Diagrams MCP
PYPI · DIAGRAMS-MCP-SERVER · 2 COMPONENTS · SCANNED SEP 21
Generate cloud architecture diagrams, flowcharts, and sequence diagrams.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security95
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known medium-severity CVE affects filelock 3.19.1, reached via diagrams > pre-commit > virtualenv > filelock. A fixed version is available. View diagnostics → Fail
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 4 of 73 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (MIT License) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 93 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability86
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1301 tokens (~92/item across 14 items; 9 tools + 5 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (78% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Diagrams MCP server?
Diagrams MCP runs locally as a PyPI package, launched with uvx diagrams-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · diagrams-mcp-server
claude mcp add mskry-diagrams-mcp-server -- uvx diagrams-mcp-server
{
"mcpServers": {
"mskry-diagrams-mcp-server": {
"command": "uvx",
"args": [
"diagrams-mcp-server"
]
}
}
} {
"servers": {
"mskry-diagrams-mcp-server": {
"command": "uvx",
"args": [
"diagrams-mcp-server"
]
}
}
} codex mcp add mskry-diagrams-mcp-server -- uvx diagrams-mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mskry-diagrams-mcp-server": {
"type": "local",
"command": [
"uvx",
"diagrams-mcp-server"
],
"enabled": true
}
}
} openclaw mcp add mskry-diagrams-mcp-server --command uvx --arg diagrams-mcp-server
mcp_servers:
mskry-diagrams-mcp-server:
command: "uvx"
args: ["diagrams-mcp-server"] {
"McpServers": {
"mskry-diagrams-mcp-server": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"diagrams-mcp-server"
]
}
}
} assistant mcp add mskry-diagrams-mcp-server -t stdio -c uvx -a diagrams-mcp-server
{
"mcpServers": {
"mskry-diagrams-mcp-server": {
"command": "uvx",
"args": [
"diagrams-mcp-server"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 −3
- Stability: pass → 0.80 functional
- 18 Sept 26 0
- Stability: 0.97 → pass security
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −3
- Stability: pass → 0.80 functional
- 11 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/diagrams-mcp-server@0.1.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Vulnerabilities 4 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-qmgc-5h2g-mvrw | CVE-2026-22701 | medium | CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:H | yes |
| GHSA-w853-jp5j-5j7f | CVE-2025-68146 | medium | CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:H | yes |
| PYSEC-2026-1374 | CVE-2026-22701 | medium | CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:H | yes |
| PYSEC-2026-1375 | CVE-2025-68146 | medium | CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 73 packages
| Packages resolved | 73 |
|---|---|
| Stale | 3 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
find_equivalent ~210
Find cross-provider equivalents for a diagram node by infrastructure role. Given a node name (e.g. 'EC2', 'Lambda', 'ComputeEngine'), returns the infrastructure role category it belongs to and the equivalent nodes from other providers. Args: node: Node class name to look up (case-insensitive, e.g. 'EC2', 'lambda'). target_provider: Optional provider to filter equivalents to (e.g. 'gcp', 'azure', 'aws'). If omitted, all equivalents across all other providers are returned. Returns: A dict with keys: category (str): Infrastructure role category name. description (str): Human-readable description of the category. source (dict): The matched node with keys node, provider, service, import. equivalents (list[dict]): Equivalent nodes, each with keys node, provider, service, import.
| Name | Type | Req | Description |
|---|---|---|---|
| node | string | yes | – |
| target_provider | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
list_categories ~82
List all infrastructure role categories with their mapped nodes. Returns a list of category dicts, each with: category (str): Category identifier (e.g. 'virtual_machine'). description (str): Human-readable description. providers (list[str]): Providers covered by this category. nodes (dict): Mapping of provider → list of node names in that category.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
list_nodes ~92
List available node classes for a provider.service combo. Args: provider: Provider name (e.g. 'aws', 'gcp', 'k8s'). service: Service category (e.g. 'compute', 'database', 'network'). Returns: List of nodes with keys: name, import, alias_of (optional).
| Name | Type | Req | Description |
|---|---|---|---|
| provider | string | yes | – |
| service | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
list_providers ~31
List all available diagram providers (aws, gcp, azure, k8s, onprem, etc.).
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
list_services ~65
List service categories for a provider (e.g. 'aws' -> ['compute', 'database', ...]). Args: provider: Provider name from list_providers (e.g. 'aws', 'gcp', 'k8s').
| Name | Type | Req | Description |
|---|---|---|---|
| provider | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
render_diagram ~140
Render a mingrammer/diagrams Python snippet to PNG and return the image. The code must be a complete Python script using `from diagrams import ...` imports and a `with Diagram(...)` context manager block. Args: code: Full Python code using the diagrams library. filename: Output filename without extension. download_link: If True, store the image on the server and return a temporary download URL path (/images/{token}) instead of the inline image. The link expires after 15 minutes.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| download_link | boolean | – | – |
| filename | string | – | – |
No output schema declared.
No examples provided.
render_mermaid ~174
Render a Mermaid diagram definition and return the image with metadata. The definition should be valid Mermaid syntax (e.g. flowchart, sequence, class, ER, state, or Gantt diagram). Returns a list of content blocks: the rendered image (SVG inline or PNG download link) plus a JSON text block with metadata including a mermaid.live edit link for opening the diagram in a browser editor. Args: definition: Mermaid diagram definition text. filename: Output filename without extension. download_link: If True, store the image on the server and return a temporary download URL path (/images/{token}) instead of the inline image. The link expires after 15 minutes.
| Name | Type | Req | Description |
|---|---|---|---|
| definition | string | yes | – |
| download_link | boolean | – | – |
| filename | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
render_plantuml ~141
Render a PlantUML diagram definition to PNG and return the image. The definition should be valid PlantUML syntax wrapped in @startuml/@enduml (sequence, class, component, activity, state, deployment, etc.). Args: definition: PlantUML diagram definition text. filename: Output filename without extension. download_link: If True, store the image on the server and return a temporary download URL path (/images/{token}) instead of the inline image. The link expires after 15 minutes.
| Name | Type | Req | Description |
|---|---|---|---|
| definition | string | yes | – |
| download_link | boolean | – | – |
| filename | string | – | – |
No output schema declared.
No examples provided.
search_nodes ~79
Search for diagram nodes by keyword across all providers and services. Args: query: Search term (case-insensitive substring match). Returns: List of matching nodes with keys: node, provider, service, import, alias_of (optional). Sorted by relevance: exact match first, then prefix, then substring.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
What is the Diagrams MCP server?
Diagrams MCP is listed in the public MCP registry as io.github.mskry/diagrams-mcp-server. Generate cloud architecture diagrams, flowcharts, and sequence diagrams. This page covers its PyPI package (diagrams-mcp-server).
Is the Diagrams MCP server safe to use?
Diagrams MCP scores 78 out of 100 on VerifyMCP. We recorded 4 known advisories against it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Diagrams MCP server expose?
Diagrams MCP exposes 9 tools: render_diagram, list_providers, list_services, list_nodes, search_nodes, and 4 more. Their descriptions and schemas cost roughly 1,014 tokens of context every time the server is loaded.
Is the Diagrams MCP server still maintained?
Diagrams MCP is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.