Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "search_docs" and "search_workspace"
⟨27 unchanged words⟩ Workbench, Caliper, Prism, Ledger, Napkin,zv1the assistant), an API behavior, or a policy. ⟨9 unchanged words⟩
⟨65 unchanged words⟩ sheet","diagram","interface","change","field","study","metric","folder"],"type":"string"},"minItems" ⟨60 unchanged words⟩
Added "prism_research_reports_get", "prism_research_reports_list" and "prism_research_run"; changed the definition of "search_workspace" (49 tools before, 52 now)
Findsentities across everyanythingtoolinbythenameworkspace 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(apps sending agent traces), Ledger entries, Napkin sketches, decks, docs, sheets, diagrams anddecks.interfaces.
Changed the definition of "comments_create", "comments_list", "comments_resolve" and 46 more
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":false,"title":"Comment on an entity"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Read an entity's comment threads"}
Added "prism_panel_runs_cancel", "prism_panel_runs_estimate", "prism_panel_runs_get" and 5 more; changed the definition of "prism_studies_results" (41 tools before, 49 now)
{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"panelRunId":{"description":"Read one synthetic panel run's answers instead of people's (ADR 0083). Synthetic results are never people's — say so whenever you report them.","type":"string"},"studyId":{"type":"string"},"workspace" ⟨31 unchanged words⟩
Cancel a panel run — Stops a queued, running or paused panel run. Answers already in stay. May return `needs_confirmation`.
Estimate a panel run — What running a study against a panel would cost: people, model calls, and approximate dollars of workspace credit. Starts nothing. Tell the person the cost before calling prism_panels_run.
Certificate recorded, valid to 2026-12-19
Authorization not required
Unknown → Live
First tool surface recorded: 41 tools (server version 0.0.0)
https://api.zerowidth.ai/mcp/x/prism (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 9 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"folderId":{"description":"Only search inside this folder and the folders under it (ids from workspace_folders_browse or a folder hit).","maxLength":100,"minLength":1,"type":"string"},"kinds":{"description":"Restrict to these kinds (flowfile,pagefolder,datasetflow,evalpage,entrydoc,boarddataset, …). Omit to search everything.","items": ⟨11 unchanged words⟩ ,"rubric","review","spec","source","doc","sheet","diagram","interface","change","folder"],"type":"string"},"minItems":1 ⟨10 unchanged words⟩ :"integer"},"q":{"description":"Case-insensitiveWords,substringanymatchedorder,againstcase-insensitive.names/titles.Fewer words find more.","maxLength":200,"minLength":1,"type ⟨33 unchanged words⟩
Read a desk-research report — One desk-research report in full: the brief (markdown) and the sources it cites. Its claims are what public sources say, not what anyone at the company told you; when you put them on the Compass map, cite sourceKind 'prism_report' with this report's id.
List a study's desk research — Every desk-research report on a study, newest first: id, title, the focus it was asked, depth, status (running / ready / failed) and an excerpt. Read one in full with prism_research_reports_get.
Run desk research on a study — Web-sourced desk research kept as a report on a study, with citations. Steer it with `focus`: research accumulates, a broad sweep first, then narrower runs as the questions sharpen. depth 'thorough' runs three angled passes at ~3× the credit. To research a company, make a standalone study about it (prism_studies_draft_standalone) and run one report per area of the business, e.g. focus 'how finance closes the month and approves spend at <company>, from job posts, filings and press'. It plans questions, searches, reads the pages and keeps only findings it can quote from them, so it takes a few …
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Resolve or reopen a thread"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Browse the workspace's tags"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Read the tags on entities"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Set an entity's tags"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Fetch ZeroWidth doc by slug"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"List ZeroWidth docs pages"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":false,"title":"Create a Prism field"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Delete a Prism field"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Read a Prism field's nodes"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"List Prism fields"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Rename, describe, or share a Prism field"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":false,"title":"Keep a study insight in Ledger"}
{"destructiveHint":false,"openWorldHint":true,"readOnlyHint":false,"title":"Mint a study interview invite"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"A study's interviews"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":false,"title":"Expand a Prism node along an axis"}
{"destructiveHint":false,"openWorldHint":true,"readOnlyHint":false,"title":"Run desk research on a Prism node"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Pin or color a Prism node"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Cancel a panel run"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Estimate a panel run"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"A panel run's progress and analysis"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":false,"title":"Create a synthetic panel"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Draft a synthetic panel from a description"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"A synthetic panel and who's on it"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"List synthetic panels"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":false,"title":"Run a study against a synthetic panel"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"What the workspace's research has found"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":false,"title":"Start a recurring research series"}
{"destructiveHint":true,"openWorldHint":true,"readOnlyHint":false,"title":"Field the next wave of a series"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"List research series"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Pause, resume, or reschedule a research series"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Run or refresh a study's analysis"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Crosstab a question by a cut"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Delete a study"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":false,"title":"Draft a feedback study from a node"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Draft a survey from a study's interviews"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":false,"title":"Draft a standalone study"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Read a study + its insights"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"List a node's feedback studies"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"List every study in the workspace"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Write a study's report narrative"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"A study's computed results"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"A study's discovered segments"}
{"destructiveHint":true,"openWorldHint":false,"readOnlyHint":false,"title":"Discover a study's segments"}
{"destructiveHint":true,"openWorldHint":true,"readOnlyHint":false,"title":"Edit, publish, open, or close a study"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Everything we know about a research subject"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Search ZeroWidth docs"}
{"destructiveHint":false,"openWorldHint":false,"readOnlyHint":true,"title":"Search the whole workspace"}
A panel run's progress and analysis — Status, progress, spend and the run's own analysis. For the numbers, call prism_studies_results with panelRunId. Synthetic answers are never people's: always say so when you report them.
Create a synthetic panel — Saves a panel from a spec (usually from prism_panels_draft) and draws its people from population records in the background, which takes a few seconds. Visible to the workspace unless visibility is PRIVATE. May return `needs_confirmation`.
Draft a synthetic panel from a description — Turns a plain description of an audience ("100 Midwest senior citizens") into a panel spec: filters on Census and General Social Survey fields, a size, and stated shares for traits with no data behind them (assumed). Saves nothing. Show the person the spec and assumedNotes, then pass the spec to prism_panels_create. poolSize is how many people in the population sample match.
A synthetic panel and who's on it — One panel with its current version and the share of people by every field (assumed fields flagged). Use it to confirm a draw looks like the audience the person meant.
List synthetic panels — Every synthetic panel the person can see: name, current version (people, status), runs so far, and fit (how far it sat from people the last time a study had both). Reuse an existing panel before drafting a new one.
Run a study against a synthetic panel — Starts a background run: every person on the panel answers the study (or, for kind interview, sits with the study's interviewer). Spends workspace credit — give the person the estimate from prism_panel_runs_estimate first. Works on draft studies. Answers land as their own result set, labeled synthetic, never counted as responses. Follow with prism_panel_runs_get. May return `needs_confirmation`.