Llm MCP Server

A TypeScript MCP server that gives text-only LLMs image understanding through StepFun vision models.

Local serverstdioTypeScript

What is the Llm MCP server?

A TypeScript MCP server that gives text-only LLMs image understanding through StepFun vision models. That is what the llm mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

Getting it running

Installation goes through your MCP client rather than a global install: point it at After on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

The tools it exposes

The server publishes 7 tools. What each one is for:

  • analyze_image — general image understanding
  • extract_text_from_image — OCR for screenshots, logs, documents, code, and UI text
  • diagnose_error_screenshot — error screenshot and stack trace diagnosis
  • understand_technical_diagram — architecture, flowchart, UML, ER, sequence, and network diagrams
  • analyze_data_visualization — charts, tables, dashboards, and metrics screenshots
  • ui_to_artifact — UI screenshot to implementation notes or design specs
  • ui_diff_check — expected vs actual UI screenshot comparison

What it needs from you

Configuration is passed through the environment: STEPFUN_API_KEY, STEPFUN_API_MODE, STEPFUN_DEFAULT_DETAIL, STEPFUN_BASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Llm's toolset — analyze_image, extract_text_from_image, diagnose_error_screenshot and 4 more — is a fair guide to whether it matches your workflow. It is maintained by rowan719; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
analyze_imagegeneral image understanding
extract_text_from_imageOCR for screenshots, logs, documents, code, and UI text
diagnose_error_screenshoterror screenshot and stack trace diagnosis
understand_technical_diagramarchitecture, flowchart, UML, ER, sequence, and network diagrams
analyze_data_visualizationcharts, tables, dashboards, and metrics screenshots
ui_to_artifactUI screenshot to implementation notes or design specs
ui_diff_checkexpected vs actual UI screenshot comparison

How to install the Llm MCP server

npm package example after publishing:

```json
{
  "mcpServers": {
    "llm-vision-mcp": {
      "command": "npx",
      "args": ["-y", "llm-vision-mcp"],
      "env": {
        "STEPFUN_API_KEY": "your_stepfun_api_key",
        "STEPFUN_API_MODE": "step_plan",
        "STEPFUN_DEFAULT_DETAIL": "high"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
STEPFUN_API_KEYCredential the server authenticates with.Yes
STEPFUN_API_MODEConfiguration value read at startup.Optional
STEPFUN_DEFAULT_DETAILConfiguration value read at startup.Optional
STEPFUN_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Llm to analyze image.
  • Use Llm to extract text from image.
  • Use Llm to diagnose error screenshot.

Frequently asked questions

It connects Llm to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (analyze_image, extract_text_from_image, diagnose_error_screenshot, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Llm directly.