{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_tcqdagrk9r9u","handle":"casino-mcp","url":"https://wellknown.network/agents/casino-mcp","links":{"self":"https://wellknown.network/agents/casino-mcp/record.json","html":"https://wellknown.network/agents/casino-mcp","markdown":"https://wellknown.network/agents/casino-mcp/record.md","api":"https://wellknown.network/api/v1/agents/casino-mcp","status":"https://wellknown.network/api/v1/agents/casino-mcp/status","claim":"https://wellknown.network/agents/casino-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/casino-mcp/claim.json","badge":"https://wellknown.network/agents/casino-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/casino-mcp/history","tools":"https://wellknown.network/api/v1/agents/casino-mcp/tools"},"ard":{"identifier":"urn:air::server:casino-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"casino-mcp","summary":"An MCP control plane over the Fortran CASINO quantum Monte Carlo code","description":"# casino-mcp\n\n[![PyPI](https://img.shields.io/pypi/v/casino-mcp.svg)](https://pypi.org/project/casino-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/casino-mcp.svg)](https://pypi.org/project/casino-mcp/)\n[![CI](https://github.com/Konjkov/casino-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/Konjkov/casino-mcp/actions/workflows/ci.yml)\n[![Licence](https://img.shields.io/pypi/l/casino-mcp.svg)](LICENSE)\n\n[![casino-mcp MCP server](https://glama.ai/mcp/servers/Konjkov/casino-mcp/badges/card.svg)](https://glama.ai/mcp/servers/Konjkov/casino-mcp)\n\nAn MCP control plane over the Fortran [CASINO](https://vallico.net/casinoqmc/) quantum Monte\nCarlo code: write the `input` for the next calculation — and the blank Jastrow factor, backflow\nfunction and geminal wave function for the first one — start it, know what is running, stop it, and read the\nresult as structured data instead of shipping 4000 lines of text into a model's context,\nincluding from a DMC run that is still going, which has no energy in `out` at all until its\nlast block.\n\n> **Beta (0.6.0).** Everything below is tested against a real CASINO: the recipes against\n> `runqmc`'s own input check, and every file the wave function writer produces against a CASINO\n> test run. Interfaces may still move before 1.0.\n\n## What it is, and what it is not\n\nCASINO already has the primitives — `opt_plan`, `runqmc --auto-continue`, `multirun`,\n`envmc`, `make_E_v_dt`. What it has no place for is the layer between them: machine-readable\nresults, a memory of what was run, and the judgement calls that sit between the steps\n(\"has the variance plateaued?\", \"is this timestep still in the linear regime?\"). That layer\nis what this package is, and three rules keep it honest:\n\n1. **No number is produced by the model.** Every value a tool returns is read from a file and\n   carries the line it came from. What CASINO did not print comes back as `null` with a\n   reason, never a guess.\n2. **Every result is reproducible from its…","publisher":null,"homepage":null,"repository":"https://github.com/Konjkov/casino-mcp/issues","version":"0.6.0","license":null,"protocols":["mcp"],"tags":["mcp","casino","quantum","monte","carlo","qmc","claude"],"pricing":null,"endpoints":[{"url":"pypi:casino-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"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"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":"casino-mcp","registry":"pypi","observedAt":"2026-09-15T11:22:44.313Z","publishedAt":"2026-09-01T12:09:21.678853Z","latestVersion":"0.6.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"casino-mcp","url":"https://pypi.org/project/casino-mcp/","firstSeenAt":"2026-09-09T11:29:45.718Z","fetchedAt":"2026-09-15T11:20:52.497Z","normalizedAt":"2026-09-15T11:20:52.497Z"}]},"firstSeenAt":"2026-09-09T11:29:45.718Z","updatedAt":"2026-09-15T11:22:44.313Z"}