Generates diagrams using Google Gemini's image generation capabilities, with support for style references via multi-image input.
Generates diagrams using OpenAI's GPT Image model for professional diagram outputs.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@diagram-forge Create an architecture diagram for a three-tier web app"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Turn natural language into enterprise-grade architecture diagrams. Diagram Forge is an MCP server that combines template-driven prompt engineering with swappable AI image providers to generate professional diagrams from any MCP-compatible client.
Instead of wrestling with diagramming tools or manually crafting image generation prompts, describe your system in plain English and let Diagram Forge handle the rest — template selection, prompt engineering, style application, and cost tracking.
13 diagram templates — Architecture (TOGAF), C4 Container, Executive Infographic, data flow, component, sequence, integration, infographic, generic, product roadmap, workstreams, kanban, and brand infographic
2 image providers — Google Gemini (recommended), OpenAI (GPT Image)
Auto provider selection — Each template recommends the best provider/model for its diagram type
Template-driven prompts — YAML templates with hex-coded color systems, explicit rendering instructions, and layout rules
Style references — Feed a visual example to guide output consistency (Gemini)
Cost tracking — SQLite-backed usage and cost reporting
Cross-client — Works with Claude Code, Claude Desktop, Codex CLI, Gemini CLI via stdio transport
Related MCP server: arch7
pip install diagram-forgeOr from source:
git clone https://github.com/jessepike/diagram-forge.git
cd diagram-forge
pip install -e ".[dev]"Set at least one API key:
export GEMINI_API_KEY="your-key" # Google Gemini (recommended)
export OPENAI_API_KEY="your-key" # OpenAI GPT ImageClaude Code (.mcp.json in your project):
{
"diagram-forge": {
"command": "python",
"args": ["-m", "diagram_forge.server"]
}
}Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"diagram-forge": {
"command": "python",
"args": ["-m", "diagram_forge.server"]
}
}
}Codex CLI / Gemini CLI — same .mcp.json format as Claude Code.
Ask your AI client naturally:
"Generate an architecture diagram of a three-tier web app with a React frontend, Node.js API layer, and PostgreSQL database"
Or be more specific:
"Create a TOGAF-style architecture diagram showing our microservices. Use the architecture template, Gemini provider, 16:9 aspect ratio."
Tool | Description |
| Generate a diagram from a text prompt with template and style support |
| Edit an existing diagram with natural language instructions |
| List available diagram templates and their variables |
| Show configured providers, API key status, and supported features |
| List available style reference images |
| View generation costs and usage stats by provider, type, or day |
| Set up an API key for a provider (session-only) |
Type | Template | Best For |
| Enterprise Architecture (TOGAF) | System architecture, layered designs |
| C4 Container Diagram | Software system internals, C4 Level 2 |
| Executive Infographic | Stakeholder presentations, semantic colors + icons |
| Data Flow / Pipeline | ETL pipelines, data movement |
| Component Detail View | Service internals, module structure |
| Sequence Diagram | Request flows, protocol interactions |
| Integration / Connection Map | System connections, API landscape |
| Infographic / Learning Card | Concept explanations, overviews |
| Product Roadmap | Phase pipelines, gate icons, status badges |
| Workstreams / Priority Lanes | Swimlane planning with status and dependencies |
| Kanban Board | Three-column task boards with category color bars |
| Brand Infographic | Investor/marketing slides with brand aesthetic |
| Custom / Freeform | Anything else |
Feed a visual example to guide output consistency. Gemini supports this natively via multi-image input.
generate_diagram(prompt="...", style_reference="c4-container")Save your own styles to ~/.diagram-forge/styles/<name>/reference.png with an optional style.yaml for metadata.
Set provider="auto" (the default) and Diagram Forge picks the best provider based on the diagram type. Each template includes a tested recommendation. Override with provider="openai" or provider="gemini" when you want a specific model.
This repo includes a Claude Code plugin in diagram-forge-plugin/ that adds a guided UX layer on top of the MCP server:
/diagram:create — Guided diagram creation with context gathering
/diagram:iterate — Refine an existing diagram
/diagram:usage — View cost report
/diagram:templates — Browse available templates
Context-gatherer agent — Automatically explores your project to understand what to diagram
Diagram intelligence skill — Auto-triggers when you mention diagrams
To use, install the plugin or add the .mcp.json from the plugin directory.
Template selection — Matches your request to one of 13 YAML templates, each encoding proven prompt patterns (color systems, layer organization, legibility rules)
Prompt rendering — Merges your description with the template, substituting variables and applying style defaults
Provider dispatch — Sends the engineered prompt to your chosen provider (Gemini or OpenAI)
Image handling — Saves the generated image, records cost and metadata to SQLite
Iteration — Edit existing diagrams with natural language instructions via providers that support image editing
# Install dev dependencies
pip install -e ".[dev]"
# Run tests (52 tests)
python -m pytest tests/ -v --cov=diagram_forge
# Lint
ruff check src/ tests/
# Type check
mypy src/
# Test MCP tools interactively
npx @modelcontextprotocol/inspector python -m diagram_forge.server
# Run low-cost model benchmark (dry-run first)
python scripts/eval_diagram_models.py --dry-run --max-cost-usd 5
python scripts/eval_diagram_models.py --execute --providers gemini,openai --resolution 1K --max-cases 6 --max-cost-usd 5Benchmark and model-refresh docs:
docs/evaluation-runbook.md
docs/model-refresh-process.md
evals/benchmark_v1.yaml
src/diagram_forge/
server.py # FastMCP server — 7 tools, stdio transport
models.py # Pydantic v2 models
config.py # YAML + env var config loading
template_engine.py # Template loading and prompt rendering
style_manager.py # Style reference image management
cost_tracker.py # SQLite usage/cost tracking
providers/
base.py # BaseImageProvider ABC
gemini.py # Google Gemini
openai_provider.py # OpenAI GPT Image
templates/ # 13 YAML prompt templatesMIT
Configure an API key for a provider (sets environment variable for current session).
Args: provider: Provider name (gemini|openai) api_key: The API key to set
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | ||
| provider | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosure. It reveals the primary side effect (sets an environment variable) and that it is session-only. However, it does not mention overwrite behavior, validation, or any error/return expectations. It is minimal but not misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a clear, front-loaded sentence followed by an Args block. Each element serves a purpose, with no redundant text. The structure is easy to scan and immediately actionable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
As a simple configuration tool with no output schema, the description could have explained expected return values or error conditions. It does not mention what happens on success/failure, which limits completeness. However, the core behavior and parameters are covered.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description adds necessary value. For 'provider' it specifies allowed values (gemini|openai), which is substantial. For 'api_key' it provides a short but adequate definition. This compensates for the schema's lack of descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb and resource: 'Configure an API key for a provider.' It also notes the session-scoped side effect (sets environment variable), which clearly distinguishes it from sibling tools focused on diagram generation, template listing, and usage reports. The purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states it sets an environment variable for the current session, providing clear context on scope. It does not explicitly mention when-not-to-use or alternatives, but the tool's purpose is inherently clear among siblings. The session-scoped detail is a useful usage guideline.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Edit an existing diagram based on instructions.
Args: image_path: Path to the existing diagram image prompt: Edit instructions provider: Image generation provider (gemini|openai) resolution: Output resolution (auto-detect if not specified) reference_images: Additional reference image paths output_path: Where to save the result
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| provider | No | gemini | |
| image_path | Yes | ||
| resolution | No | ||
| output_path | No | ||
| reference_images | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior itself. It only states that the tool edits an image and saves a result, but does not mention side effects, overwrite behavior, provider requirements, or return values. This is insufficient for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and front-loaded with the purpose, followed by a compact argument list. It avoids excessive verbosity, though the argument list is not structurally formatted beyond plain text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 6 parameters and no annotations or output schema, the description provides parameter explanations but lacks behavioral context such as what happens to the original file, how providers affect output, and what the function returns. It is adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has zero descriptions, so the description compensates by explaining each parameter with meaningful detail, such as provider options (gemini|openai), resolution auto-detection, and the purpose of reference_images. This adds value beyond the schema's bare titles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Edit') and resource ('existing diagram') and distinguishes itself from sibling generate_diagram by emphasizing 'existing'. This clearly states what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for editing existing diagrams, but it does not explicitly state when to use it over generate_diagram or other alternatives. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate an architecture diagram from a text prompt.
Args:
prompt: Description of what to generate
diagram_type: Type of diagram (architecture|data_flow|component|sequence|integration|infographic|c4_container|exec_infographic|generic)
theme: Background theme (light|dark). Default: light — the portfolio-wide
default (rep / marketing / CISO-facing output is the common case). Pass
theme="dark" for a dark charcoal canvas. This single switch governs the
background; you do NOT need to describe a background color in prompt.
provider: LEAVE AS DEFAULT ("auto"). The server is responsible for picking the right provider and model for the diagram type — callers should describe what to draw and let the server decide how. The current default chain is OpenAI gpt-image-2 (primary) → Gemini (fallback). Override only if you have a specific provider/model comparison need.
model: LEAVE UNSET unless you're explicitly benchmarking models. Server picks the right model for the chosen provider.
resolution: Output resolution (1K|2K|4K)
aspect_ratio: Output aspect ratio (16:9|1:1|9:16|4:3)
style_reference: Style name or path to reference image
output_path: Where to save the image (auto-generated if not provided)
temperature: Generation creativity (0.0 to 2.0)
quality: Output quality tier for OpenAI gpt-image-2 / gpt-image-1-mini (low|medium|high|auto).
Cost scales dramatically: at 1536x1024 on gpt-image-2, low=$0.005, medium=$0.041, high=$0.165.
Ignored by Gemini and legacy gpt-image-1.5. Default: auto.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | ||
| theme | No | light | |
| prompt | Yes | ||
| quality | No | auto | |
| provider | No | auto | |
| resolution | No | 2K | |
| output_path | No | ||
| temperature | No | ||
| aspect_ratio | No | 16:9 | |
| diagram_type | No | generic | |
| style_reference | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden, and it does this well: it explains default provider fallback, cost scaling by quality tier, and that theme governs only the background. It stops short of stating file-creation side effects or auth requirements, but the output_path parameter and cost details provide meaningful transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The one-line summary is followed by a well-organized Args block. While long, each line adds essential info about defaults, constraints, or pricing; no filler or repetition. It is appropriately detailed for an 11-parameter tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 11 parameters, no annotations, and no output schema, the description is remarkably complete. It covers all parameters, provides usage decision rules, cost implications, and fallback behavior, leaving little ambiguity for an agent invoking the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description is the only source of parameter meaning. Every parameter is explained in Args, including defaults, allowed values, and special guidance for provider/model (LEAVE AS DEFAULT) and quality (cost breakdown). This far exceeds mere schema names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a clear verb and object: 'Generate an architecture diagram from a text prompt.' It distinguishes itself from sibling 'edit_diagram' by focusing on creation, and the parameter list covers many diagram types, making the scope explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides strong usage guidance: tells callers to leave provider/model as default, explains when to override, and gives context on theme defaults. It does not explicitly name alternative tools like list_templates, but the generation-vs-edit distinction is clear enough for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get usage and cost report for diagram generations.
Args: days: Number of days to report on (default: 30) group_by: Group results by 'provider', 'diagram_type', or 'day'
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| group_by | No | provider |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It accurately states the core behavior (getting a report) but does not explicitly note that it is read-only or describe the output format. The 'get' wording implies safety, and the description is not misleading, but it lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured. The first sentence states the purpose, and the Args list provides parameter details without unnecessary fluff. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, so the description should ideally describe the report's structure or contents. It does not mention what fields or format the report includes. The parameters are well-covered, but the output is left undefined, which is a gap for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no descriptions, so the Args section in the description is essential. It fully explains both parameters: 'days' as the report period and 'group_by' with allowed values. This goes beyond the schema's minimal structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with a specific verb ('Get') and resource ('usage and cost report for diagram generations'). It is distinct from sibling tools which focus on diagram generation and configuration.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context that this tool is for reporting, and no sibling tool overlaps with this purpose. It does not explicitly mention alternatives or exclusions, but the role is obvious from the tool's unique function.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List configured providers with status, models, and health information.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility for disclosing behavior. The verb 'List' clearly indicates a non-destructive, read-only operation, and the description details what information is returned. However, it does not disclose potential edge cases such as empty states, authorization requirements, or rate limiting, which would enhance transparency for a more complete picture.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the core action and resource. Every word contributes meaning, and there is no unnecessary jargon or repetition. It is optimally sized for quick comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no parameters, no output schema), the description is largely complete. It states the main purpose and the specific fields included in the result (status, models, health). While it does not explicitly describe the return format (e.g., array vs. object), the information provided is sufficient for most use cases, and the lack of complexity reduces the need for additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the input schema is an empty object. The description adds no parameter information, but since there are no parameters to document, the baseline of 4 applies. There is no additional semantic burden for the description to bear.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb ('List') and resource ('configured providers'), and distinguishes this tool from siblings like 'configure_provider' (which modifies providers) and other list tools (templates, styles). It also specifies the content of the listing (status, models, health), leaving no ambiguity about what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies that this tool is for viewing provider information, but it does not explicitly state when to use it versus alternatives, nor does it mention exclusions or prerequisites. The context is clear but not explicitly guided, so it remains at the 'implied usage' level.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all available style reference images.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It indicates a read-only operation ('List') and adds the qualifier 'available', but does not disclose return format, potential pagination, or error behavior. This is acceptable for a simple zero-parameter tool but lacks richer context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the verb and resource. Every word adds value, making it an appropriately sized and well-structured description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no params, no output schema), the description is nearly complete. It clearly states what the tool lists, but could optionally mention how style reference images relate to diagram generation for better context relative to the sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, so the description does not need to explain parameter details. The baseline of 4 applies, and the description correctly avoids inventing parameter information. No additional semantic burden exists.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'List all available style reference images' uses a specific verb (List) and resource (style reference images) that clearly distinguishes it from siblings like list_templates and list_providers. It's unambiguous and directly reflects the tool's function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool (when you need to see all available style reference images) but does not explicitly name alternatives or exclusion criteria. However, the distinct resource makes the usage context clear without needing a specific alternative mention.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all available diagram templates with descriptions.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. The word 'List' clearly indicates a read-only operation with no side effects, and mentioning 'with descriptions' outlines the content of the return. However, it does not specify pagination, sorting, or any limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no filler. It efficiently conveys the action, target, and output detail in under 10 words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, no-output-schema listing tool, the description is complete. It tells the agent exactly what the tool does and what the response contains (templates and descriptions), which is sufficient for the agent to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline for parameter semantics is 4. The description adds the 'all available' scope, which is relevant context for what the listing will return, though no parameter details are needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'all available diagram templates with descriptions', making the tool's purpose unambiguous. It also differentiates from sibling tools like list_providers and list_styles by specifying templates as the subject.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when the agent needs to enumerate diagram templates, but it does not explicitly state when to use this tool versus alternatives. Sibling tools are visually distinct, but no direct comparison or exclusion criteria is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0configure_provideredit_diagramgenerate_diagramget_usage_reportlist_providerslist_styleslist_templatesEach tool has a clearly distinct purpose: generation, editing, listing resources, usage reporting, and provider configuration. No two tools overlap in a way that would cause misselection.
All tool names follow a consistent verb_noun pattern in snake_case (generate_diagram, edit_diagram, list_templates, configure_provider, etc.). The use of 'list' for multiple resource types and 'get' for a report is a reasonable variation within the same structural convention.
Seven tools is well-scoped for a diagram generation service, covering creation, editing, resource discovery, configuration, and reporting without unnecessary bloat.
The core lifecycle of diagram generation and editing is covered, along with resource discovery and provider management. The main gap is the lack of tools for managing previously generated diagrams (e.g., listing or deleting outputs), but this is a minor oversight since outputs are saved as files.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Generate cloud architecture diagrams, flowcharts, and sequence diagrams.
Create and edit architecture diagrams from your AI agent; get an SVG and a live editable canvas.
Generate, edit, and export data-architecture diagrams from your AI. Column lineage, PNG in chat.
Create and edit collaborative architecture diagrams with any AI assistant using the Trident 2D DSL.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jessepike/diagram-forge'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
