Agentic Mermaid MCP server
io.github.adewale/agentic-mermaidadewalestreamable-httpv0.5.6Scanned
Render, verify, describe, and safely edit Mermaid diagrams through MCP.
9 tools: 7 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
7 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Agentic Mermaid MCP server can do
The Agentic Mermaid MCP server is published by the GitHub account adewale. It has 9 tools. It can create or change data (7 tools: execute, render_svg, render_ascii, render_png and 3 more), but cannot delete data. 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 3 findings (long-description and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 0.5.6.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
9 tools
Changes things 7Claude Code: ask
buildAuthor a new Mermaid diagram from blank by folding a list of structured ops over an empty diagram of `family`.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
executeRun JavaScript in an isolated sandbox; return a value.2 findings
Why it is in this group
- The name "execute" says "execute": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The description is 15,100 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...:boolean;type:string;note?:string}[]> opSignatures(family:DiagramKind):string[] }"
- Warn
The server marks "execute" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "execute" says "execute": a word for a change.
Description, as the server wrote it Run JavaScript in an isolated sandbox; return a value. No promises, async/await, dynamic import, or type annotations. SVG/ASCII/layout enforce security:'strict', embedFontImport:false. 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{readonly code:string;readonly message:string;readonly line?:number;readonly col?:number;readonly preservation?:SourcePreservationReceipt;readonly help?:string;}type RenderedRegionKind='node'|'edge'|'label'|'canvas'|'group'|'cluster'|'lane'|'band'|'compartment'|'plot'|'ring';interface RenderedRegion{id:string;kind:RenderedRegionKind;elementId?:string;parentId?:string;bounds:{x:number;y:number;w:number;h:number;};cellSpans?:Array<{row:number;start:number;end:number;}>;occludedCellSpans?:Array<{row:number;start:number;end:number;}>;sourceLine?:number;}type DiagramActionKind='href'|'call'|'callback';type DiagramActionSecurity='safe'|'unsafe'|'source-only'|'unsupported';interface DiagramActionRecord{id?:string;regionId?:string;family:DiagramKind;target:string;action:DiagramActionKind;raw:string;line?:number;href?:string;tooltip?:string;security:DiagramActionSecurity;executable:false;message?:string;}interface LayoutRect{x:number;y:number;w:number;h:number;}interface ExtensionIdentity<Kind extends string=string>{readonly id:`${Kind}:${string}`;readonly kind:Kind;readonly version:string;readonly compatibility:ExtensionCompatibility;readonly provenance:ExtensionProvenance;}interface ExtensionCompatibility{readonly[contract:string]:string|undefined;readonly core?:string;readonly scene?:string;}interface ExtensionProvenance{readonly owner:string;readonly source:string;readonly reference?:string;}type CheckMermaidSpec=readonly string[]|CheckMermaidObjectSpec;interface CheckMermaidObjectSpec{include?:readonly string[];exclude?:readonly string[];exact?:boolean;}interface CheckMermaidResult{ok:boolean;missing:string[];unexpected:string[];facts:string[];}interface CreateMermaidOptions{c4Variant?:C4Variant;direction?:Direction;}type C4Variant='C4Context'|'C4Container'|'C4Component'|'C4Dynamic'|'C4Deployment';type Direction='TD'|'TB'|'LR'|'BT'|'RL'; interface ValidDiagram{readonly kind:DiagramKind;readonly source:SourceMap} interface ExtensionValidDiagram{ readonly kind:ExternalFamilyId readonly descriptorIdentity:ExtensionIdentity<'family'> readonly source:SourceMap } interface PreservedValidDiagram{ readonly kind:ExternalFamilyId readonly source:SourceMap readonly body:{ readonly kind:'preserved' readonly representation:'opaque'|'unknown' readonly source:string readonly preservation:SourcePreservationReceipt readonly spans:PreservedSourceSpans readonly diagnostic:{ readonly code:'UNSUPPORTED_FAMILY'|'UNKNOWN_HEADER'|'FAMILY_DESCRIPTOR_MISMATCH' readonly message:string readonly help:string } } } type ParsedDiagram=ValidDiagram|ExtensionValidDiagram|PreservedValidDiagram type Narrow=(d:ParsedDiagram)=>ValidDiagram|null interface RenderedLayout{version:1;kind:DiagramKind|ExternalFamilyId;nodes:unknown[];edges:unknown[];groups:unknown[];labels?:Array<{id:string;text:string;bounds?:LayoutRect;container?:LayoutRect;visibility?:'visible'|'hidden'|'semantic'}>;regions?:RenderedRegion[];actions?:DiagramActionRecord[];bounds:{w:number;h:number}} interface ResolvedScene{version:2;family:string;width:number;height:number;svg:string} interface VerifyResult{ok:boolean;warnings:unknown[];layout:RenderedLayout;checks?:{renderability:'passed'|'failed'|'not-checked';sourceLoss:'detected'|'not-detected';taskCorrectness:'not-checked'}} type MermaidConfigScalar=string|number|boolean|null type MermaidConfigValue=MermaidConfigScalar|MermaidConfigValue[]|{[key:string]:MermaidConfigValue|undefined} type MermaidRuntimeConfig={[key:string]:MermaidConfigValue|undefined} interface StyleColors{bg?:string;fg?:string;line?:string;accent?:string;muted?:string;surface?:string;border?:string} type SceneStyleRole="node"|"edge"|"edge-label"|"group"|"group-header"|"label"|"actor"|"lifeline"|"activation"|"message"|"block"|"note"|"class-box"|"member"|"entity"|"attribute"|"relationship"|"cardinality"|"pie-slice"|"legend"|"bar"|"series"|"point"|"axis"|"grid"|"plate"|"section"|"task"|"milestone"|"marker-line"|"rail"|"period"|"event… [9100 more characters not shown]
