CodePic
REMOTE · CODEPIC.CC · SCANNED SEP 20
AI agent draws editable hand-drawn diagrams (flowchart, ER, architecture) via MCP, not static images
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security66
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 7 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1600 tokens (~228/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 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 CodePic MCP server?
CodePic is a hosted endpoint at https://codepic.cc/api/mcp/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · codepic.cc
claude mcp add --transport http abelce-codepic 'https://codepic.cc/api/mcp/mcp'
{
"mcpServers": {
"abelce-codepic": {
"url": "https://codepic.cc/api/mcp/mcp"
}
}
} {
"servers": {
"abelce-codepic": {
"type": "http",
"url": "https://codepic.cc/api/mcp/mcp"
}
}
} [mcp_servers.abelce-codepic] url = "https://codepic.cc/api/mcp/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"abelce-codepic": {
"type": "remote",
"url": "https://codepic.cc/api/mcp/mcp",
"enabled": true
}
}
} openclaw mcp add abelce-codepic --url 'https://codepic.cc/api/mcp/mcp' --transport streamable-http
mcp_servers:
abelce-codepic:
url: "https://codepic.cc/api/mcp/mcp" {
"McpServers": {
"abelce-codepic": {
"Transport": "http",
"Url": "https://codepic.cc/api/mcp/mcp"
}
}
} assistant mcp add abelce-codepic -t streamable-http -u 'https://codepic.cc/api/mcp/mcp'
{
"mcpServers": {
"abelce-codepic": {
"type": "http",
"url": "https://codepic.cc/api/mcp/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 29 Aug 26 −1
- Tool “create_diagram” rewrote its description, which is the text the model reads security
- Tool “get_shape_docs” rewrote its description, which is the text the model reads security
- Schema quality: 1432 → 1600 ▼ functional
- New tool “get_shape_catalog” functional
- 26 Aug 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 0
- Stability: 0.97 → pass security
- 24 Aug 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.
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 31 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 30 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 · Probed https://codepic.cc/api/mcp/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=codepic.cc | CN=WE1,O=Google Trust Services,C=US | 4 Aug 2026 | 2 Nov 2026 | ECDSA 256 | ECDSA-SHA256 | 3038a9eb38d3badd13799042e9f958bb |
| SANs: codepic.cc, *.codepic.cc | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of codepic.cc. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| cc. | present | 12593 | 13 | Verified |
| codepic.cc. | present | 2371 | 13 | Verified |
| codepic.cc. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
| content-security-policy | frame-ancestors 'self' |
| x-frame-options | SAMEORIGIN |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://codepic.cc/api/mcp/mcp | Verified | 200 | |
| http (plaintext) | http://codepic.cc/api/mcp/mcp | HTTPS enforced | 308 | https://codepic.cc/api/mcp/mcp |
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 →
create_diagram Create Diagram ~687
Create a custom CodePic hand-drawn style diagram by specifying nodes and edges. Requires API Key authentication. Returns a public view URL. **THIS IS THE DEFAULT TOOL FOR ANY USER-DESCRIBED DIAGRAM.** Whenever the user describes a diagram they want ("draw an A/B test flowchart", "帮我画一个登录流程", "a system architecture with a load balancer and 3 servers", etc.), build it here from their description. Do NOT fall back to `create_from_template` / `list_templates` unless the user explicitly asked for a template. When responding to the user, present the returned URL as a clickable markdown link (e.g. `[Open in CodePic →](URL)`) so the user can click it directly in their AI client (Cursor / Claude / etc.). **Container nesting (IMPORTANT — use whenever possible):** - Set `parentId` on a node to nest it inside another node. ANY node type can be a container. - The parent automatically becomes draggable-as-a-group and users can keep dropping elements into it. - Call `get_shape_catalog` with tag `container-capable` to choose among native structural containers and adaptive semantic shapes such as rectangles, circles, ellipses, diamonds, cylinders, and hexagons. - Parent bounds are expanded automatically using the selected shape's title and outline safe area. - Use absolute canvas coordinates for all nodes — child coordinates are auto-converted to parent-relative. - Set node `name`, `description`, and `tags` when later MCP/Agent reads need stable business semantics beyond visible text. - **Rule**: whenever 2+ nodes logically belong to the same module / component / region, create a container node first and set `parentId` on each child. **Design tips for beautiful diagrams:** - Use semantic types: `button-primary` for CTA buttons (auto blue), `diamond` for decisions - Pick a color palette and apply it consistently — light fill + darker stroke of the same hue: • Blue: fillColor #e3f2fd / #bbdefb, strokeColor #1565c0, fontColor #1565c0 (or #ffffff on dark fill) • Green: fillC…
| Name | Type | Req | Description |
|---|---|---|---|
| backgroundColor | string | – | Canvas background color (default: '#f8f9fa') |
| edges | array | – | Array of connector edges between nodes |
| name | string | yes | Document name |
| nodes | array | yes | Array of shape nodes to place on the canvas |
No output schema declared.
