Governed OT data tap: 14 field protocols + cross-protocol RCA brain; audit + MOC gating.
English · 中文
Ask an AI agent why the line stopped — and get an answer that cites its evidence.
A vendor-neutral, read-first data tap for the factory floor. It speaks 14 field protocols, correlates what it reads across them, and hands your agent an evidence-cited verdict instead of a guess. Every call is audited, and no reading ever phones home.
pip install "iaiops[opcua]" # pick your protocol — or [all]
iaiops init # write ~/.iaiops/config.yaml
iaiops doctor # check the setup before you trust it
Prefer a container? The published image is cosign-signed and runs non-root. It speaks MCP over stdio, so keep stdin open and mount a volume for the audit store:
cosign verify --key deploy/margo/cosign.pub ghcr.io/industrial-aiops/iaiops:0.28.0-factory
docker run -i --rm -v iaiops-state:/home/iaiops/.iaiops \
ghcr.io/industrial-aiops/iaiops:0.28.0-factory
For a hardened or air-gapped deployment (read-only rootfs, cap_drop: ALL, no-new-privileges,
optional on-box LLM) use deploy/margo/compose.yaml and
deploy/airgap/. The analysis engine needs no GPU and no model API — it is
deterministic; an LLM is optional and only phrases the verdict.
| Reads | OPC-UA (+ Historical Access, tag auto-discovery) · Modbus TCP/RTU · S7comm · Mitsubishi MC · Omron FINS · MTConnect · MQTT/Sparkplug B · EtherNet/IP · EtherCAT · PROFINET · SECS/GEM · HART-IP · BACnet/IP · IO-Link — plus read-only REST layers for BAS supervisors (Metasys / Niagara) and Ignition Gateway |
| Figures out | downtime root cause (the flagship copilot), alarm floods (ISA-18.2), broken dataflows, data trustworthiness, OEE, asset inventory, legacy PLC program explainer (ST/AWL/L5X) |
| Governs | audit · budget · risk-tier · undo — on every call, through one engine, from both MCP and CLI |
| Stays yours | no telemetry, no phone-home. Six tools can send data off-box by design (stream_publish, stream_publish_event, uns_publish, historian_push, mqtt_publish, rca_narrate) — IAIOPS_NO_EGRESS=1 withholds all six for an air-gapped posture |
Ten per-industry editions ship in this package — fab · factory · process · building · water ·
warehouse · clinical · pharma · renewables · plcnext — each adding its own read-only advisory checks.
Substation / utility telecontrol (IEC-104 · DNP3 · IEC-61850) ships separately as
iaiops-energy.
Four commands. Only one of them touches a device, and it prints what it will send before it sends anything.
pip install "iaiops[modbus]" # pick the protocol you actually have, or [all]
iaiops onboard status # ← run this first. Contacts NOTHING.
iaiops doctor # config, secrets, reachability — and the version
iaiops readiness # every scenario, and what each gap needs
onboard status answers the smaller questions you have first: which journey is
this site on — reading its devices directly, or subscribing to a UNS broker its
data already flows through — which step of it are you on, and what is the one
command that advances it? It is derived from your store and config.yaml every
time. The one thing it keeps is a namespace audit verdict, and that counts only for
the broker and topic filter it was taken on and always shows its age — so edit
config.yaml by hand and the answer stays true.
readiness reads your config and local store and answers one question: which
scenarios can this site run today, and what does each gap need? Every gap comes
with the command that closes it, ranked by how much it unlocks. No agent, no
cloud, no account, and nothing on the wire.
Then the path, in the order that matters — survey what is there, take a bounded sample, and only then explain it:
| contacts a device? | ||
|---|---|---|
| Survey | iaiops scan plan → iaiops scan run | preview sends nothing; the run itemises every packet class it sent |
| Configure | iaiops onboard draft → you merge it into config.yaml | no — it reads the stored scan, and writes nothing |
| Tap | iaiops collect run line1 --duration 7d | yes — and it reports what it saw and what it missed |
| Declare | iaiops tags export → a person fills in role → iaiops tags apply --by <you> | no — the role column comes out empty on purpose |
| Explain | iaiops oee measure --since … --until … · iaiops investigate open · iaiops diag rca | no — all over collected history |
See the whole thing run against a real device in about two minutes, including
a genuine mid-run outage, with ./demo/oee-line/run_demo.sh — no hardware, no
configuration, nothing written outside a temporary directory.
demo/oee-line/ explains what each step is for and what the
numbers do and do not claim.
OT is exactly where you want an agent on a tight leash. The read paths are the product; the few write paths are OT-dangerous, off by default, and gated by MOC discipline — dry-run, one-shot approval, undo capture, hash-chained audit.
The analysis layers cannot reach a language model. That is a guard, not a slogan:
tests/test_brain_is_llm_free.py scans eight packages — brain, discovery, runtime,
readiness, collect, knowledge, retain, connectors — for any import that could reach one,
and an empty result is the guarantee. A model is used in exactly two places, and neither is
load-bearing: rca_narrate rephrases a verdict that was already computed and already cited, and an
agent front-end decides which tool to call. Remove both and the numbers are the same numbers.
That guard is static — it proves nothing can call a model. For a validation team the sentence they are asked to accept is the executed one, so it is executed:
iaiops verify determinism --out determinism-record.json
A pinned in-repo dataset goes through availability, production counts, the Six Big Losses,
ISA-18.2 alarm load, control charts, the conservative baseline and the RCA copilot. Each result is
canonically encoded and digested; the suite runs twice in this process and once in each of two
fresh interpreters started at different PYTHONHASHSEED values — the arm that catches a set or
dict iteration order reaching a result, which a single run never can. The socket API raises
throughout, so a computation that reached for a device or a hostname fails here instead of quietly
working on a machine that happened to be online. Afterwards the run is asked what it pulled in:
a model library that was already loaded (an MCP server holds iaiops.core.llm for the opt-in
narration tool) is recorded, not judged — only what the suite itself imported can condemn it.
