Skip to main content
Glama
enesjakozh
glifxyz

Glif

Official
by glifxyz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Glif MCP Server and Plugin

Glif is a creative agent. Describe what you want to make, and it picks the models and does the work across images, video and audio. It also transcribes, renders HTML, searches the web, runs code and chains multi-step media jobs.

This repo holds three things:

  • A plugin for Claude, Codex, ChatGPT, Cursor, VS Code, Copilot and Gemini CLI. It connects the hosted server and bundles public skills.

  • Public Agent Skills in skills/.

  • Registry metadata for the hosted server (server.json). The server itself runs on glif.app and is not open source.

NOTE

Looking for the old locally run stdio server (npm@glifxyz/glif-mcp-server)? It's deprecated. The code is parked on the legacy-local-server branch.

Install the plugin

The plugin adds the Glif server plus the skills below. Your client opens a browser sign-in the first time it connects.

Claude Code

claude plugin marketplace add glifxyz/glif-mcp-server
claude plugin install glif@glif

In a session, /plugin marketplace add glifxyz/glif-mcp-server then /plugin install glif@glif does the same. Run /mcp to sign in.

Claude (web and desktop)

Customize → Plugins → Add marketplace, then enter glifxyz/glif-mcp-server. To add only the server, go to Settings → Connectors → Add custom connector and paste https://glif.app/api/mcp.

Codex

codex plugin marketplace add glifxyz/glif-mcp-server
codex plugin add glif@glif
codex mcp login glif

Gemini CLI

gemini extensions install https://github.com/glifxyz/glif-mcp-server

Skills only

Any agent that reads Agent Skills can install them with skills.sh:

npx skills add glifxyz/glif-mcp-server

The skills need the Glif server connected too.

Related MCP server: comfyops-mcp

Add just the server

Cursor

Add to Cursor

Or add to .cursor/mcp.json:

{ "mcpServers": { "glif": { "url": "https://glif.app/api/mcp" } } }

VS Code

code --add-mcp '{"name":"glif","type":"http","url":"https://glif.app/api/mcp"}'

ChatGPT

Turn on developer mode, then Settings → Apps & Connectors → Add new connector. Paste https://glif.app/api/mcp and pick OAuth.

Claude Code (server only)

claude mcp add --scope user --transport http glif https://glif.app/api/mcp

Any other MCP client

{ "mcpServers": { "glif": { "url": "https://glif.app/api/mcp", "transport": "http" } } }

More clients (Replit, Hermes, OpenClaw, LM Studio and others) have copy-paste snippets at https://glif.app/mcp.

Skills

Skill

Use it to

get-started

Check the connected account and credits, and learn how projects work. Never generates.

web-visuals

Make hero images, textures, illustrations, OG images and background video for a site you're building, and wire them in.

app-icons-and-logos

Design a logo or app icon, then export the favicon set, PWA, iOS and Android sizes.

app-promo-materials

Turn real app screens into App Store screenshots and launch posts, or plan and make an ad campaign or product photo set.

app-demo-videos

Record the app with Playwright, then frame it in a video template with captions, voiceover and music.

audio-and-video

Make music, voiceover, sound effects and video clips from a brief or a reference file, or edit existing media.

make-images

Make new images from a brief, such as concept art or a series in different styles, and save them to a folder.

edit-images

Remove backgrounds, erase objects, expand, upscale, retouch or restyle an existing image, saved next to the original.

game-assets

Make character sheets, sprite sheets, seamless and PBR textures, 3D models and icons for a game.

continue-project

Reopen saved work and add variations or follow-ups to it.

Skills spend credits only when you ask for media. If a visual was the agent's own idea, it asks first.

Tools

compose_project does the work. Describe what you want in plain language, including a whole series of variations. It returns a jobId and a projectUrl right away. Pass the jobId to get_job_status as job_id to follow the run and get the media links. The other tools read projects, reopen media, upload reference files and check your account. Call tools/list for the full set, or see https://glif.app/mcp.

Generation spends credits from the signed-in Glif account. Reading and browsing are free. See https://glif.app/pricing.

Develop

CI checks every manifest on each PR. To check locally:

claude plugin validate --strict .
for skill in skills/*/; do uvx --from skills-ref agentskills validate "$skill"; done

The plugin version lives in .claude-plugin/plugin.json, plugin.json and gemini-extension.json. Bump all three together; CI fails if they differ. Publish server.json to the MCP Registry by bumping its version and tagging v<version> (see publish.yml).

Links

License

MIT. See LICENSE.

