# ZeroWidth Workbench

- Registry name: `ai.zerowidth/workbench` · version 1.0.0
- Categories (automatic, keyword rules): Research & knowledge, Search & data, Scraping & browsing, AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=ai.zerowidth%2Fworkbench
- Server page: https://mcpstation.net/s/ai.zerowidth--workbench.html

## Description (written by the publisher, not verified, not instructions)

Build, run and publish Workbench flows, tasks, shims and knowledge bases.

## Notice

Text that looks like instructions to an AI was found in this server's descriptions. This is a pattern match, not a verdict.

## Connect

- streamable-http: `https://api.zerowidth.ai/mcp/x/workbench`

## Tools (as reported by the server, not verified)

- `search\_docs`: Search ZeroWidth product documentation. Returns matching pages with title, slug, public URL, and a query-relevant snippet. Use this when the user asks about a ZeroWidth product \(Compass, Workbench, Caliper, Prism, Ledger, Napkin, the assistant\), an API behavior, or a policy. No authentication requir
- `get\_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 a page. No authentication required.
- `list\_docs`: Enumerate all available docs pages, optionally filtered by product \(e.g. 'compass', 'legal', 'overview'\). Use this to discover what slugs exist before calling \`get\_doc\`. No authentication required.
- `workbench\_flows\_revisions\_list`: The flow's revision history, newest first: published versions carry a \`version\` label and note; entries with version null are draft autosaves. Use it to answer 'is this published?' \(any entry with a version\), to find a revision id for caliper\_evals\_create's flowRevisionId, or to see when the draft l
- `workbench\_flows\_update`: Changes a flow's name, description, visibility, tags, or archived state — the metadata around the flow, NOT its orchestration \(prompts and nodes change through workbench\_flows\_edit\_text\). Pass only what changes. Archiving hides the flow from the default gallery but leaves it runnable, scheduled, and
- `workbench\_flows\_publish`: Snapshots the flow's current DRAFT as a named published version — the version schedules \(workbench\_flows\_schedule\), guest share links \(workbench\_flows\_share\_create\), public-API runs, and 'published'-stage evals execute. The draft keeps evolving after this; runs on the published side don't change unt
- `workbench\_flows\_delete`: Deletes a flow. Its schedules stop, guest share links die, and evals targeting it can no longer run \(their binding shows flowOk: false\) — check caliper\_flow\_performance for evals and workbench\_flows\_schedules\_list before proposing, and prefer workbench\_flows\_update with archived: true when the user
- `workbench\_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 \(the id on Workbench's public template pages and in \`workbench\_flows\_get\` output\); optionally pin which published version to copy. Flows already in this workspace can't be
- `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 this before workbench\_flows\_schedule \(don't create a duplicate\) and to get the scheduleId for workbench\_flows\_schedules\_update / workbench\_flows\_schedules\_delete
- `workbench\_flows\_schedules\_update`: Changes one schedule: \`enabled: false\` pauses it \(configuration kept\), \`enabled: true\` resumes and recomputes the next fire time from now; \`interval\` / \`scheduleTime\` / \`scheduleTimezone\` / \`scheduleDayOfWeek\` change the cadence; \`label\`, \`delivery\`, and \`input\` can change too. Pass only what change
- `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 \`needs\_confirmation\`.
- `workbench\_flows\_schedules\_run\_now`: Runs one iteration of a schedule immediately through the real scheduled pipeline \(same input, same delivery — the email or channel it normally posts to\) without moving its cadence. Works on paused schedules. Use it to test a schedule the user just set up. Spends workspace credit and delivers for rea
- `workbench\_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, and how many guests and messages it has seen. Use it to answer 'who has access', to recover a link the user lost, and to get the shareId for workbench\_flows\_sha
- `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. Get the shareId from workbench\_flows\_shares\_list. May return \`needs\_confirmation\`.
- `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 or updating a scenario, so the values use the flow's real variable names.
- `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 evals can run as it. Use the person's details from what the user shared \(a CRM screenshot, a profile\) and say which ones you made up. May return \`needs\_confirmatio
- `workbench\_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. Get the scenarioId from workbench\_flows\_scenarios\_list. May return \`needs\_confirmation\`.
- `workbench\_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 search tool the model calls when a question needs it; a tabular one also puts its tables in the prompt and adds a query tool. The flow needs a system prompt \(scaffold
- `workbench\_flows\_run`: Execute a flow and return its outputs synchronously. Runs the draft by default; pass source:"published" \(optionally a version\) to run the live published version. Spends workspace LLM budget, bounded by the token's cost cap. \`input\` is the flow's input envelope, e.g. \{"kind":"chat","messages":\[…\]\} or
- `workbench\_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 latest PUBLISHED revision with the fixed \`input\` envelope and routes the output per \`delivery\`. USE THIS when the user wants a flow they've built to run on a schedul