The record separates result (identical every run — the part to sign) from context (when and
where this run happened). Two good runs are not byte-identical records, and someone will diff
them, so the halves are named rather than mixed.
This is the form the claim has to take to be usable: not "our model is accurate", which is not
evidence in a GxP context, but a test case someone can write into an IQ/OQ protocol — remove the
model, block the network, re-run the standard dataset, compare the hash — execute, and sign.
verify_determinism is the same check from the MCP side; iaiops verify suite lists what it
covers without running it.
Short version: verified against real protocol libraries, containers and in-process servers — not yet against real plant gear. We grade evidence rather than saying "tested", because a real container round-trip and a synthetic fixture are not the same claim.
| Rung | Who judges our frames | Protocols at this rung today |
|---|---|---|
| 2a — real wire to a third-party server | somebody else's implementation of the spec | OPC-UA (Microsoft opc-plc; certificate trust enforced both ways) · Modbus TCP (pymodbus) · Modbus RTU (pymodbus over a socat PTY) · MQTT / Sparkplug B (a real mosquitto broker) · BACnet/IP (bacpypes3, two IPs on one subnet) · MTConnect (the Institute's own cppagent) · SECS/GEM (secsgem equipment side) · EtherNet/IP (identification) |
| 2b — real wire to a server we wrote from the spec | the third-party client parses our frames | S7comm (pyS7) · Mitsubishi MC (pymcprotocol) · EtherNet/IP (tag layer — pycomm3, all three driver routes) · PROFINET-DCP |
| 2c — real wire, but both ends are ours | nobody independent | Omron FINS · IO-Link · HART-IP (codec itself at rung 1, against hart-protocol) |
| mock only — protocol logic exercised, nothing on the wire | — | EtherCAT · BAS (Metasys / Niagara) · Ignition gateway |
| 3 — real physical / vendor device | the device | zero, for every protocol |
Each row's detail — and, per protocol, what is still not covered — is in
docs/VERIFICATION-RECORD.md. That file is the
record; this table is its summary, and a test fails if the two disagree.
Per-protocol evidence — including what each test does not cover — is in
docs/VERIFICATION-RECORD.md, one row per protocol, naming the test
behind each claim. Every 待核实 is hardware-gated, not forgotten — each one names the equipment that would settle it.
我们在找现场测试伙伴。 软件里能验证的我们都验证了（真实 in-process 服务器、真实协议库、Docker 容器 loopback）——剩下的 待核实 清单只有真设备能回答：物理 Modbus-RTU（RS-485）、EtherCAT 从站、HART 网关、在线 BACnet 楼宇设备、在线 Metasys/Niagara BAS 控制器、在线 Ignition 网关、国产 PLC（汇川/信捷）、真机 PLCnext、真实变电站 RTU/IED、欧姆龙 FINS 真机、IO-Link 主站。如果你是 OT 工程师、系统集成商或工厂团队，手上有任何这类设备：装上 iaiops，对你的设备跑一遍 iaiops doctor，把结果告诉我们。经你验证的设备会署名写进支持矩阵；现场反馈的问题我们优先分诊；功能可以通过 GitHub Issues/Discussions 直接共创。
We're looking for field-testing partners. Everything software-verifiable has been verified; what's left on the honest 待核实 list only real equipment can answer — physical Modbus-RTU (RS-485), EtherCAT slaves, HART gateways, live BACnet HVAC, live Metasys/Niagara BAS controllers, live Ignition gateway, domestic PLCs (Inovance/Xinje), live PLCnext, substation RTUs/IEDs, live Omron FINS PLCs, IO-Link masters. If you're an OT engineer, integrator, or factory team with access to any of these: install iaiops, run iaiops doctor against your gear, and tell us what happened. Verified-equipment reports get credited in the support matrix, field-reported issues get fast triage, and features are co-designed in the open via GitHub Issues/Discussions.
👉 参与入口 | Start here: open an issue with the protocol and device model in the title, or email zhouwei008@gmail.com. Either reaches a person, and a report gets answered against the current release.