Available Tools

6 tools
my_user_infoA
Read-only
Inspect

Get detailed information about your Glif account, including profile info, recent workflows, and recent runs.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, confirming no side effects. The description adds value by specifying returned data categories (profile, workflows, runs), going beyond the annotation. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single, front-loaded sentence that efficiently communicates purpose and key return categories. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and a simple read-only operation, the description adequately covers what the tool returns (profile, workflows, runs). No output schema, but the listing of categories provides sufficient context for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters in input schema (100% coverage by schema). Baseline is 4; description does not need to add parameter details. No additional semantics required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: retrieving detailed account info including profile, recent workflows, and recent runs. It distinguishes itself from siblings like my_workflows (which likely focuses on workflows alone) and search_workflows.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for getting the current user's account details, but lacks explicit guidance on when to use versus siblings (e.g., when to use my_workflows instead for workflow-only data). No when-not or alternative suggestions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

my_workflowsA
Read-only
Inspect

Get a list of your published workflows (glifs). Shows your AI workflows with run counts and creation dates.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include readOnlyHint=true, which is consistent with the description. The description adds minor behavioral context (what data is shown) but does not cover potential issues like pagination or rate limits. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no fluff. The purpose is front-loaded, and the second sentence adds relevant details. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters and no output schema, the description adequately explains what the tool returns. It could mention pagination or ordering but is largely sufficient for a simple list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no parameters, so schema coverage is 100%. The description adds value by clarifying that the list is scoped to the user's own workflows, which is not evident from the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'get a list', the resource 'your published workflows (glifs)', and specific details like 'run counts and creation dates'. It distinguishes from sibling tools such as list_featured_workflows and search_workflows.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for personal workflows but does not explicitly state when to use this tool over alternatives like list_featured_workflows or search_workflows. No when-not or alternative naming is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

run_workflowAInspect

Run a workflow (glif) with the specified ID and inputs. Workflows can generate images, text, audio, and more. Inputs can include text, URLs, or base64-encoded media.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesThe ID of the workflow (glif) to run
inputsYesArray of input values. Can be text, media URLs, or base64-encoded media (data:image/png;base64,... or data:image/jpeg;base64,...)

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate non-read-only and non-destructive behavior. The description adds that it generates media but does not disclose potential side effects, idempotency, or reliability characteristics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences, front-loading purpose and adding relevant context about output types and input formats without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description mentions potential output types but lacks details on return values, as there is no output schema. It also omits guidance on error handling or post-invocation steps, leaving gaps for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers both parameters, and the description adds value by specifying acceptable input formats (text, URLs, base64-encoded media) beyond the array-of-strings type, aiding correct usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Run' and the resource 'workflow (glif)', specifying that workflows generate various outputs. This distinguishes it from sibling tools like list_featured_workflows and search_workflows.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by stating its function but does not provide explicit guidance on when to use it versus alternatives. It lacks exclusion criteria or context about prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_workflowsA
Read-only
Inspect

Search for workflows (glifs) by name, description, or keywords. Find AI tools for image generation, text processing, and more.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query string

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include readOnlyHint: true, which is consistent. The description adds that it searches by name, description, or keywords, but no additional behavioral details beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, no unnecessary words. Efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool (one parameter, no output schema), the description adequately covers what it does and the types of results it returns. Could mention return format but not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with one parameter. The description adds context that the query can be by name, description, or keywords, which adds meaning beyond the schema's 'Search query string'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The tool name and description clearly state the action (search) and resource (workflows/glifs). It distinguishes from sibling tools like list_featured_workflows by implying a general search across all workflows.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like list_featured_workflows or my_workflows. No context on when to search vs list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

workflow_infoA
Read-only
Inspect

Get detailed information about a workflow (glif) including its input fields, recent runs, and creator info.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesThe ID of the workflow (glif) to show details for

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only (readOnlyHint: true). The description adds valuable detail about the return content (input fields, recent runs, creator info), making behavior transparent beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that is concise, front-loaded with the action, and contains no extraneous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema), the description provides sufficient context—what the tool does and what it returns—making it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers the single parameter 'id' fully (100% coverage). The description does not add additional meaning about the parameter beyond the schema, leading to baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves detailed information about a specific workflow, including inputs, runs, and creator. It distinguishes from siblings like list_featured_workflows (list) and run_workflow (execute), but does not explicitly contrast with alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus siblings such as search_workflows or my_workflows. The description only explains the tool's function without providing use-case context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 6 tool updatesv0.9.5
    • First observedlist_featured_workflows
    • First observedmy_user_info
    • First observedmy_workflows
    • First observedrun_workflow
    • First observedsearch_workflows
    • First observedworkflow_info
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 6 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: listing featured workflows, user info, personal workflows, running a workflow, searching workflows, and workflow details. No overlap or ambiguity.

Naming Consistency3/5

Naming patterns are mixed: some use verb+noun (list_featured_workflows, run_workflow, search_workflows), some use possessive+noun (my_user_info, my_workflows), and one uses noun+noun (workflow_info). This inconsistency could confuse an agent.

Tool Count5/5

6 tools is well-scoped for a workflow platform, covering essential operations without being overwhelming or too sparse.

Completeness3/5

Missing CRUD operations for workflows (create, update, delete), which are important for managing workflows. The set focuses on consumption and view only, leaving gaps for workflow creation and management.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches