Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agentic Mermaid

NPM · AGENTIC-MERMAID · 2 COMPONENTS

Render, verify, describe, and safely edit Mermaid diagrams through MCP.

+15 this week 89 Trust /100

Last scanned (19 minutes ago)

Scores higher than 93% of npm servers

Category Design and Media

Trust breakdown (7 categories)

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 Security99
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 2 of 23 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to adewale/agentic-mermaid). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 2 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability50
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 5167 tokens (~861/item across 6 items; 6 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 Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
  • 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 current MCP spec version (2026-07-28).Pass
Changelog

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.

  • 3 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 2 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
    • Package version: 0.5.5 → 0.5.6 functional
  • 1 Nov 26 +26
    • Known CVEs: unverified → pass ▲ security
    • Malware scan: unverified → pass ▲ security
    • Dependency health: unverified → 0.91 ▲ functional
  • 31 Oct 26 −11
    • Known CVEs: pass → unverified ▼ security
    • Malware scan: unverified → pass ▲ security
    • Stability: 0.97 → pass security
    • Dependency health: 0.91 → unverified ▼ functional
    • Package version: 0.4.1 → 0.5.5 functional
  • 30 Oct 26 0
    • Stability: pass → 0.97 functional
    • Package version: 0.5.3 → 0.5.4 functional
  • 29 Oct 26 −17
    • Malware scan: pass → unverified ▼ security
    • Stability: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Dependency health: 1.00 → 0.91 ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Schema quality: 1094 → 852 ▲ functional
    • Schema quality: 1094 → 850 ▲ functional
    • Schema quality: excellent → good functional
    • Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. functional
    • Package version: 0.4.1 → 0.5.3 functional
    • Package version: 0.4.1 → 0.5.1 functional
  • 24 Oct 26 +1
    • Stability: 0.97 → pass security
  • 23 Oct 26 −1
    • Stability: pass → 0.97 functional
Diagnostics

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 5 Nov 2026 · Analysed npm/agentic-mermaid@0.5.6

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo adewale/agentic-mermaid
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/adewale/agentic-mermaid/.github/workflows/publish.yml@refs/tags/v0.5.6
Rekor log index 3642793127
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:7c70366ed17e199eacf80227cce245cd040e0915f59ed146f787e99aeebc4c40935e0e624ce783895be14fa021c802d7b5c0c2a6be7511f2451a2a63a

Background: How many MCP packages publish verified provenance →

Dependencies 23 packages
Packages resolved 23
Stale 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~4,922 tokens

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 →

Tool Tokens
build ~188

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`: { ok, family, source, verify } or { ok:false, family, opIndex, error }. Call `describe_sdk` for the family before authoring unfamiliar ops.

NameTypeReqDescription
familystringyesDiagram family to author (one of: zenuml, eventmodeling, flowchart, state, sequence, timeline, class, er, journey, architecture, xychart, pie, quadrant, gantt, mindmap, gitgraph, radar, sankey, c4, p…
opsarrayyesNon-empty ordered list of ops; each is { kind, ...fields }.

No output schema declared.

No examples provided.

describe ~105

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 semantic fact lines for machine checking (for example edge A -> B : label, member Duck +quack()).

NameTypeReqDescription
formatstring–text (default), json AX tree, or facts semantic read-back.
sourcestringyesMermaid source.

No output schema declared.

No examples provided.

describe_sdk ~139

Return version-matched mutation operations for one diagram family, or use capability=resolved-scene for painted geometry, runtime limits and typed errors. Use detail=signatures for the compact op menu or detail=fields (default) for exact field types, required flags, enum values, defaults, and constraints. Call this before build, mutate, or execute when the family schema is not already known.

NameTypeReqDescription
capabilitystring–Read-only rendering capability; use instead of family.
detailstring–signatures for a compact menu; fields for the complete schema (default).
familystring–Diagram family whose mutation operations are needed.

No output schema declared.

No examples provided.

