{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_z9xnpc34uzsx","handle":"pm4py-mcp","url":"https://wellknown.network/agents/pm4py-mcp","links":{"self":"https://wellknown.network/agents/pm4py-mcp/record.json","html":"https://wellknown.network/agents/pm4py-mcp","markdown":"https://wellknown.network/agents/pm4py-mcp/record.md","api":"https://wellknown.network/api/v1/agents/pm4py-mcp","status":"https://wellknown.network/api/v1/agents/pm4py-mcp/status","claim":"https://wellknown.network/agents/pm4py-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/pm4py-mcp/claim.json","badge":"https://wellknown.network/agents/pm4py-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/pm4py-mcp/history","tools":"https://wellknown.network/api/v1/agents/pm4py-mcp/tools"},"ard":{"identifier":"urn:air::server:pm4py-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"pm4py-mcp","summary":"Open-source Model Context Protocol server for process mining, wrapping PM4Py behind a small handle-based tool surface.","description":"# pm4py-mcp\n\nAn AGPL-licensed, stdio-first **Model Context Protocol** server that wraps [PM4Py](https://github.com/process-intelligence-solutions/pm4py) behind a small handle-based tool surface — making research-grade process mining available to Claude and any MCP-capable agent, locally and on open standards (XES, **OCEL 2.0**, BPMN, PNML).\n\n> **Status:** Phase 2 Part 2 complete — `pm4py-mcp 0.4.1` ships **67 workflow-shaped tools + 7 curated prompts** spanning I/O, discovery (traditional + DECLARE + log skeleton + POWL + temporal profile), conformance, filtering, statistics, visualization (Graphviz + matplotlib), OCEL 2.0, textual abstractions, domain-context injection, model conversions, **organizational mining**, **simulation**, and Markdown report rendering. Installable via `uvx pm4py-mcp`. (0.4.1 adds 5 organizational-mining discovery tools + `abstract_sna` + `simulate_log` + `visualize_dotted_chart` + `visualize_performance_spectrum` + `/organizational_analysis` prompt.)\n\n**Today** — load XES / CSV / Parquet logs or OCEL 2.0 (JSON / XML / SQLite), discover Petri nets / process trees / BPMN / DFGs / object-centric Petri nets / OC-DFGs, run token-replay or alignment conformance, filter chains, render dual-channel PNG + SVG — and now **turn every artifact into a textual abstraction the LLM can read directly**, **register domain SOPs that prompts respect across the session**, and **render a final Markdown report from accumulated findings**. 48 natural-language tools + 6 slash-command prompts, fully local, nothing leaves your machine.\n\n**Next (0.4.0)** — advanced discovery (DECLARE, POWL, log skeleton, organizational mining), model conversions (Petri ↔ BPMN ↔ Process Tree ↔ POWL), simulation (`play_out`), dotted chart + performance spectrum, plus the matching `abstract_declare` / `abstract_log_skeleton` / `abstract_temporal_profile` tools. Team deployment via Streamable HTTP lands in Phase 4.\n\n## Why\n\nNo open-source MCP server for process mining exists today. Celo…","publisher":null,"homepage":"https://github.com/azizketata/pm4py-mcp","repository":"https://github.com/azizketata/pm4py-mcp/blob/main/CHANGELOG.md","version":"0.4.1","license":null,"protocols":["mcp"],"tags":["agents","claude","mcp","model-context-protocol","ocel","pm4py","process-mining","xes"],"pricing":null,"endpoints":[{"url":"pypi:pm4py-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":"analytics.reporting","name":"Reporting & Dashboards","confidence":1,"provenance":"derived"}],"categories":["analytics"],"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":"pm4py-mcp","registry":"pypi","observedAt":"2026-10-28T20:22:48.539Z","publishedAt":"2026-04-24T14:12:55.256168Z","latestVersion":"0.4.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"pm4py-mcp","url":"https://pypi.org/project/pm4py-mcp/","firstSeenAt":"2026-09-10T10:23:17.959Z","fetchedAt":"2026-10-28T20:20:34.393Z","normalizedAt":"2026-10-28T20:20:34.393Z"}]},"firstSeenAt":"2026-09-10T10:23:17.959Z","updatedAt":"2026-10-28T20:22:48.539Z"}