mcp-registry/ai.zerowidth/workbench · v1.0.0
As of 2026-10-26 18:04 UTC, the Zerowidth Workbench MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 5 outages in 90 days, with a median recovery of 2 minutes.
Build, run and publish Workbench flows, tasks, shims and knowledge bases.
Point your MCP client at this streamable-http endpoint: https://api.zerowidth.ai/mcp/x/workbench
2 tool definition(s) exceed ~1,200 tokens each (largest: workbench_flows_schedule, ~1,439).
Move long reference material out of descriptions (link a doc or expose a resource), drop repeated examples, and collapse large enums. Trimming these to ~600 tokens saves ~1,673 tokens every session. How to fix →
61 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →
27 parameter(s) across 12 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →
2 tool(s) have parameters with no type (no type/enum/anyOf/$ref).
Give every parameter a "type" (or "enum"/"anyOf"). Untyped parameters make models guess — strings for numbers, objects for arrays. How to fix →
Loading this server's tool list costs an agent ~20,466 tokens before any work — more than 95% of MCP servers.
Split rarely-used tools into a separate server or a toolset the client can enable, or expose one "search tools" entry point. Many agents load every connected server's tools into every request. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
In the last 30 days: 0 tool(s) removed and 9 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 12 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fai.zerowidth%2Fworkbench/fixes
{
"name": "workbench_tasks_freeze",
"description": "Freezes a reviewed plan as the Task's next version and activates it. Pass the EXACT plan object a compile returned — never hand-edit it (change the sentence and recompile instead). Freeze ONLY after the user has seen the proposal and said go; echo what you're freezing in one line first. In-flight runs keep their pinned versions. After freezing, offer to start a first run.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"taskId",
"sentence",
"plan"
],
"properties": {
"plan": {
"description": "The plan object from workbench_tasks_compile, verbatim.",
"type": "string"
},
"taskId": {
"type": "string",
"description": "The task id (create a draft first if none)."
},
"sentence": {
"type": "string",
"maxLength": 5000,
"minLength": 1,
"description": "The sentence this plan was compiled from."
},
"workspace": {
"type": "string",
"description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
},
"approvalId": {
"type": "string",
"description": "Approval id from a prior needs_confirmation response. Omit on the first call."
}
}
},
"annotations": {
"title": "Freeze a compiled plan (activate the Task)",
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
},
"title": "Freeze a compiled plan (activate the Task)"
}{
"name": "workbench_tasks_start",
"description": "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 it does next. Check where it stands with workbench_tasks_run_view when they ask; don't poll it in a loop.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"taskId"
],
"properties": {
"input": {
"description": "Trigger payload — the document text / JSON the task starts from.",
"type": "string"
},
"taskId": {
"type": "string",
"description": "Task id (from workbench_tasks_list)."
},
"workspace": {
"type": "string",
"description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
},
"approvalId": {
"type": "string",
"description": "Approval id from a prior needs_confirmation response. Omit on the first call."
}
}
},
"annotations": {
"title": "Start a Task run",
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
},
"title": "Start a Task run"
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/ai.zerowidth/workbench"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/ai.zerowidth/workbench"}) over MCP.
workbench_flows_schedule ~1,439 tokensworkbench_flows_schedules_update ~1,434 tokensworkbench_flows_scaffold ~1,036 tokensworkbench_kb_add_documents ~500 tokensworkbench_flows_update ~453 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fai.zerowidth%2Fworkbench?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fai.zerowidth%2Fworkbench?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.zerowidth%2Fworkbench.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.zerowidth%2Fworkbench.svg :target: https://glimind.com/server/mcp-registry%2Fai.zerowidth%2Fworkbench?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:76b9f99a1aaca435…, first seen 2026-10-22, included at leaf 43710 of 74,608. Version history · verify what your client received.
Compare: most reliable communication servers · most reliable knowledge servers · most reliable retrieval servers · most reliable search servers · most reliable devops servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-26 18:04 UTC, the Zerowidth Workbench MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 5 outages in 90 days, with a median recovery of 2 minutes.
Zerowidth Workbench MCP server advertises 61 tools, including comments_create, comments_list, comments_resolve, entity_tags_browse, entity_tags_get.
Point your MCP client at this streamable-http endpoint: https://api.zerowidth.ai/mcp/x/workbench
Glimind scanned all 61 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.