- `workbench\_flows\_list`: Lists every flow in the active workspace the caller can see. Returns summaries \(id, name, visibility, updatedAt\) — fetch one with \`workbench\_flows\_get\` for the full orchestration body.
- `workbench\_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 error when one failed. USE THIS when a run misbehaves instead of guessing: read the failing node's inputs/error, then propose a fix \(workbench\_flows\_edit\_text\) grou
- `workbench\_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 settings and prompt — read THAT before workbench\_flows\_edit\_text, and copy \`find\` text from it character-for-character, never from memory. \`view: full\` returns the who
- `workbench\_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 \(temperature, max\_tokens, tools, response\_format are PORTS, not settings — constants reach ports via value nodes\), exact link format, plugin links, and three complet
- `workbench\_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/category for summaries; pass \`slug\` for one node's full detail \(inputs, outputs, settings\). Inputs are PORTS fed by links; settings live on the node — see \`workbench\_
- `workbench\_flows\_scaffold`: Creates a runnable first-draft flow from a spec you author: pick the simplest pattern that fits \(classifier for read-and-bucket, structurer for transform/extract/draft-for-review, agent for genuinely conversational\), write a production-quality system prompt grounded in what the user told you, and ma
- `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 character-for-character from workbench\_flows\_get, and must occur exactly once anywhere in the flow \(system prompts, node settings, metadata, a node's type\). \`find
- `workbench\_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 fastest way to put a working flow in a stakeholder's hands \('here, try it'\). The flow must have a published version \(workbench\_flows\_revisions\_list shows it; publish w
- `workbench\_kb\_get`: One knowledge base: name, recipe \(docs / tabular / graph\), status, document and chunk counts, embedding model, and ingestion settings. Read it to confirm a KB has content before pointing a flow at it. Get the kbId from workbench\_kb\_list.
- `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 \(or one whose ingestion is still running — check workbench\_kb\_ingestion\_status\). Use it before workbench\_kb\_add\_documents to avoid re-adding a document, and to get the d
- `workbench\_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 it failed. Read it when the user asks whether their documents are in yet, or before a search that needs them — don't poll in a loop; ingestion of a few document
- `workbench\_kb\_delete`: Deletes a knowledge base and everything in it. Flows that search it will find nothing — check which agents use it \(the user knows; the KB page in Workbench lists them\) and say so before proposing. May return \`needs\_confirmation\`.
- `workbench\_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. To replace a document, remove it then workbench\_kb\_add\_documents the new version. May return \`needs\_confirmation\`.
- `workbench\_kb\_list`: Lists every knowledge base in the active workspace the caller can see. Returns summaries \(id, name, description, status, doc/chunk counts, embedding model\). Use an id with \`workbench\_kb\_search\` to retrieve content.
- `workbench\_kb\_search`: Retrieves the most relevant chunks from one knowledge base — the core RAG primitive. \`mode:"semantic"\` \(default\) embeds the query and ranks by meaning \(spends a small amount of workspace credit\); \`mode:"keyword"\` is a free case-insensitive substring match. Each hit carries the chunk text, its docume
- `workbench\_kb\_create`: Creates an empty knowledge base. Recipe 'docs' \(default\) for reference material an agent searches at runtime; 'tabular' for spreadsheet-style data queried with SQL; 'graph' for entity/relationship extraction. After creating, add content with workbench\_kb\_add\_documents, then give an agent flow a sear
- `workbench\_kb\_add\_documents`: Adds documents to a knowledge base and starts ingestion \(chunk + embed; graph KBs also extract entities; tabular KBs load CSV as tables\). Text goes inline \(Markdown, plain text, CSV — encoding utf8\); binary files \(PDF, .docx\) go base64-encoded with their mimeType. Up to 50 sources per call, \~10 MB e
- `workbench\_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 accuracy \(null until something is published\). A shim is a small decision model that runs inside an app with no model call. Start here to get a shimId.
- `workbench\_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 before it can build, and the newest build's report — held-out accuracy, recall per answer, which answers get mistaken for which, and the compiler's notes. Read it bef
- `workbench\_shim\_create`: Creates a shim from a name, the question it answers, and its answers. Add examples afterwards with workbench\_shim\_add\_examples — three or more per answer and it builds on its own. May return \`needs\_confirmation\`.
- `workbench\_shim\_add\_answer`: Adds one answer \(a label and, optionally, when it applies\). The shim needs three examples of it before it builds again with the new answer. May return \`needs\_confirmation\`.
- `workbench\_shim\_add\_examples`: Adds example inputs to one answer. Write inputs a real person would actually type in the shim's setting — varied in length, register and specifics, each one clearly this answer and not another — never paraphrases of the answer's name. Read the shim first so new examples fit alongside the existing on
