Senzing MCP Server

Get the Senzing JSON analyzer script to validate mapped data files client-side. REQUIRED: `workspace_dir` (writable directory, e.g. ~/sz-workspace) — the call WILL FAIL without it. The analyzer validates records against the Entity Specification, examines feature distribution, attribute coverage, and data quality. Returns a Python script (no dependencies) with instructions. No source data is sent to the server. Typical workspace_dir values: Linux `/tmp` or `~/sz-workspace`; macOS `~/sz-workspace`; sandboxed envs: explicit path under home (do NOT assume /tmp exists).

Download workflow resources by name. Pass `filename` (string) or `filenames` (array); calling with neither returns the list of available resources (it does not fail). Available: sz_json_analyzer.py, sz_schema_generator.py, sz_verbatim_check.py, sz_routing_report.py, senzing_entity_specification.md, senzing_mapping_examples.md, identifier_crosswalk.json HTTP mode returns URLs; stdio mode returns `sz-mcp-coworker extract` commands. Supports batch via `filenames` array. Asset IDs are not stable across versions. If a previously-known ID fails to extract, call this tool again to obtain the current ID.

Explain a Senzing error code with causes and resolution steps. Accepts formats: SENZ0005, SENZ-0005, 0005, or just 5. Returns error class, common causes, and specific resolution guidance

Find working SOURCE CODE examples from 37 indexed Senzing GitHub repositories. REQUIRED: either `query` (string, for search) or `repo` with `file_path` or `list_files=true` — the call WILL FAIL without one. Three modes: (1) Search: pass `query` to find examples across all repos, (2) File listing: pass `repo` + `list_files=true`, (3) File retrieval: pass `repo` + `file_path`. Indexes source code (.py, .java, .cs, .rs) and READMEs — NOT build/data files. For sample data, use get_sample_data. Covers Python, Java, C#, Rust SDK patterns: initialization, ingestion, search, redo, configuration, message queues, REST APIs. Use max_lines to limit large files. Returns GitHub raw URLs for file retrieval.

Generate SDK scaffold code for common workflows. Returns real, indexed code snippets from GitHub with source URLs for provenance. Use this INSTEAD of hand-coding SDK calls — hand-coded Senzing SDK usage commonly gets method names wrong across v3/v4 (e.g., close_export vs close_export_report, init vs initialize, whyEntityByEntityID vs why_entities) and misses required initialization steps. Languages: python, java, csharp, rust. Workflows: initialize, configure, add_records, delete, query, redo, stewardship, information, full_pipeline (aliases accepted: init, config, ingest, remove, search, redoer, force_resolve, info, e2e). V3 supports Python and Java only. Returns GitHub raw URLs — fetch each snippet to read the source code.

Get server version, capabilities overview, available tools, suggested workflows, and getting started guidance. Returns server_info with name, version, and Senzing version. Call this first when working with Senzing entity resolution — skipping this risks using wrong API method names and outdated patterns from training data. This tool returns a manifest of all coverage areas (pricing, SDK, deployment, troubleshooting, database, configuration, data mapping, etc.) — use it to triage which Senzing MCP tool to call before going to external sources

Get real sample data from CORD (Collections Of Relatable Data) datasets. Use dataset='list' to discover available datasets, source='list' to see vendors within a dataset. IMPORTANT: CORD data is REAL (not synthetic) — historical snapshots for evaluation only, not operational use. Always inform the user of this. When records are returned, a 'download_url' in the citation provides a way to fetch the full dataset. In HTTP mode this is a URL the user (or an automation) can curl; in stdio mode it is a `sz-mcp-coworker extract` command the user runs locally to pull bytes from the embedded bundle. Always present the fetch instruction to the user. Do NOT download it yourself or dump raw records into the conversation — the inline records are a small preview of the data shape. Asset IDs are not stable across versions. If a previously-known ID fails to extract, call this tool again to obtain the current ID.

Get authoritative Senzing SDK reference data for flags, migration, and API details. Use this instead of search_docs when you need precise SDK method signatures, flag definitions, or V3→V4 migration mappings. Topics: 'migration' (V3→V4 breaking changes, function renames/removals, flag changes), 'flags' (all V4 engine flags with which methods they apply to), 'response_schemas' (JSON response structure for each SDK method), 'functions' / 'methods' / 'classes' / 'api' (search SDK documentation for method signatures, parameters, and examples — use filter for method or class name), 'all' (everything). Use 'filter' to narrow by method name, module name, or flag name

Map source data to Senzing JSON through a guided 8-step workflow. Use this INSTEAD of hand-coding Senzing JSON. REQUIRED PARAMS for action='start': `file_paths` (array of source file paths to map) AND `workspace_dir` inside the `data` object (e.g. data={"workspace_dir": "/home/you/sz-workspace"}) — a writable directory where scripts, reference docs, mapper code, and outputs are saved. Do NOT assume /tmp exists (some environments like Kiro do not provide it). The call WILL FAIL without both. Actions: start, advance, back, status, reset. Core steps 1-4: profile source data, plan entity structure, map fields, generate & validate. Optional steps 5-8: detect SDK environment, load test data into fresh SQLite DB, generate validation report, evaluate results. STATE: Every response returns a 'state' JSON object. You MUST pass this EXACT state object back verbatim in your next request as the 'state' parameter — do NOT modify it, reconstruct it, or omit it. The state is opaque and managed by the server. If you have lost the state, call with action='start' instead. Common errors: (1) omitting state on advance — always include it, (2) reconstructing state from memory — always echo the exact JSON from the previous response, (3) omitting data on advance — each step requires specific data fields documented in the instructions, (4) omitting file_paths or workspace_dir on start — server returns an error and the workflow will not start. Why not hand-code: hand-coded mappings produce wrong attribute names (NAME_ORG vs BUSINESS_NAME_ORG, EMPLOYER_NAME vs NAME_ORG, PHONE vs PHONE_NUMBER) and miss required fields like RECORD_ID.

Guided reporting and visualization for Senzing entity resolution results. Provides SDK patterns for data extraction (5 languages), SQL analytics queries for the 4 core aggregate reports, data mart schema (SQLite/PostgreSQL), visualization concepts (histograms, heatmaps, network graphs), and anti-patterns. Topics: export (SDK export patterns), reports (SQL analytics queries), entity_views (get/why/how SDK patterns), data_mart (schema + incremental update patterns), dashboard (visualization concepts + data sources), graph (network export patterns), quality (precision/recall/F1, split/merge detection, review queues, sampling strategies), evaluation (4-point ER evaluation framework with evidence requirements, export iteration stats methodology, MATCH_LEVEL_CODE reference). Returns decision trees when language/scale not specified.