{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_7k28jzs3vzrr","handle":"mypr-mcp","url":"https://wellknown.network/agents/mypr-mcp","links":{"self":"https://wellknown.network/agents/mypr-mcp/record.json","html":"https://wellknown.network/agents/mypr-mcp","markdown":"https://wellknown.network/agents/mypr-mcp/record.md","api":"https://wellknown.network/api/v1/agents/mypr-mcp","status":"https://wellknown.network/api/v1/agents/mypr-mcp/status","claim":"https://wellknown.network/agents/mypr-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mypr-mcp/claim.json","badge":"https://wellknown.network/agents/mypr-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mypr-mcp/history","tools":"https://wellknown.network/api/v1/agents/mypr-mcp/tools"},"ard":{"identifier":"urn:air::server:mypr-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mypr-mcp","summary":"A persistent, workspace-shared Python environment for MCP agents","description":"# mypr-mcp\n\n`mypr-mcp` provides a persistent, workspace-scoped Python layer between an LLM agent and the workstation. Each workspace has one Python kernel. Every MCP connection opened for that workspace shares the same variables, imports, functions, and background-task handles.\n\nIt provides a development toolkit for LLM agents: file operations, code and document search, web search, Git, shell commands, HTTP, browser automation, network scanning, and system diagnostics through one Python API. Agents can combine these tools in scripts and extend the environment with reusable Python functions, skills, and external MCP integrations.\n\nThe runtime is intended for Linux, Python 3.14, and [uv](https://docs.astral.sh/uv/).\n\nLicensed under the [GNU Affero General Public License v3.0](LICENSE) (AGPL-3.0-only).\n\n## Run\n\nInstall [uv](https://docs.astral.sh/uv/getting-started/installation/), then configure your MCP client to launch:\n\n```sh\nuvx mypr-mcp serve\n```\n\nThe client communicates with the server over stdio. The server's working directory becomes the workspace, so configure the client to launch it from the directory where the agent should work. `uvx` downloads and runs the package automatically.\n\nFor clients using `mcpServers` JSON configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"mypr\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mypr-mcp\", \"serve\"]\n    }\n  }\n}\n```\n\nMake sure `uvx` is on the client's `PATH`, or use its absolute executable path.\n\n### Codex\n\nWith `uv` installed, add the following table to the target workspace's `.codex/config.toml`. Codex loads project configuration for trusted projects. Use `~/.codex/config.toml` instead for a user-wide registration. See the [official Codex MCP documentation](https://developers.openai.com/codex/mcp).\n\n```toml\n[mcp_servers.mypr]\ncommand = \"uvx\"\nargs = [\"mypr-mcp\", \"serve\"]\nstartup_timeout_sec = 180\ntool_timeout_sec = 60\nrequired = true\n```\n\nStart Codex in the target workspace. The MCP process uses its launch directory as the w…","publisher":null,"homepage":null,"repository":null,"version":"1.6.1","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:mypr-mcp","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":"infra.browser-automation","name":"Browser Automation","confidence":0.859,"provenance":"derived"},{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.836,"provenance":"derived"}],"categories":["dev","infra"],"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":"mypr-mcp","registry":"pypi","observedAt":"2026-10-28T17:24:10.099Z","publishedAt":"2026-10-13T12:57:18.830634Z","latestVersion":"1.6.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mypr-mcp","url":"https://pypi.org/project/mypr-mcp/","firstSeenAt":"2026-09-22T10:23:03.509Z","fetchedAt":"2026-10-28T17:23:05.116Z","normalizedAt":"2026-10-28T17:23:05.116Z"}]},"firstSeenAt":"2026-09-22T10:23:03.509Z","updatedAt":"2026-10-28T17:24:10.099Z"}