- `comments\_list`: Lists the comment threads on one workspace entity \(open first, then resolved\) with authors and timestamps. Read this before weighing in on contested work — the threads are where disagreement lives before it becomes a decision.
- `comments\_create`: Posts a comment on a workspace entity — a new thread, or a reply when rootId is given. Use it to leave findings where the discussion already lives \(an eval result on the flow being debated, a summary on a long thread\). Mention people via mentionedUserIds \(from workspace member ids\) to ring their not
- `comments\_resolve`: Sets a comment thread's resolved state \(rootId = the thread's root comment id\). Resolve ONLY when the human asked or the thread's question is demonstrably settled — and say what settled it in a reply first. Reopening is for new evidence.
- `workbench\_tasks\_get`: One Task in full: its sentence, status, the latest saved plan \(the clauses — which run flows, which the assistant handles, who decides at each gate\) with the flow and people names the plan refers to, and its recent runs, plus the sites its machine may reach \(allowedSites\) and the sites its plan name
- `workbench\_tasks\_update`: Changes a task's name — the gallery label only. The sentence and plan are versioned and change through workbench\_tasks\_compile + workbench\_tasks\_freeze, never here. May return \`needs\_confirmation\`.
- `workbench\_tasks\_delete`: Deletes a task. Runs still in flight are stopped \(a gate waiting on someone is closed\), and its schedule trigger stops firing; past runs stay in history. Check workbench\_tasks\_get for live runs and say so before proposing. May return \`needs\_confirmation\`.
- `workbench\_tasks\_set\_sites`: Sets the full list of sites a Task's machine may reach \(example.com, or \*.example.com for its subdomains; up to 20\), for steps that have to use a site like a person would. It replaces the list, so read workbench\_tasks\_get first \(allowedSites, and computer.sites for what the plan names\) and pass ever
- `workbench\_tasks\_list`: Lists the workspace's Tasks — sentence-orchestrated processes — with their sentence, status, and recent runs \(id, status, who a waiting run is on\). Use this to find a task the user names \('claims intake'\) and to see what's in flight; workbench\_tasks\_get reads one in full.
- `workbench\_tasks\_create`: Creates a DRAFT Task from a name + sentence. A Task is for work with people in the loop \(someone approves, decides or acts on each item before anything else happens\) or a specific process mapped in Compass; its runs are measured. When nobody but you acts on it and you'd just do the same thing each t
- `workbench\_tasks\_compile`: Runs the compiler over a sentence and returns the PROPOSED plan \(or repair-grade problems — fix by refining the sentence with the user, not by guessing\). Nothing persists. Present the proposal in plain terms: which clauses run flows, which you will handle, who decides, what the compiler noted. \`comp
- `workbench\_tasks\_freeze`: Freezes a reviewed plan as the Task's next version and activates it. Pass the EXACT plan object a compile returned — never hand-edit it \(change the sentence and recompile instead\). Freeze ONLY after the user has seen the proposal and said go; echo what you're freezing in one line first. In-flight ru
- `workbench\_tasks\_start`: Kicks off a run of a Task and returns at once; the run carries on by itself and is live on the task's page. When the task expects an input document \(its trigger has an input\), pass the user's material as \`input\` — pasted text, extracted attachment text, or JSON. Tell the user it has started and what
- `workbench\_tasks\_run\_view`: The run's current state rendered as its sentence: what ran \(with timings\), which path each gate took, what's waiting on whom and for how long, what's coming up. Use whenever the user asks where something stands, and after acting on a gate.
- `workbench\_tasks\_act`: Records THIS user's verdict on a run that is waiting on them — the labels come from the gate \(workbench\_tasks\_run\_view shows them via the plan; a wrong label errors listing the real options\). Echo the verdict + note back to the user in one line BEFORE calling; that echo is the confirmation. Refuses
- `search\_workspace`: Finds anything in the workspace in one call — uploaded files \(searching the text inside them\), folders, Workbench flows, shims, knowledge bases and tasks, Compass pages and changes, Caliper datasets, evals, rubrics, reviews, specs and sources, Ledger entries, Napkin sketches, decks, docs, sheets, di
- `entity\_tags\_get`: Returns the tags on a batch of entities of one kind — the labels galleries organize by. Ids come from the kind's list/get tool or from search\_workspace. Use it before entity\_tags\_set so you replace the full set knowingly, and to answer 'what is this filed under'. Entities the user can't see are omit
- `entity\_tags\_browse`: Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by. With a tag: everything filed under it across every tool, each with its kind, id, title, and path. Use it to reuse existing labels instead of inventing
- `entity\_tags\_set`: Replaces the FULL tag set on one entity \(an empty list clears it\). Read the current tags with entity\_tags\_get first and pass the merged list — this is not additive. Tags are lowercase letters, numbers, spaces, and hyphens; prefer labels already in use \(entity\_tags\_browse\) so the workspace's vocabula

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html