| Protocol | Tool | Operation | R/W | risk_tier | Returns (key fields) |
|---|---|---|---|---|---|
| OPC-UA | opcua_server_info | server status | R | low | state, product_name, namespaces |
| OPC-UA | opcua_browse | browse node tree | R | low | [{node_id, browse_name, depth}] |
| OPC-UA | opcua_read_node | read one node | R | low | value, datatype, source_timestamp, good |
| OPC-UA | opcua_read_many | batch read | R | low | [{node_id, value, ...}] |
| OPC-UA | opcua_subscribe_sample | bounded sample | R | low | {collected, samples[]} |
| OPC-UA | opcua_read_alarms | alarm surfacing | R | low | {active_alarms[], active_count} |
| OPC-UA | opcua_read_history | Historical Access (HDA) | R | low | {supported, count, values[]} |
| OPC-UA | opcua_diagnose_connection | connection triage | R | low | {verdict, checks[]} |
| OPC-UA | opcua_discover_tags | tag auto-discovery → semantic asset model | R | low | {tag_count, assets[], naming_report} |
| OPC-UA | opcua_health_summary | threshold classify (was health_summary¹) | R | low | {overall, counts, offenders[]} |
| OPC-UA | opcua_anomaly_scan | stddev outliers (was anomaly_scan¹) | R | low | {mean, stddev, outliers[]} |
| Modbus | modbus_read_holding | FC03 | R | low | {raw_registers, decoded[]} |
| Modbus | modbus_read_input | FC04 | R | low | {raw_registers, decoded[]} |
| Modbus | modbus_read_coils | FC01 | R | low | {bits[]} |
| Modbus | modbus_read_discrete | FC02 | R | low | {bits[]} |
| Modbus | modbus_detect_byte_order | byte/word-order auto-detect | R | low | {best_order, candidates[]} |
| Modbus | modbus_list_templates | vendor register templates | R | low | {templates[]} |
| Modbus | modbus_apply_template | decode block via template | R | low | {values:{name: engineering_value}} |
| Modbus | modbus_health_summary | threshold classify | R | low | {overall, counts, offenders[]} |
| S7comm | s7_cpu_info | CPU id + run/stop | R | low | {cpu_status, cpu_info} |
| S7comm | s7_read_area | read DB/M/I/Q | R | low | {items:[{address, value}]} |
| S7comm | s7_read_db | read data block | R | low | {items:[{address, value}]} |
| S7comm | s7_read_many | batch addresses | R | low | {items:[{address, value}]} |
| S7comm | s7_write_db | write data block | W | high/MOC | {before, written, _undo_id} |
| Mitsubishi MC | mc_cpu_status | CPU type | R | low | {cpu_type, cpu_code} |
| Mitsubishi MC | mc_read_words | word devices | R | low | {words[]} |
| Mitsubishi MC | mc_read_bits | bit devices | R | low | {bits[]} |
| Mitsubishi MC | mc_read_many | random read | R | low | {words[], dwords[]} |
| Mitsubishi MC | mc_write_words | write words | W | high/MOC | {before, written, _undo_id} |
| Omron FINS | fins_cpu_info | controller data read (0501) | R | low | {controller_model, controller_version} |
| Omron FINS | fins_cpu_status | controller status (0601) | R | low | {run_mode, status} |
| Omron FINS | fins_read_words | memory-area word read (DM/CIO/W/H/A/EM) | R | low | {words[]} |
| Omron FINS | fins_read_bits | memory-area bit read | R | low | {bits[]} |
| Omron FINS | fins_read_many | batch reads | R | low | {items[]} |
| Omron FINS | fins_write_words | memory-area write | W | high/MOC | {before, written, _undo_id} |
| MTConnect | mtconnect_probe | device model | R | low | {devices:[{components:[{data_items}]}]} |
| MTConnect | mtconnect_current | latest values | R | low | {observations[]} |
| MTConnect | mtconnect_sample | bounded stream | R | low | {observations[]} |
| MTConnect | mtconnect_assets | assets | R | low | {assets[]} |
| MTConnect | mtconnect_oee_snapshot | OEE inputs | R | low | {availability, execution, verdict} |
| MQTT/Sparkplug | mqtt_read_topic | bounded read | R | low | {messages:[{topic, payload}]} |
| MQTT/Sparkplug | sparkplug_subscribe_sample | bounded SpB sample (full decode) | R | low | {samples:[{sparkplug, payload:{metrics[]}}], seq_gap_count} |
| MQTT/Sparkplug | sparkplug_decode_payload | decode raw SpB payload | R | low | {metrics:[{name, alias, datatype, value, is_historical}]} |
| MQTT/Sparkplug | sparkplug_node_list | node discovery + state | R | low | {nodes:[{group_id, edge_node_id, online, devices}], primary_hosts[]} |
| MQTT/Sparkplug | uns_browse | topic-tree browse | R | low | {topics[], tree{}} |
| MQTT/Sparkplug | uns_topic_audit | UNS naming + sprawl governance | R | low | {verdict, sprawl_findings, findings{casing_collisions[], scattered_leaves[], …}} |
| MQTT/Sparkplug | uns_schema_drift | Sparkplug schema-drift (baseline vs current) | R | low | {verdict (none/additive/breaking), node_changes[]} |
| MQTT/Sparkplug | uns_live_audit | live UNS audit (bounded broker sample) | R | low | {verdict, findings{}} |
| MQTT/Sparkplug | sparkplug_live_schema | live NBIRTH schema snapshot | R | low | {nodes[], metrics[]} |
| MQTT/Sparkplug | uns_live_drift | live drift vs stored baseline | R | low | {verdict, node_changes[]} |
| MQTT/Sparkplug | mqtt_publish | publish/command | W | high/MOC | {published_bytes, applied} |
| EtherNet/IP | eip_controller_info | Logix controller id | R | low | {controller:{vendor, product_name, revision, serial}} |
| EtherNet/IP | eip_list_tags | tag discovery | R | low | {tag_count, tags:[{name, data_type, structure}]} |
| EtherNet/IP | eip_read_tag | read one tag/array | R | low | {tag, value, type, good} |
| EtherNet/IP | eip_read_many | batch read | R | low | {items:[{tag, value, type}]} |
| EtherNet/IP | eip_write_tag | write tag | W | high/MOC | {before, written, _undo_id} |
| Diagnostics | diagnose_dataflow | localize no-data | R | low | {verdict, diagnosis, hops[]} |
