mcp-registry/io.github.flowboardstudio/flowboard · v3.5.0@5468b90e66e7f4a14c55b2e50ee68775fa0d14c8
As of 2026-10-26 23:12 UTC, the Flowboardstudio Flowboard MCP server is up with a Glimind reliability score of 85/100 (grade B). Over the last 30 days it answered 99.5% of Glimind's liveness checks. It had 7 outages in 90 days, with a median recovery of 21 minutes.
Discover cloud shapes and create, inspect, validate, patch, and review architecture diagrams.
Point your MCP client at this streamable-http endpoint: https://flowboard.studio/mcp
4 tool(s) list "required" fields that are not declared in "properties" (or "required" is not an array of strings).
Make "required" an array of property names that exist in "properties". Agents cannot supply an argument the schema never describes. How to fix →
23 of 23 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
31 parameter(s) across 18 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 →
6 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 18 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.flowboardstudio%2Fflowboard/fixes
{
"name": "create_diagram",
"description": "Create one persistent Flowboard architecture diagram after calling list_shapes and list_diagrams, then reuse its ID with patch_diagram or update_diagram instead of making test copies. Any node may contain any other node; indentation expresses grouping, not infrastructure policy. Markdown nodes look like '- API {#api type=pod x=100 y=100}'. Flows belong under ## Flows. JSON and YAML use flows[]. A node may use icon=github independently of type. See https://flowboard.studio/guide#agent-workflow",
"inputSchema": {
"type": "object",
"required": [
"content"
],
"properties": {
"format": {
"enum": [
"markdown",
"json",
"yaml"
],
"type": "string",
"default": "markdown"
},
"content": {
"type": "string",
"examples": [
"# Orders\n\n- API {#api type=pod x=100 y=100}\n- DB {#db type=database x=400 y=100}\n\n## Flows\n- api -> db {#orders speed=2 direction=forward color=#f05a47 label=\"orders\"}"
],
"description": "Diagram document in the selected format. Markdown, JSON, and YAML have equal capabilities and all call animated relationships flows: Markdown uses a ## Flows section; JSON and YAML use a flows array. Any node type may contain any other node type or open a shared view; only missing references, self-parenting, and cycles are rejected. Empty labels normalize to the node ID. Optional icon selects a visual glyph without changing type or containment. All nodes support titleSize/labelSize (sm, md, lg; titleSize takes precedence), headerStyle (compact, default), and titlePosition (inside, above). General diagrams use schemaVersion: 2 and viewType: general. Nodes can use geometry (rectangle, rounded, diamond, ellipse, cylinder, text), fill, stroke, textColor, and strokeWidth independently of optional C4 kind. Visual frame nodes use frame: {memberIds: [...], lanes?: [...], orientation?: horizontal|vertical}; they move their members without changing C4 parentId. View layouts support notes as well as nodes. Documents and views support page-local layers ({id,name,objectIds,hidden?,locked?}) and stackingOrder (back-to-front object IDs). Layers never change C4 ownership; locks are editor protections, not access-control permissions. Version 2 does not infer missing architecture meaning. Document, view, and node presentation settings architectureTypes/technologyLabels control labels without removing metadata. Flow routing supports fromSide/toSide (left/right/top/bottom), lane, offset, and lineShape (orthogonal, curved, or straight); parallel flows auto-separate in the editor. Optional composed or independent levels use views; an empty nodeIds/list is a blank board and multiple entryIds may open one shared view. Limits: 500 nodes, 1000 flows, 200 notes. Full guide: https://flowboard.studio/guide#markdown"
}
},
"x-flowboard": {
"guide": "https://flowboard.studio/guide#markdown",
"limits": {
"flows": 1000,
"nodes": 500,
"notes": 200
},
"flowSpeeds": [
0.125,
0.25,
0.5,
1,
2,
4,
8
],
"containment": "Any node type may contain any other node type.",
"shapeCatalog": "Use list_shapes or GET https://flowboard.studio/api/shapes to discover exact node types.",
"flowDirections": [
"forward",
"reverse",
"both"
]
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "delete_diagram",
"description": "Delete a persistent Flowboard diagram by ID.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"examples": [
"diagram-1e03a8b8c845c589a519",
"orders-event-streaming",
"https://flowboard.studio/users/alice/orders-event-streaming"
],
"description": "A canonical diagram ID, unique accessible title slug, /app?diagram= URL, or /users/{owner}/{diagram-slug} URL"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": true,
"idempotentHint": true
}
}{
"name": "get_architecture_decision",
"description": "Read one authorized workspace decision record and portable Markdown. Acceptance is a recorded human decision; do not infer approval.",
"inputSchema": {
"type": "object",
"required": [
"workspace",
"id"
],
"properties": {
"id": {
"type": "string"
},
"workspace": {
"type": "string",
"description": "Exact workspace slug to which the signed-in account belongs."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
}
}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/io.github.flowboardstudio/flowboard"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.flowboardstudio/flowboard"}) over MCP.
update_diagram ~886 tokenscreate_diagram ~873 tokenspropose_diagram_changes ~836 tokenssubmit_agent_feedback ~297 tokensvalidate_diagram ~270 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%2Fio.github.flowboardstudio%2Fflowboard?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.flowboardstudio%2Fflowboard?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.flowboardstudio%2Fflowboard.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.flowboardstudio%2Fflowboard.svg :target: https://glimind.com/server/mcp-registry%2Fio.github.flowboardstudio%2Fflowboard?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:fe2c6e3fcef7e330…, first seen 2026-10-17, included at leaf 5608 of 76,031. Version history · verify what your client received.
Compare: most reliable productivity servers · most reliable other servers · most reliable files servers · most reliable knowledge servers · most reliable retrieval 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 23:12 UTC, the Flowboardstudio Flowboard MCP server is up with a Glimind reliability score of 85/100 (grade B). Over the last 30 days it answered 99.5% of Glimind's liveness checks. It had 7 outages in 90 days, with a median recovery of 21 minutes.
Flowboardstudio Flowboard MCP server advertises 23 tools, including create_diagram, decide_diagram_proposal, delete_diagram, get_architecture_decision, get_architecture_model.
Point your MCP client at this streamable-http endpoint: https://flowboard.studio/mcp
Glimind scanned all 23 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.