Create and edit roadmaps with JSON or markup; share edit and view links from AI agents.
Scored across 43 tools
Most tools are separated by domain prefixes and clear resource nouns, but artifacts_get/export_json and roadflow_get/export_json/export_markup return effectively the same workspace data, and model_get overlaps with the list_* tools. The detailed descriptions help, but an agent could easily pick the wrong read/export tool.
All three namespaces use a consistent prefix_verb_noun arrangement, with singular/plural variants and bulk operations following the same pattern. Minor deviations like artifacts_new/model_new/roadflow_new instead of create and bare status/get verbs keep it from a perfect score.
43 tools is well over the 25-tool threshold for a single MCP server, even though the surface is split into three domains. This large count makes initial tool selection expensive for an agent and suggests the server could be split into artifacts, model, and roadflow servers.
Each subdomain covers its main lifecycle: create/open/read/update/version for workspaces, and parameter/observation/edge CRUD plus evaluation for models. The main gaps are the lack of hard-delete for shared artifacts/maps and no project delete—only session unbind—but these are workable.
Replace (or merge) the Artifacts graph with normalized JSON. Shared edit mode auto-saves to the cloud.
Inputs: json, merge.
Clear the in-memory Artifacts workspace for this MCP session (does not delete cloud graphs or the Plans workspace).
Inputs: no named parameters.
Export the current Artifacts workspace as JSON (serializeState).
Inputs: no named parameters.
Return the current Artifacts workspace as JSON.
Inputs: no named parameters.
Load one shared Artifacts version by relative index (-1 newest). Optional load=true replaces the MCP workspace (does not save).
Inputs: rel (required), load.
List shared Artifacts version checkpoints (newest first). Requires a shared edit workspace.
Inputs: no named parameters.
Create an ephemeral in-memory Artifacts graph workspace. Optional seed JSON (serializeState shape: nodes + labels). No cloud id until artifacts_create_shared.
Inputs: json.
Return mode, ids, /artifacts/?id= URLs, and node/label counts.
Inputs: no named parameters.
Delete a manual edge by edgeId.
Inputs: edgeId (required), id.
Delete one fact by parameterId + scope/scopeKey + setId.
Inputs: parameterId (required), id, scope, setId, +1 more.
Delete a parameter and its observations (cascade).
Inputs: parameterId (required), id.
Unbind the Model project from this MCP session. Does not delete MySQL rows.
Inputs: no named parameters.
Read-only computeModel. Does not write MySQL. View ids allowed. Default period is calendar start (not today). periodId and range* are mutually exclusive. Cell cap 2000.
Inputs: id, setId, slice, periodId, +5 more.
Hydrate records from MySQL. include=summary (default counts), dictionaries, parameters, observations, edges, or all. Prefer model_upsert_observation to change one fact — do not treat this as a blob to rewrite.
Inputs: id, include.
One catalog row plus its observations (facts).
Inputs: parameterId (required), id.
Streams, axes (members), phases, parameter sets, chains, and calendar. Period members may be derived from calendar.
Inputs: id.
Manual lineage edges only (SOURCE/FLOW/INTERFACE). FORMULA edges are derived from formulas on load — not stored.
Inputs: id, toId, fromId, edgeType.
List facts. Filter by parameterId, setId, evidenceStatus. Sets are a column (Base/Downside/Upside), not an axis.
Inputs: id, setId, parameterId, evidenceStatus.
List parameter catalog rows. Optional filters: streamId, role, layer, primaryOwner.
Inputs: id, role, layer, streamId, +1 more.
Create a Model project in MySQL (parameter register). Allocates a view id (mv-…) when omitted and returns viewUrl. Optional seed: title, calendar, streams, axes, phases, parameterSets, chains, parameters, observations, edges. Does not persist CALC outputs or FORMULA edges. Binds this MCP session. UI: /model/?id=…
Inputs: axes, edges, title, chains, +7 more.
Bind this MCP session to an existing Model project (edit or view id). View ids are read-only.
Inputs: id (required).
Update title, calendar, viewId, streams, axes, phases, parameterSets, and/or chains. Send If-Match via rev. Replaces each provided dictionary in full.
Inputs: id, rev, axes, title, +6 more.
Counts, rev, and /model/?id= URLs for the bound project (or pass id).
Inputs: id.
Create or patch a manual SOURCE, FLOW, or INTERFACE edge. FORMULA is rejected.
Inputs: edgeId (required), id, rev, toId, +5 more.
Create or replace one fact (parameterId + scope + setId). Example: Base P2 facility MW. Do not write CALC-computed values; only IN facts or CALC overrides (valueOverride). Pass rev for If-Match.
Inputs: parameterId (required), id, rev, scope, +7 more.
Create or replace many facts (cap 400). Same body shape as model_upsert_observation. Rejects CALC outputs unless valueOverride. continueOnError returns per-row errors; otherwise one transaction.
Inputs: observations (required), id, continueOnError.
Create or patch one parameter definition (not observations). Pass rev for If-Match on update.
Inputs: parameterId (required), id, rev, name, +20 more.
Create or patch many catalog rows (cap 400). Same body shape as model_upsert_parameter. continueOnError returns per-row errors; otherwise one transaction.
Inputs: parameters (required), id, continueOnError.
Replace workspace state with normalized JSON (serializeState shape). In shared edit mode, saves to the cloud automatically.
Inputs: json, merge.
Replace roads via friendly markup (same as the editor panel). Shared edit mode auto-saves.
Inputs: markup (required).
Clear the in-memory workspace for this MCP session (does not delete cloud maps).
Inputs: no named parameters.
Export steps as CSV (road, goal, lane, step, notes, type, status, position, date).
Inputs: no named parameters.
Export the current workspace as JSON (serializeState).
Inputs: no named parameters.
Export the current workspace as friendly markup.
Inputs: no named parameters.
Return the current workspace as JSON and/or markup.
Inputs: format.
Load one shared-map version by relative index (e.g. -1 newest, -2 previous). Returns JSON state. Does not change the live map or workspace unless load=true.
Inputs: rel (required), load.
List shared-map version checkpoints (newest first). Relative indexes: -1 = newest. Requires a shared edit workspace (not view-only).
Inputs: no named parameters.
Create an ephemeral in-memory roadflow workspace (default). Optional seed JSON and/or markup. No cloud id until create_shared.
Inputs: json, markup.
Return mode, ids, URLs, and road/step counts for the current MCP session workspace.
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Create, read and live-edit visual boards, Kanban plans, Gantt timelines and diagrams with AI agents.
Flowcharts that people and agents edit together on one live canvas, exported as Mermaid.
Create, edit and organize hand-drawn diagrams (flowcharts, ER, architecture) from any AI agent.
Share HTML/Markdown documents via URL instantly. Create, edit, delete docs from any AI tool.
Add one secure layer between your agents and this server.