| Diagnostics | alarm_bad_actors | ISA-18.2 flood | R | low | {flood_verdict, top_offenders[]} |
| Diagnostics | tag_health | offender ranking | R | low | {overall, offenders[]} |
| Diagnostics | historian_health | gap/flatline | R | low | {verdict, gaps[]} |
| Diagnostics | subscription_health | sequenced-feed loss/reorder/overload | R | low | {verdict, missed_count, overloaded_channels[]} |
| Diagnostics | downtime_root_cause | AI downtime RCA copilot (cited, advisory) | R | low | {verdict, primary_cause, hypotheses:[{cause, confidence, evidence[]}]} |
| Diagnostics | downtime_root_cause_live | RCA copilot that gathers its own live evidence | R | low | {…downtime_root_cause…, collected_evidence} |
| Diagnostics | learn_cause_weights | learn per-site RCA cause weights from labeled incidents | R | low | {cause_weights{}, rationale} |
| Diagnostics | data_quality_scorecard | fleet data-trust rollup | R | low | {fleet_score, fleet_status, issue_breakdown, worst_tags[], endpoints[]} |
| Diagnostics | data_quality_fleet_rollup | cross-endpoint fleet view | R | low | {fleet_score, endpoints[]} |
| Diagnostics | heartbeat_health | heartbeat/watchdog liveness | R | low | {alive, distinct_transitions, longest_stall_s, reason} |
| Alarm (ISA-18.2) | alarm_flood_analysis | flood episodes / chattering / stale / summary | R | low | {episodes[], chattering[], stale[], summary{}} |
| Alarm (ISA-18.2) | alarm_rationalization_worksheet | CSV-exportable rationalization rows | R | low | {rows[], csv_path?} |
| Baseline | baseline_learn | conservative change-log baseline (refuses thin history) | R | low | {band{p1,p99,median,mad} | insufficient_data} |
| Baseline | baseline_check | silent-by-default violation check | R | low | {status, violations[] (cited)} |
| Baseline | baseline_record_change | record operator change (restarts learning) | R | low | {recorded, change_point} |
| Baseline | baseline_status | no_baseline / learning / ok / violation | R | low | {status, window} |
| Historian | historian_query | read history back out of sqlite/TDengine/IoTDB | R | low | {rows[], truncated} |
| Historian | historian_coverage | per-tag row counts + first/last ts | R | low | {tags:[{tag, rows, first, last}]} |
| PLC program | plc_program_outline | structure of exported ST/AWL/L5X program | R | low | {blocks[], call_graph, timers[]} |
| PLC program | plc_program_xref | symbol/address cross-reference (cited lines) | R | low | {sites:[{kind, source_file, line, quote}]} |
| PLC program | plc_program_section | one named block's source (≤200 lines) | R | low | {text, source_file} |
| Export | export_data | export local store → CSV/SQLite/Parquet | R | low | {path, row_count, preview[]} |
| Analytics | oee_compute | OEE = A×P×Q | R | low | {availability, performance, quality, oee, oee_pct} |
| Analytics | downtime_events | stoppage detect + categorize | R | low | {event_count, total_downtime_s, by_category, events[]} |
| Analytics | oee_multidim | OEE machine×part×shift | R | low | {matrix[], worst_performers[], mean_oee} |
| Analytics | asset_inventory | active fingerprint | R | low | {assets:[{protocol, vendor, model, firmware, reachable}]} |
| Analytics | cross_protocol_asset_model | merge discovered tags into one asset model | R | low | {assets[], tag_count} |
| Analytics | adopt_alias_map / diff_alias_map | tag alias-map adopt/diff | R | low | {aliases{}, changes[]} |
| Analytics | monitor_changes | bounded change-of-value | R | low | {change_count, changes:[{value, previous, wall_clock}]} |
| EtherCAT | ethercat_master_state | master/WKC + slave count | R | low | {master_state, expected_working_counter, slaves_found, slaves_expected} |
| EtherCAT | ethercat_slaves | bus scan | R | low | {slave_count, slaves:[{index, name, vendor_id, product_code, state}]} |
| EtherCAT | ethercat_slave_info | slave detail | R | low | {sync_managers[], fmmus[], object_dictionary[], input_bytes} |
| EtherCAT | ethercat_read_sdo | CoE SDO upload | R | low | {index, byte_length, hex, as_uint} |
| EtherCAT | ethercat_read_pdo | input PDO snapshot | R | low | {working_counter, input_hex, input_byte_length} |
| EtherCAT | ethercat_write_sdo | CoE SDO download | W | high/MOC | {before, written, applied} |
| EtherCAT | ethercat_set_state | AL-state transition | W | high/MOC | {before, requested, reached, applied} |
| PROFINET | profinet_discover | DCP IdentifyAll (segment-wide) | R | low | {station_count, stations:[{name_of_station, mac, ip, vendor_id, device_roles[]}]} |
| PROFINET | profinet_identify_station | identify by name-of-station | R | low | {found, name_of_station, mac, ip, device_family} |
| PROFINET | profinet_station_params | targeted DCP Get (by MAC) | R | low | {found, name_of_station, ip, netmask, gateway} |
| PROFINET | profinet_asset_inventory | DCP asset register | R | low | {asset_count, io_controller_count, assets[]} |
| PROFINET | profinet_dcp_set | DCP Set (station name / IP suite) | W | high/MOC | {before, applied, _undo_id} |
| SECS/GEM | secsgem_equipment_status | GEM link + identity (S1F1/F2) | R | low | {communication_state, are_you_there} |
| SECS/GEM | secsgem_list_status_variables | SVID namelist (S1F11/F12) | R | low | {count, status_variables[]} |
| SECS/GEM | secsgem_read_status_variables | SVID values (S1F3/F4) | R | low | {svids, values[]} |
| SECS/GEM | secsgem_list_equipment_constants | ECID namelist (S2F29/F30) | R | low | {count, equipment_constants[]} |
