -m mle_kit_mcp --port 5057\n```\n\nDefaults:\n- `PORT` defaults to `5057` if `--port` is not provided\n- `mount_path=/` and `streamable_http_path=/mcp`\n\n### Claude Desktop config\n```json\n{\n  \"mcpServers\": {\n    \"mle_kit\": {\n     …","publisher":null,"homepage":"https://github.com/IlyaGusev/mle_kit_mcp","repository":"https://github.com/IlyaGusev/mle_kit_mcp","version":"1.2.10","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:mle-kit-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.825,"provenance":"derived"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.802,"provenance":"derived"}],"categories":["dev"],"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":"mle-kit-mcp","registry":"pypi","observedAt":"2026-10-28T15:26:24.458Z","publishedAt":"2025-11-01T14:10:19.100473Z","latestVersion":"1.2.10"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mle-kit-mcp","url":"https://pypi.org/project/mle-kit-mcp/","firstSeenAt":"2026-09-10T06:23:22.711Z","fetchedAt":"2026-10-28T15:25:37.305Z","normalizedAt":"2026-10-28T15:25:37.305Z"}]},"firstSeenAt":"2026-09-10T06:23:22.711Z","updatedAt":"2026-10-28T15:26:24.458Z"}