Loading…
Agentic Mermaid renders, verifies, describes, and safely edits Mermaid diagrams for AI agents.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 27 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The agentic-mermaid-hosted MCP server exposes 9 tools, focused primarily on developer capabilities. Its published description reads: "Agentic Mermaid renders, verifies, describes, and safely edits Mermaid diagrams for AI agents". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates agentic-mermaid-hosted F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Unguarded destructive tools" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check agentic-mermaid-hosted's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add agentic-mermaid-hosted to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://agentic-mermaid.dev/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Run JavaScript in an isolated sandbox; return a value. One call composes edits. Submit JavaScript; declaration types are guidance. No promises, async/await, dynamic import, or type annotations. Hosted
Return version-matched mutation operations for one diagram family. Use detail=signatures for the compact op menu or detail=fields (default) for exact field types, required flags, enum values, defaults
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: execute
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
execute Execute Mermaid SDK code Run JavaScript in an isolated sandbox; return aRecommendationAnnotate destructive tools and require human approval.
tool: execute
A tool description tries to alter the model’s use of another tool.
than the direct render_svg/render_ascii/render_png/verify/describe tools —RecommendationDescriptions must describe only their own tool.
tool: describe_sdk
A tool description tries to alter the model’s use of another tool.
ild, mutate, or execute when the family schema is not already known.RecommendationDescriptions must describe only their own tool.
tool: mutate
A tool description tries to alter the model’s use of another tool.
counterpart to `execute`: plain JSON in, plain JSON out, no sandbox. PrRecommendationDescriptions must describe only their own tool.
tool: build
A tool description tries to alter the model’s use of another tool.
error }. Call `describe_sdk` for the family before authoring unfamiliar opsRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
up to 24 hours; execute, mutate, and build bypass it. HTTP /mcp responsRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: execute
An unusually long description is a common injection-padding tactic.
description length 14965 charsRecommendationKeep descriptions concise.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Render a Mermaid source string to themeable SVG. Returns { ok, svg }. Layout is deterministic: identical input produces identical geometry. The hosted boundary forces security:'strict' and embedFontIm
Render a Mermaid source string to text. Returns { ok, text }. useAscii true → plain ASCII (+,-,|); false/absent → Unicode box drawing (┌,─,│). targetWidth sets a hard terminal display-cell bound; impo
Rasterize a Mermaid source string to PNG. Returns { ok, png_base64 }. Hosted rendering uses resvg-wasm with bundled fonts; bytes may differ from the local napi renderer, so hosted PNG is a convenience
Parse and verify a Mermaid diagram without rendering it. Returns { ok, family, summary, warnings, layout: { bounds, nodes, edges } } for valid diagrams and { ok: false, errors } for parse failures. `f
Describe a Mermaid diagram. format=text returns { ok, text } with one or two summary sentences; format=json returns { ok, tree } with the AX tree; format=facts returns { ok, facts } with deterministic
Apply a list of structured edit ops to an existing Mermaid `source` and return the edited diagram. This is the declarative counterpart to `execute`: plain JSON in, plain JSON out, no sandbox. Prefer i
Author a new Mermaid diagram from blank by folding a list of structured ops over an empty diagram of `family`. The declarative counterpart to hand-writing source. Returns the same envelope as `mutate`