| SECS/GEM | secsgem_read_equipment_constants | ECID values (S2F13/F14) | R | low | {ecids, values[]} |
| SECS/GEM | secsgem_list_alarms | alarm list (S5F5/F6) | R | low | {count, alarms[]} |
| SECS/GEM | secsgem_list_process_programs | PPID directory (S7F19/F20) | R | low | {count, process_programs[]} |
| BACnet (building) | bacnet_discover | Who-Is device discovery | R | low | {device_count, devices:[{device_id, address}]} |
| BACnet (building) | bacnet_object_list | a device's objects | R | low | {object_count, objects:[{object_type, instance}]} |
| BACnet (building) | bacnet_read_property | one object property | R | low | {object_type, instance, property, value} |
| BACnet (building) | bacnet_read_points | all present-values (HVAC snapshot) | R | low | {point_count, points:[{object_type, instance, present_value}]} |
| BACnet (building) | bacnet_cov_subscribe | bounded COV capture (always unsubscribes) | R | low | {notifications[], terminated_reason} |
| BACnet (building) | bacnet_read_trend_log | TrendLog readRange (bounded) | R | low | {records:[{timestamp, value}]} |
| BACnet (building) | bacnet_write_property | present-value write (priority) | W | high/MOC | {before, written, _undo_id} |
| HART-IP (process) | hart_device_identity | cmd 0 identity | R | low | {manufacturer, device_type, revision} |
| HART-IP (process) | hart_primary_variable | cmd 1 PV | R | low | {value, unit} |
| HART-IP (process) | hart_dynamic_variables | cmd 3 PV/SV/TV/QV + loop current | R | low | {variables[], loop_current} |
| HART-IP (process) | hart_burst_sample | bounded burst-variable sampling | R | low | {samples[]} |
| IO-Link | iolink_master_info | master identity | R | low | {vendor, product, serial} |
| IO-Link | iolink_ports | ≤32-port sweep (mode/status/device id) | R | low | {ports[]} |
| IO-Link | iolink_device_info | per-port device identity | R | low | {vendor_id, device_id, product_name} |
| IO-Link | iolink_read_pdin | process-data-in (raw hex + bytes) | R | low | {hex, bytes[]} |
| IO-Link | iolink_read_isdu | ISDU acyclic parameter read | R | low | {index, subindex, value} |
| IO-Link | iolink_scan | master + all connected devices | R | low | {master{}, devices[]} |
| BAS (Metasys/Niagara) | bas_point_list | supervisory point directory | R | low | {point_count, points:[{id, name, type}]} |
| BAS (Metasys/Niagara) | bas_point_read | read one supervisory point | R | low | {point, value, unit, status} |
| BAS (Metasys/Niagara) | bas_alarm_list | active controller alarms | R | low | {alarm_count, alarms:[{id, priority, state}]} |
| BAS (Metasys/Niagara) | bas_trend_read | trend/history samples (bounded) | R | low | {records:[{timestamp, value}]} |
| BAS (Metasys/Niagara) | bas_command | supervisory command (default-OFF; life-safety object denylist refuses fire/smoke/egress/pressurization before any I/O) | W | high/MOC | {before, written, _undo_id} |
| Ignition | ignition_gateway_status | Gateway + module health | R | low | {state, version, modules:[{name, state}]} |
| Ignition | ignition_tag_browse | tag-tree browse | R | low | {tags[], tree{}} |
| Ignition | ignition_tag_read | current tag values | R | low | {values:[{path, value, quality, timestamp}]} |
| Ignition | ignition_alarm_status | active alarms | R | low | {alarm_count, alarms:[{path, priority, state}]} |
| Ignition | ignition_tag_history | tag-history query (bounded) | R | low | {rows:[{path, timestamp, value}]} |
| 信创 / compliance | compliance_mapping | 《工控网络安全防护指南》↔ iaiops | R | low | {pillars[], status_summary, controls:[{pillar, status, gap}]} |
| 信创 / compliance | compliance_frameworks | 等保 2.0 + IEC 62443 FR1–6 crosswalk | R | low | {controls:[{crosswalk}]} |
| 信创 / compliance | compliance_dengbao_levels | 等保 二级 baseline vs 三级 增量 | R | low | {pillars:[{l2, l3_delta, status}]} |
| 信创 / compliance | compliance_report | deliverable compliance report (md/html) | R | low | {markdown | out_path} |
| 信创 / compliance | compliance_evidence_bundle | audit-evidence zip (hash-chain verified) | R | low | {bundle_path, manifest} |
| 信创 / historian | historian_push | push telemetry to sqlite/TDengine/IoTDB | R(→historian) | low | {sink, received, written, skipped_non_numeric} |
| Self | protocols_supported | capability map | R | low | {protocols[], diagnostics[], analytics[]} |
(The energy protocols — IEC-104 / DNP3 / IEC-61850 — moved to iaiops-energy in 0.8.0; their tool matrix lives in that repo.)
196 governed tools = 183 read + 10 MOC-gated device writes + historian_push (a write, to a historian rather than to a device: [WRITE][risk=low]) + the 2 deprecated aliases below. The device writes are (s7_write_db, mc_write_words, fins_write_words, mqtt_publish, eip_write_tag, ethercat_write_sdo, ethercat_set_state, profinet_dcp_set, bacnet_write_property, bas_command). The read side now includes two vendor-REST read-only layers above the field protocols — a BAS controller layer (Metasys/Niagara, building edition) and an Ignition Gateway MES/SCADA layer (factory edition). ¹ The 2 deprecated aliases are the two deprecated brain aliases health_summary / anomaly_scan, renamed to opcua_health_summary / opcua_anomaly_scan in 0.10.0 — the deprecated aliases are still registered and will be removed in a future release (target: 1.0.0). Read-only per-edition tools load ONLY under their edition (see per-edition tool modules below), so a bare protocol / single-edition surface is smaller than this line-wide total. The table above is representative, not exhaustive; run protocols_supported() (or iaiops protocols) for the live map.
opc.tcp:// via asyncua (sync facade). Security: anonymous + username/password, plus application-certificate message security (Sign / SignAndEncrypt) — set client_cert + client_key (+ optional server_cert) and the client opens a signed/encrypted secure channel (no cert ⇒ the anonymous / username path is unchanged). Validated end-to-end against an in-process asyncua server (tests/test_opcua_security.py) for Basic256Sha256 in both Sign and SignAndEncrypt modes: server_cert pinning and client-side server-cert auto-discovery are exercised, and the test asserts the negotiated policy URI + message-security mode on the live encrypted channel (plus a negative test that anonymous is refused by a secure-only server).endpoint_url, username (password encrypted), security_mode, security_policy; for cert security client_cert / client_key / optional server_cert (PEM or DER paths; aliases certfile / keyfile).opcua_alarm_events — bounded event subscription + ConditionRefresh, events carry the server's own timestamps (verified against an in-process asyncua server; third-party A&C servers 待核实). Untimed fallback: opcua_read_alarms browses alarm-like boolean nodes.待核实): cert-security interop with third-party / vendor servers (KEPServerEX / Prosys / Siemens / real PLCs), the other policies (Aes128Sha256RsaOaep / Aes256Sha256RsaPss / Basic128Rsa15 / Basic256), strict server-side certificate-trust enforcement, and cert-based user identity (X509 identity token, distinct from channel security).pymodbus (+ pyserial). Read function codes FC01 (coils), FC02 (discrete), FC03 (holding), FC04 (input). Write FCs (FC05/06/15/16) = not implemented (read-only).host, port (502), unit_id. RTU — transport: rtu, serial_port (e.g. /dev/ttyUSB0), baudrate, unit_id. Registers are untyped 16-bit words → decode hint (uint16/int16/uint32/int32/float32/raw); modbus_detect_byte_order auto-detects the byte/word order (AB/BA · ABCD/DCBA/BADC/CDAB) from hint values — pure logic, no extra device load.modbus_list_templates / modbus_apply_template): named register maps decoding a block into engineering values — energy meters (Eastron SDM630, Schneider PM5xxx, Carlo Gavazzi EM24), PV inverters (Huawei SUN2000, Growatt), Phoenix PLCnext process data, and water-industry templates (E+H Promag, Hach SC controller, generic dosing pump). Each template carries an explicit 待核实 caveat — no invented "verified" addresses.待核实.pyS7 (pure-Python, ISO-on-TCP / RFC1006 — no native libsnap7). S7-300/400/1200/1500 and compatible clones. Memory areas DB / M (merker) / I / Q. No protocol auth (CPU gates via "Permit access with PUT/GET").host, port (102), rack, slot (0/1 for 1200/1500; 0/2 common for 300/400).s7_write_db = high risk_tier, MOC, dry-run default, captures BEFORE value + undo.pymcprotocol — MC 3E frame (binary) only. 1E / 4E frames = not supported. PLC types Q / L / QnA / iQ-R / iQ-L. Devices: D/W/R (word), M/X/Y/B (bit).host, port (5007 default; set to the module's open MC port), plctype.mc_write_words = high/MOC/dry-run default, captures BEFORE + undo.iaiops[fins] extra pins nothing): 10-byte FINS header framing, FINS/UDP (default port 9600) and FINS/TCP (node-address handshake per Omron W342), SID matching, bounded response parsing, end-code table per W227/W342. Commands: 0101 memory-area read (words/bits over DM/CIO/W/H/A/EM), 0102 write, 0501 controller data read, 0601 controller status.host, port (9600), transport (udp default / tcp), FINS network/node/unit addressing.fins_write_words = high/MOC/dry-run default, captures BEFORE + undo; CLI double-confirm on --apply.tests/test_fins.py); live Omron PLC behaviour and banked-EM access stay 待核实.flavor: — iotcore (ifm IoT-Core POST envelope, default) and rest (plain-REST GET, Balluff/Turck-style). Reads: master identity, bounded ≤32-port sweep, per-port device identity, process-data-in (raw hex + bytes), ISDU acyclic parameter read. NO write tools. Bounded/size-capped HTTP (256 KiB response cap), schema-checked JSON with teaching errors. Reuses the MTConnect HTTP pin (iaiops[iolink] → requests).host/URL, flavor, timeout_s. protocol: iolink.tests/test_iolink.py); live master datapoint paths stay 待核实.transport: tcp, length-delimited framing) via an in-tree transport; the HART command codec is verified vs hart-protocol. Tools: hart_device_identity (cmd 0), hart_primary_variable (cmd 1), hart_dynamic_variables (cmd 3, PV/SV/TV/QV + loop current), hart_burst_sample (bounded sampling of burst-published variables). No write / device-specific commands exposed (OT-dangerous on live instruments).host (HART-IP server/gateway), port (5094), transport (udp default / tcp).待核实.requests + xml.etree), namespace-agnostic (parses MTConnect 1.x Devices/Streams/Assets schemas). Endpoints: /probe, /current, /sample, /assets. Read-only by specification. XML parsing is hardened (DTD/entity declarations rejected — XXE/billion-laughs defense).agent_url (e.g. http://host:5000).interval=); only bounded count= samples.paho-mqtt — MQTT 3.1.1 & 5. Sparkplug B topic convention spBv1.0/{group}/{type}/{edge}/[device] (NBIRTH/DBIRTH/NDATA/DDATA/NDEATH/DDEATH/STATE). TLS + username/password supported.sparkplug_b.proto generated module (depends only on protobuf). Per metric you get name, alias (resolved to its name via the BIRTH model), datatype (Int8…Int64/UInt…/Float/Double/Boolean/String/DateTime/Text/UUID/DataSet/Bytes/File/Template/PropertySet…), value, timestamp, and the is_historical / is_null flags. A birth/death + seq model tracks node/device online state (NBIRTH/DBIRTH ↔ NDEATH/DDEATH), builds the alias→name map from BIRTH, applies NDATA/DDATA by alias, and flags seq gaps / out-of-order. Primary-host awareness: STATE/<host_id> topics surface in sparkplug_node_list. sparkplug_decode_payload decodes a single raw payload (base64/hex) offline.iaiops collect run holds ONE subscription open for the run and samples from its last-value cache, so a plant whose data is already unified into a UNS can be tapped without touching a PLC. Refusals are the feature. MQTT is pushed, and the obvious cache answers with the last value forever after a publisher dies — availability then reads 100% on a stopped line, in every subscriber at once. So a point is a reading only when it has been seen at all (never-published is not zero), is fresher than stale_after_s, and — for Sparkplug — its node has not sent NDEATH/DDEATH. Anything else raises OTNoReadingError, which the collector records as a gap (collection was blind), never as downtime.stale_after_s is REQUIRED to collect, and deliberately has no default: a value that stopped updating and one that is simply constant are identical on the wire, so only the site knows how often a point is published. Guessing it here would put a guess underneath every availability figure. Same discipline as running_when on a run_state tag.group/edge[/device]:metric — exactly the node id mqtt live-schema reports, so its output is usable as config refs without translation. Payloads decode as a bare scalar or a {"value": …} / {"v": …} JSON envelope; an unknown envelope is not guessed at by picking its only number.host/broker, port (1883 / 8883 TLS), topic, use_tls, username (password encrypted), stale_after_s (required for collection).tests/test_uns_tap_live.py, opt-in) — publish → read → publisher stops → the run records a gap instead of repeating the cache. Also exercised across a real network on three separate hosts (broker, edge node, reader) against a spec-correct Sparkplug node — alias-only NDATA, periodic re-BIRTH, and a genuine broker-issued Last Will after the publisher was kill -9'd on another machine (refusal in ~2s with stale_after_s deliberately set to 60, so only the death signal could have caused it). 待核实: the edge node is still our own implementation, not a commercial EoN (Ignition / Litmus / HighByte), and not a commercial broker (HiveMQ / EMQX).mqtt_publish = high/MOC/dry-run default. A transient publish has no automatic inverse (delivered is delivered); a retained one overwrites durable broker state, so it captures the prior retained payload and records an inverse.pycomm3 (pure-Python — no native deps). Tag-based, symbolic access: read/write tags by name (Conveyor.Speed, Array[3], Program:Main.X) and discover the controller's tag list at runtime (eip_list_tags, the headline feature). eip_controller_info reads the controller identity.host, slot (0 for CompactLogix; the CPU slot for a ControlLogix chassis), port (44818). protocol: ethernetip (alias eip).eip_write_tag = high risk_tier, MOC, dry-run default, captures BEFORE value + undo.Supported: a real EtherCAT master via pysoem (the Python binding for the SOEM C stack). CoE SDO read (ethercat_read_sdo, acyclic mailbox upload) + SDO write (ethercat_write_sdo, download), input PDO read (ethercat_read_pdo, one bounded cyclic snapshot), bus scan / slave enumeration (ethercat_slaves, ethercat_slave_info — identity, SM/FMMU mapping, object-dictionary summary), master/working-counter state (ethercat_master_state), and AL-state transitions INIT↔PREOP↔SAFEOP↔OP (ethercat_set_state).
HARD REQUIREMENTS (no way around them): Linux, root or CAP_NET_RAW, a dedicated NIC cabled to the bus, and real EtherCAT slave hardware. pysoem is an OPTIONAL extra: pip install iaiops[ethercat] — the base package installs and imports without it, and every EtherCAT tool then degrades to a teaching error (never crashes, never imports pysoem at module load).
NOT supported: no software simulator exists (unlike OPC-UA / Modbus) — EtherCAT is hardware-only and not testable in mock-only CI; macOS is unsupported. EoE / FoE / SoE mailbox protocols and full PDO-mapping decode/expansion = roadmap.
Connection params: nic (the dedicated interface name, e.g. eth1; alias interface), optional expected_slaves (a sanity check vs the bus scan). protocol: ethercat.
Operations matrix:
| Tool | Op | R/W | risk | Capture/notes |
|---|---|---|---|---|
ethercat_master_state | master + WKC state, slave count | R | low | expected vs found |
ethercat_slaves | bus scan / enumerate | R | low | index/vendor/product/rev/addr/AL-state |
ethercat_slave_info | one-slave detail | R | low | SM/FMMU + OD summary |
ethercat_read_sdo | CoE SDO upload | R | low | hex + uint interpretation |
ethercat_read_pdo | input PDO snapshot | R | low | single cycle, never loops |
ethercat_write_sdo | CoE SDO download | W | high/MOC | before-value (SDO read-back) + undo |
ethercat_set_state | AL-state transition | W | high/MOC | before-state + undo; can start/stop motion |
Write/state safety: ethercat_write_sdo (hex little-endian bytes) and ethercat_set_state are high risk_tier, MOC, dry-run by default, capture the BEFORE value/state for undo, and need a CLI double-confirm. Changing EtherCAT state can START or STOP machine motion — treat with extreme care. 未经授权勿对生产控制系统写入.