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
mutateApply a list of structured edit ops to an existing Mermaid `source` and return the edited diagram.1 finding
Why it is in this group
- The description's first verb is "apply": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "mutate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "apply": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
render_asciiRender a Mermaid source string to text.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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; impossible bounds return a typed error.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
render_pngRasterize a Mermaid source string to PNG.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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 surface, not part of the byte-determinism contract. For file/URL artifacts use the local stdio server.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
render_svgRender a Mermaid source string to themeable SVG.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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 embedFontImport:false.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
verifyParse and verify source, structure, and renderability.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Parse and verify source, structure, and renderability. This runs the graphical pipeline. Returns { ok, family, summary, warnings, layout: { bounds, nodes, edges } } for valid diagrams and { ok: false, errors } for parse failures. `family` is the detected diagram family and `summary` a one-line description — check them: ok:true only means the diagram is structurally valid, not that it is the kind you intended. Warnings use the layout-rubric codes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
describeDescribe a Mermaid diagram.No findings
Why it is in this group
- The name "describe" says "describe": a word for reading.
Description, as the server wrote it 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()).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
describe_sdkReturn version-matched mutation operations for one diagram family, or use capability=resolved-scene for painted geometry, runtime limits and typed errors.No findings
Why it is in this group
- The name "describe_sdk" says "describe": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:01 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 7
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agentic-mermaid.dev/mcp: tools/list returned 9 tools to an anonymous client, including execute (write), render_svg (write), render_ascii (write), render_png (write), verify (write) and 2 more
Findings
Matches of fixed checks, with the text they matched.
- Warnexecute
The server marks "execute" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "execute" says "execute": a word for a change.
- Warnmutate
The server marks "mutate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "apply": a word for a change.
- Infoexecute
The description is 15,100 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...:boolean;type:string;note?:string}[]> opSignatures(family:DiagramKind):string[] }"
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:describe_sdkOnly readsdescriptioninputSchema
- Changed:executeChanges thingsdescription
Tools8 changed.~8 changedView diff
- Changed:buildChanges thingsinputSchema
- Changed:describe_sdkOnly readsinputSchema
- Changed:executeChanges thingsdescription
- Changed:mutateChanges thingsdescriptioninputSchema
- Changed:render_asciiChanges thingsinputSchema
- Changed:render_pngChanges thingsinputSchema
- Changed:render_svgChanges thingsinputSchema
- Changed:verifyChanges thingsdescription
Install
Pinned to version 0.5.6. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentic-mermaid https://agentic-mermaid.dev/mcpclaude mcp add --transport http agentic-mermaid https://agentic-mermaid.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__agentic-mermaid__describe_sdk",
"mcp__agentic-mermaid__describe"
],
"ask": [
"mcp__agentic-mermaid__execute",
"mcp__agentic-mermaid__render_svg",
"mcp__agentic-mermaid__render_ascii",
"mcp__agentic-mermaid__render_png",
"mcp__agentic-mermaid__verify",
"mcp__agentic-mermaid__mutate",
"mcp__agentic-mermaid__build"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agentic-mermaid. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.adewale/agentic-mermaid/verify?hash=de88d8fff8d36c12f014f34666e004718203a2f8c58a09a26893ba668c7e880f" | jq -e '.changed == false'Pinned hash de88d8fff8d3, from Nov 15, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.adewale/agentic-mermaid/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.adewale/agentic-mermaid)Source: MCP Registry · repository. Synced Nov 2, 2026, 15:17 UTC.
Agentic Mermaid MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agentic Mermaid MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 7 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Agentic Mermaid MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agentic Mermaid MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Agentic Mermaid MCP server have?
- 9 tools: 7 write, 2 read. execute, render_svg, render_ascii, render_png, verify, mutate, build, describe_sdk and 1 more.
Does the Agentic Mermaid MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agentic Mermaid MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agentic Mermaid MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Oct 31, 2026. Every change is on this page and in its Atom feed.