Categories › AI & Agents › Multi-agent, orchestration & workflows
Build, run and publish Workbench flows, tasks, shims and knowledge bases.
Remote server: your requests and data go to api.zerowidth.ai. Claude Code: claude mcp add --transport http zerowidth-workbench https://api.zerowidth.ai/mcp/x/workbench · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_docs — Search ZeroWidth product documentation. Returns matching pages with title, slug, public URL, and a query-relevant snippet. Use this when theget_doc — Fetch the full Markdown body of a specific docs page by its slug. Use this after `search_docs` when the user needs the complete content of alist_docs — Enumerate all available docs pages, optionally filtered by product (e.g. 'compass', 'legal', 'overview'). Use this to discover what slugs exworkbench_flows_revisions_list — The flow's revision history, newest first: published versions carry a `version` label and note; entries with version null are draft autosaveworkbench_flows_update — Changes a flow's name, description, visibility, tags, or archived state — the metadata around the flow, NOT its orchestration (prompts and nworkbench_flows_publish — Snapshots the flow's current DRAFT as a named published version — the version schedules (workbench_flows_schedule), guest share links (workbworkbench_flows_delete — Deletes a flow. Its schedules stop, guest share links die, and evals targeting it can no longer run (their binding shows flowOk: false) — chworkbench_flows_fork — Copies a PUBLIC flow from another workspace (a template) into this one as a new draft the user owns. Identify it by its flowUuid (the id on workbench_flows_schedules_list — Every schedule on one flow: cadence, whether it's paused (`enabled: false`), the next fire time, delivery, and the last run's status. Read tworkbench_flows_schedules_update — Changes one schedule: `enabled: false` pauses it (configuration kept), `enabled: true` resumes and recomputes the next fire time from now; `workbench_flows_schedules_delete — Removes a schedule for good. Prefer workbench_flows_schedules_update with enabled: false when the user might want it back. May return `needsworkbench_flows_schedules_run_now — Runs one iteration of a schedule immediately through the real scheduled pipeline (same input, same delivery — the email or channel it normalworkbench_flows_shares_list — Every guest link on one flow, newest first: label, whether it's still live, the shareUrl (live links only — dead ones have no URL), expiry, workbench_flows_shares_revoke — Kills one guest link immediately — anyone holding it gets a closed page from then on. Conversations already had stay in the flow's history. workbench_flows_scenarios_list — A flow's variables (each {{token}} in an agent's prompt, with its type) and every saved scenario with its values. Read this before creating workbench_flows_scenarios_create — Saves a named scenario: values for the flow's variables, e.g. one demo customer. It shows in the test pane's Scenarios menu, and Caliper evaworkbench_flows_scenarios_update — Renames a scenario or changes its values. `values` MERGES into what's saved: pass only the variables that change, and null to clear one. Getworkbench_flows_scenarios_delete — Deletes one scenario. A design session running as it goes back to no scenario. May return `needs_confirmation`.workbench_flows_attach_knowledge_base — Attaches a knowledge base to an AGENT flow's draft, the same way picking it in the agent editor does: a docs knowledge base becomes a searchworkbench_flows_run — Execute a flow and return its outputs synchronously. Runs the draft by default; pass source:"published" (optionally a version) to run the liworkbench_flows_schedule — Set a specific built flow to run automatically on a cadence — the deterministic counterpart to a routine. Each run executes the flow's latesworkbench_flows_list — Lists every flow in the active workspace the caller can see. Returns summaries (id, name, visibility, updatedAt) — fetch one with `workbenchworkbench_executions_get — The flow's stack traces: recent executions with per-node timelines — what each node received, produced, how long it took, and the exact erroworkbench_flows_get — One flow. Default `view: summary` lists its nodes and links so you can pick one; `view: node` with a nodeId returns that node's full settingworkbench_flow_authoring_guide — READ THIS FIRST before writing or editing any raw flow orchestration JSON. Covers the document shape, the settings-vs-input-ports rule (tempworkbench_node_catalog_get — The ground truth for what nodes exist and what their ports actually are — verify against this instead of recalling. Search by keyword/categoworkbench_flows_scaffold — Creates a runnable first-draft flow from a spec you author: pick the simplest pattern that fits (classifier for read-and-bucket, structurer workbench_flows_edit_text — Applies ONE precise text replacement to a flow's DRAFT orchestration — Edit-tool semantics: `find` must be the EXACT current text, copied chworkbench_flows_share_create — Creates a no-account guest link where anyone can chat with the flow's latest PUBLISHED revision at workbench's /s/<token> page — the fastestworkbench_kb_get — One knowledge base: name, recipe (docs / tabular / graph), status, document and chunk counts, embedding model, and ingestion settings. Read workbench_kb_documents_list — Every document ingested into the KB's current content: id, name, type, size, chunk count. Empty for a KB with nothing ingested yet (or one wworkbench_kb_ingestion_status — The state of one ingestion run started by workbench_kb_add_documents: PENDING / RUNNING / DONE / FAILED, chunks written, and the error when workbench_kb_delete — Deletes a knowledge base and everything in it. Flows that search it will find nothing — check which agents use it (the user knows; the KB paworkbench_kb_document_delete — Removes one ingested document and all its chunks; searches stop returning it at once. Get the documentId from workbench_kb_documents_list. Tworkbench_kb_list — Lists every knowledge base in the active workspace the caller can see. Returns summaries (id, name, description, status, doc/chunk counts, eworkbench_kb_search — Retrieves the most relevant chunks from one knowledge base — the core RAG primitive. `mode:"semantic"` (default) embeds the query and ranks workbench_kb_create — Creates an empty knowledge base. Recipe 'docs' (default) for reference material an agent searches at runtime; 'tabular' for spreadsheet-stylworkbench_kb_add_documents — Adds documents to a knowledge base and starts ingestion (chunk + embed; graph KBs also extract entities; tabular KBs load CSV as tables). Teworkbench_shim_list — Every shim the user can see: id, name, the question it answers, how many answers and examples it has, and the published version's held-out aworkbench_shim_get — One shim in full: the question, where its inputs come from, every answer with its description and examples, what the shim still needs beforeNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.