pnio-dcp — profinet_discover (DCP IdentifyAll: one broadcast surfaces every station on the segment — name-of-station, MAC, IP, vendor/device id, role — closer to passive discovery than a per-device fingerprint), profinet_identify_station (by name-of-station), profinet_station_params (targeted DCP Get by MAC → name + IP suite), and profinet_asset_inventory (a register with IO-controller vs IO-device role decoding).profinet_dcp_set re-addresses one station (name-of-station and/or IP suite, by MAC) — high risk_tier, MOC, dry-run default, captures the BEFORE addressing + undo descriptor. Re-addressing a live station can disrupt its IO connection.CAP_NET_RAW) on the NIC on the PROFINET subnet. pnio-dcp is an OPTIONAL extra: pip install iaiops[profinet] — the base package installs/imports without it, and every tool then degrades to a teaching error.host — THIS machine's IP on the PROFINET subnet (the DCP broadcast goes out on it). protocol: profinet.pnio-dcp DCP — not verified against live PROFINET devices yet.iaiops-energyThe energy vertical — IEC 60870-5-104 / DNP3 / IEC 61850 MMS read-only monitoring for substation RTUs/IEDs — moved to its own package in 0.8.0: iaiops-energy (pip install iaiops-energy), built on iaiops.core (shared governance / brain / runtime). Its protocol reference, support matrix, and validation status live in that repo.
The building vertical adds BACnet/IP (ASHRAE 135) — the dominant building-automation protocol for HVAC, lighting, metering, and facility plant. Install with pip install iaiops[building] and expose with IAIOPS_MCP=building (bundle: bacnet + modbus + opcua + iolink).
BAC0 over bacpypes3): bacnet_discover (Who-Is device discovery), bacnet_object_list (a device's objects), bacnet_read_property (one object property), bacnet_read_points (present-value of all analog/binary/multistate points — the HVAC snapshot), bacnet_cov_subscribe (bounded change-of-value capture — capped by count AND wall-clock, always unsubscribes), bacnet_read_trend_log (TrendLog buffered records via one bounded readRange). Config: host = THIS machine's BACnet/IP interface (ip or ip/mask) / port (47808).bacnet_write_property (present-value at a BACnet priority 1..16, or relinquish) = high risk_tier, MOC, dry-run default, BEFORE-value read-back + undo. Overriding a live building-control point can move real HVAC/plant.tests/test_bacnet_live.py); COV / trend-log / writes on live HVAC gear stay 待核实.IAIOPS_MCP=water (or iaiops-mcp-water, pip install iaiops[water]) exposes modbus + opcua + hart + the brain — the protocol set waterworks / wastewater plants actually run. Adds water-domain tag semantics (溶解氧 DO / ORP / 余氯 chlorine / 氨氮 ammonia / TSS/MLSS / 跨膜压差 TMP / UV / 加药 dosing / 曝气 aeration) and water-industry Modbus templates (E+H Promag, Hach SC controller, generic dosing pump — all with explicit 待核实 caveats).
IAIOPS_MCP=warehouse (or iaiops-mcp-warehouse, pip install iaiops[warehouse]) exposes eip + profinet + modbus + opcua + sparkplug + the brain — conveyor & sorter drives over EtherNet/IP (Rockwell) and Profinet (Siemens), VFD / energy meters over Modbus (conveyor_vfd / agv_battery templates), WMS/WCS gateways over OPC-UA, and AMR/IoT telemetry over MQTT-Sparkplug. Edition tools (read-only, advisory): line_bottleneck (Theory-of-Constraints throughput bottleneck across stations) + sortation_health. PdM (pdm_forecast), downtime_triage and OEE are reused as-is.
IAIOPS_MCP=clinical (or iaiops-mcp-clinical, pip install iaiops[clinical]) exposes bacnet + modbus + opcua + the brain — hospital facilities as a distinct patient-safety vertical over the building brain. Edition tools (read-only, advisory): isolation_room_check (负压/正压 isolation-room pressurization), medical_gas_check (medical-gas alarm-panel safety), or_environment_check (OR temperature / humidity / pressure envelope). BACnet BMS + Modbus gas-alarm panels + OPC-UA plant SCADA.
IAIOPS_MCP=pharma (or iaiops-mcp-pharma, pip install iaiops[pharma]) exposes bacnet + modbus + hart + opcua + the brain. No new protocol — that is the point: no field protocol is specific to pharma. Cleanrooms run BACnet, purified-water systems run Modbus and HART, filling and lyophilization run S7, DCS and bioreactors run OPC-UA, and all of it was already here. What pharma needed was semantics: the water edition's indicators are municipal (DO, ORP, chlorine, turbidity) and the clinical edition grades one room's pressure, where Annex 1 inspects the cascade.
Edition tools (read-only, advisory): cleanroom_pressure_cascade (EU GMP Annex 1, door by door — adjacency is declared, never inferred from a room list), cleanroom_particle_check, pharma_water_check (USP <645> stage-1 procedure: the non-temperature-compensated reading, the measured temperature rounded down to the tabulated step, and exceeding stage 1 reported as proceed to Stage 2 rather than as a failure).
No compendial limit tables are shipped. The particle limits, the stage-1 conductivity table and the TOC limit belong to the site's qualified specification at its compendial revision. A transcription nobody in this repository can verify would end up deciding whether a batch environment passed — and the error that hurts is the flattering one, since a limit set too loose reads as "in specification". Limits are passed in and cited back; anything not declared is reported no_limit / not_graded and named, never counted as passing. Known gaps are listed in the edition's skill: no PI historian connector, S7 without hardware verification, no GxP (Annex 11 / Part 11) crosswalk yet, and LIMS / QMS deliberately out of scope — they run REST and databases, not f
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
uvx iaiopsMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-industrial-aiops-iaiops": {
"command": "uvx",
"args": [
"iaiops"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referenceiaiopspypiIndustrial-AIOps works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.