Developer Tools

agentic-mermaid.dev

Generates diagrams from Mermaid syntax in multiple output formats.

1 endpoint9 known toolsFirst detected July 25, 2026Last detected September 6, 2026

ENDPOINT 1

https://agentic-mermaid.dev/mcp

No auth detected

MCP server metadata

Name: agentic-mermaid-hosted
Version: 0.4.1

Capabilities

tools

Server instructions

agentic-mermaid hosted MCP server (stateless). Direct tools render_svg, render_ascii, render_png, verify, and describe cover plain render/verify calls cheaply. Successful deterministic pure-tool results may be reused by a private server-side compute cache for up to 24 hours; execute, mutate, and build bypass it. HTTP /mcp responses themselves are cache-control: no-store, so clients must not infer response freshness from CDN headers. The x-agentic-mermaid-compute-cache response header reports hit, miss, mixed, bypass, or disabled. There is no layout seed — the library's optional style seed only re-rolls ink of styled looks. describe_sdk progressively discloses one family's version-matched mutation schema. Declarative mutate/build apply typed op lists and verify before emitting source; prefer them for straightforward structured edits. execute runs synchronous JavaScript against the typed mermaid.* SDK in an isolated on-demand sandbox for logic the ops don't express; async/await and Promise jobs are not supported, and network access is disabled. Inputs are capped at 64KB; for bigger diagrams, Code Mode artifacts, or file/URL PNG output, run the local stdio server (see https://agentic-mermaid.dev/docs/mcp/).

Known tools 9

execute

Run JavaScript in an isolated sandbox; return a value.

Potential side effects

describe_sdk

Return version-matched mutation operations for one diagram family.

Inferred read-only

render_svg

Render a Mermaid source string to themeable SVG.

Inferred read-only

render_ascii

Render a Mermaid source string to text.

Inferred read-only

render_png

Rasterize a Mermaid source string to PNG.

Inferred read-only

verify

Parse and verify a Mermaid diagram without rendering it.

Inferred read-only

describe

Describe a Mermaid diagram.

Inferred read-only

mutate

Apply a list of structured edit ops to an existing Mermaid `source` and return the edited diagram.

Potential side effects

build

Author a new Mermaid diagram from blank by folding a list of structured ops over an empty diagram of `family`.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentic-mermaid-hosted]
url = "https://agentic-mermaid.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentic-mermaid-hosted": {
      "type": "http",
      "url": "https://agentic-mermaid.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentic-mermaid-hosted
Remote MCP URL: https://agentic-mermaid.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentic-mermaid-hosted": {
      "url": "https://agentic-mermaid.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentic-mermaid-hosted": {
      "type": "http",
      "url": "https://agentic-mermaid.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentic-mermaid-hosted",
  "transport": "streamable-http",
  "url": "https://agentic-mermaid.dev/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agentic-mermaid.dev was fetched 2026-08-25T18:28:34.961Z.

Trust status Neutral

agentic-mermaid.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.