No examples provided.
create_from_template Create from Template ~302
Create a new CodePic diagram from a predefined template. Requires API Key authentication. Returns a public view URL and edit URL. **STRICT USAGE RULE — READ BEFORE CALLING:** Only call this tool when the user has **explicitly** asked to use a template. Explicit signals include phrases like: "use a template", "from template", "用模板", "从模板创建", "list templates and pick one", or the user directly naming/selecting a template slug. If the user merely describes a diagram they want (e.g. "draw an A/B test flowchart", "帮我画一个登录流程", "给我做一个系统架构图"), **DO NOT** call this tool. Call `create_diagram` instead and build the diagram from the user's description. Never silently substitute a template for a described diagram — the user will get a generic result that does not match what they asked for. When responding to the user, present the returned URL as a clickable markdown link (e.g. `[Open in CodePic →](URL)`) so the user can click it directly in their AI client (Cursor / Claude / etc.).
| Name | Type | Req | Description |
|---|---|---|---|
| locale | string | – | Language for template content (default: en) |
| name | string | – | Document name (defaults to template name) |
| slug | string | yes | Template slug (e.g. 'flowchart', 'erd', 'kanban'). Call list_templates to see all. |
No output schema declared.
No examples provided.
get_diagram Get Diagram ~88
Fetch the current state of an existing CodePic diagram. Returns a compact summary of all elements with their IDs, types, positions, and parent-child relationships. Use this before update_diagram when you need to: add nested children to existing containers, make targeted edits to specific elements, or understand the current structure. Requires API Key authentication.
| Name | Type | Req | Description |
|---|---|---|---|
| documentId | string | yes | Document ID to fetch |
No output schema declared.
No examples provided.
get_shape_catalog Get Shape Catalog ~124
Return compact machine-readable shape metadata for planning a diagram: semantic tags, geometry family, container support, recommended padding, default size, and MCP availability. Use this before create_diagram when choosing shapes or containers. Unlike get_shape_docs, this tool is concise and filterable.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Filter by the shape category. |
| containerMode | string | – | Filter by container support. adaptive shapes become containers when they receive children. |
| tag | string | – | Filter by one exact AI tag, e.g. container-capable, decision, database, or architecture. |
No output schema declared.
No examples provided.
get_shape_docs Get Shape Docs ~75
Return the full CodePic shape reference — all element types, their fields, data payloads, and JSON examples. Call get_shape_catalog first for concise shape selection and container capabilities; use this tool when you need complete fields or type-specific data (e.g. select options, triangle direction, callout tail). No authentication required.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_templates List Templates ~108
List all available CodePic diagram templates. Use this ONLY when the user has explicitly asked to browse, list, or pick from templates (e.g. "show me templates", "列出模板"). Do NOT call this as a preparatory step when the user just described a diagram they want — in that case go straight to `create_diagram`. Discovering slugs here is only meaningful before a user-confirmed `create_from_template` call.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Filter by category |
No output schema declared.
No examples provided.
update_diagram Update Diagram ~216
Update an existing CodePic diagram. You can rename it, replace all nodes/edges, or add/remove individual nodes and edges. Requires API Key authentication. When responding to the user, present the returned URL as a clickable markdown link (e.g. `[Open in CodePic →](URL)`) so the user can click it directly in their AI client (Cursor / Claude / etc.).
| Name | Type | Req | Description |
|---|---|---|---|
| addEdges | array | – | Edges to add |
| addNodes | array | – | Nodes to add (without replacing existing ones) |
| backgroundColor | string | – | New canvas background color |
| documentId | string | yes | Document ID to update (from a previous create call) |
| edges | array | – | Full replacement of all edges |
| name | string | – | New document name |
| nodes | array | – | Full replacement of all nodes. If provided, replaces the entire canvas content. |
| removeEdgeIds | array | – | IDs of edges to remove |
| removeNodeIds | array | – | IDs of nodes to remove |
No output schema declared.
No examples provided.
What is the CodePic MCP server?
CodePic is an MCP server listed in the public MCP registry as io.github.abelce/codepic. AI agent draws editable hand-drawn diagrams (flowchart, ER, architecture) via MCP, not static images. This page covers its hosted endpoint (https://codepic.cc/api/mcp/mcp).
Is the CodePic MCP server safe to use?
CodePic scores 80 out of 100 on VerifyMCP. 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 CodePic MCP server expose?
CodePic exposes 7 tools: get_shape_docs, get_shape_catalog, list_templates, create_from_template, create_diagram, and 2 more. Their descriptions and schemas cost roughly 1,600 tokens of context every time the server is loaded.
Does the CodePic MCP server require authentication?
No. We connected to CodePic without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the CodePic MCP server still maintained?
CodePic 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.