execute ~3,844

Run JavaScript in a sandboxed node:vm context; return a value. No promises, async/await, dynamic import, or type annotations. SDK: type DiagramKind='flowchart'|'state'|'sequence'|'timeline'|'class'|'er'|'journey'|'architecture'|'xychart'|'pie'|'quadrant'|'gantt'|'mindmap'|'gitgraph'|'radar'|'sankey'|'c4'|'packet'|'kanban'|'requirement'|'treemap'|'ishikawa'|'block'|'eventmodeling'|'zenuml' type MutationOp={kind:string;[field:string]:unknown} type Result<T,E={code:string;message:string}>={ok:true;value:T}|{ok:false;error:E} type ExternalFamilyId=`family:${string}`;interface SourceLocation{readonly line:number;readonly col:number;}interface SourceMap{readonly nodes:ReadonlyMap<string,SourceLocation>;readonly edges:ReadonlyMap<string,SourceLocation>;readonly groups:ReadonlyMap<string,SourceLocation>;readonly labels:ReadonlyMap<string,SourceLocation>;readonly spans?:SourceMapSpans;}interface SourceMapSpans{readonly preserved:PreservedSourceSpans;readonly nodes:ReadonlyMap<string,SourceSpan>;readonly edges:ReadonlyMap<string,SourceSpan>;readonly groups:ReadonlyMap<string,SourceSpan>;readonly labels:ReadonlyMap<string,SourceSpan>;readonly metadata?:ReadonlyMap<string,ReadonlyMap<string,{readonly key:SourceSpan;readonly value:SourceSpan;}>>;}interface PreservedSourceSpans{readonly source:SourceSpan;readonly wrapper?:SourceSpan;readonly frontmatter?:SourceSpan;readonly initDirectives?:readonly SourceSpan[];readonly accessibilityDirectives?:readonly SourceSpan[];readonly header:SourceSpan;readonly body:SourceSpan;}interface SourceSpan{readonly start:SourceSpanPoint;readonly end:SourceSpanPoint;}interface SourceSpanPoint{readonly offset:number;readonly line:number;readonly col:number;}interface SourcePreservationReceipt{readonly version:1;readonly classification:'unsupported'|'inventory-only'|'unknown';readonly source:string;readonly header:string;readonly upstreamFamilyId?:string;readonly mermaidVersion:string;readonly spans?:PreservedSourceSpans;}interface ParseError{readon…

NameTypeReqDescription
codestringyesJavaScript to execute; mermaid.* SDK is global.
timeoutMsinteger–Optional hard timeout (default 5000ms).

No output schema declared.

No examples provided.

mutate ~302

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 it for straightforward edits; reserve `execute` for logic the ops don't express. Returns { ok, family, source, verify:{ ok, warnings } } on success, or { ok:false, family, opIndex, error } — where `error` names the offending field and lists the valid ones — when an op is malformed or cannot apply. Ops apply in order and are all-or-nothing: the first failing op stops the batch (its position is `opIndex`) and the input is left untouched. Each op is { "kind": <op>, …fields }. Call `describe_sdk` for the detected family before authoring unfamiliar ops; it returns compact signatures or exact field types, enum values, defaults, and constraints. Set mode to source-preserving for supported edits to opaque Class or Flowchart source. Exact edited bytes and portability warnings are retained; unsupported operations still fail atomically. This mode does not promise portable export.

NameTypeReqDescription
modestring–Source-preserving mode edits owned source ranges without regenerating unsupported syntax.
opsarrayyesNon-empty ordered list of edit ops; each is { kind, ...fields }.
sourcestringyesMermaid source to edit.

No output schema declared.

No examples provided.

render_png ~344

Rasterize a Mermaid source string to PNG. By default returns base64-encoded PNG bytes. Set output to "file" or "url" to write a managed artifact instead; artifact responses include {path?, url?, mimeType, bytes, sha256}. File/URL artifacts are generated under the MCP server's artifact directory with safe names, size limits, and TTL cleanup. Uses bundled resvg + Inter (DejaVu Sans fallback) for same-machine cross-runtime determinism where verified. Agentic Mermaid outputs SVG, PNG, ASCII, Unicode, and JSON layout. For non-PNG output, use execute() with mermaid.renderMermaidSVG, mermaid.renderMermaidASCII (useAscii true for ASCII, false for Unicode), or verifyMermaid(...).layout — those are streaming text/data and don't need a dedicated tool.

NameTypeReqDescription
backgroundstring–Portable basic color or hex color painted behind the raster artifact.
fitToobject–Exactly one output width or height constraint.
fontDirsarray–Trusted native host directories searched for additional fonts.
loadSystemFontsboolean–Allow the native rasterizer to load machine-dependent system fonts.
minLabelPxnumber–Legibility floor in effective px: the render warns (BELOW_READABLE_SIZE) when fitTo/scale rasterizes the smallest configured text below it. 0 disables.
optionsobject–Shared advanced RenderOptions object.
outputstring–PNG return mode (default base64).
scalenumber–Positive output scale used when no fitTo constraint is supplied.
sourcestringyesMermaid source.

No output schema declared.

No examples provided.

Install

How do I install the Agentic Mermaid MCP server?

Agentic Mermaid runs locally as an npm package, launched with npx -y agentic-mermaid. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · agentic-mermaid

# add to Claude Code
claude mcp add adewale-agentic-mermaid -- npx -y agentic-mermaid
Common questions

What is the Agentic Mermaid MCP server?

Agentic Mermaid is an MCP server listed in the public MCP registry as io.github.adewale/agentic-mermaid. Render, verify, describe, and safely edit Mermaid diagrams through MCP. This page covers its npm package (agentic-mermaid).

Is the Agentic Mermaid MCP server safe to use?

Agentic Mermaid scores 89 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Agentic Mermaid MCP server expose?

Agentic Mermaid exposes 6 tools: execute, describe_sdk, render_png, describe, mutate, build. Their descriptions and schemas cost roughly 4,922 tokens of context every time the server is loaded.

Is the Agentic Mermaid MCP server still maintained?

Agentic Mermaid is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Agentic Mermaid MCP server under?

Agentic Mermaid declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.