Inglés | 中文
Convierte tu clave de API de SJTU Zhiyuan No.1 en algo que realmente puedas usar en Claude Code y Codex.
SJTU MCP envuelve la API de modelos alojada en SJTU como un servidor MCP local, para que puedas llamar a estos modelos directamente desde tu flujo de trabajo de agente normal en lugar de escribir scripts de integración manualmente una y otra vez.
¿Ya has solicitado una clave de API de SJTU Zhiyuan No.1, pero aún te resulta difícil usarla en la práctica?
Este proyecto existe para resolver exactamente ese problema:
ya tienes acceso a la API
quieres usarla desde Claude Code o Codex
pero el endpoint de SJTU en sí no se conecta directamente a estas herramientas de agente de forma inmediata
no quieres reescribir la capa de integración cada vez
Related MCP server: Claude-LMStudio-Bridge
Compatible con Claude Code
Compatible con Codex
Compatible con tareas de texto y visión
Utiliza el endpoint de SJTU compatible con OpenAI
Se adapta de forma natural a los flujos de trabajo MCP existentes
Para la mayoría de los usuarios, el camino más sencillo es:
git clone este repositorio
cd al directorio del proyecto
instalarlo una vez
añadirlo como un servidor MCP global en Claude Code o Codex
git clone https://github.com/EternalWavee/sjtu-mcp.git
cd sjtu-mcp
pip install -e .Después de la instalación, tu cliente MCP puede iniciar el servidor automáticamente cuando sea necesario. En el uso normal, no necesitas ejecutar manualmente el comando del servidor cada vez.
Requeridas:
SJTU_API_KEY
Opcionales:
SJTU_API_BASE_URL
SJTU_DEFAULT_TEXT_MODEL
SJTU_DEFAULT_REASONING_MODEL
SJTU_DEFAULT_VISION_MODEL
SJTU_REQUEST_TIMEOUT
Cómo usarlas:
.env.example es solo una plantilla que muestra qué variables necesitas
en el uso real, coloca estos valores en el bloque env de tu configuración de MCP
Usa esto si quieres que sjtu esté disponible en todos tus proyectos de Claude Code en esta máquina.
claude mcp add sjtu --scope user -- python -m sjtu_mcp.serverLuego:
abre ~/.claude.json
busca la entrada sjtu
copia la sección env de examples/claude-project.mcp.json
reemplaza your-api-key con tu clave real
Verificar:
claude mcp listUsa esto si quieres confirmar una configuración compartida en el repositorio para tus compañeros de equipo.
Cómo usarlo:
copia examples/claude-project.mcp.json en la raíz de tu proyecto como .mcp.json
reemplaza your-api-key con tu clave real
ajusta los modelos predeterminados y el tiempo de espera si es necesario
Ejemplo para Windows / macOS:
{
"mcpServers": {
"sjtu": {
"command": "python",
"args": ["-m", "sjtu_mcp.server"],
"env": {
"SJTU_API_BASE_URL": "https://models.sjtu.edu.cn/api/v1",
"SJTU_API_KEY": "your-api-key",
"SJTU_DEFAULT_TEXT_MODEL": "deepseek-chat",
"SJTU_DEFAULT_REASONING_MODEL": "deepseek-reasoner",
"SJTU_DEFAULT_VISION_MODEL": "qwen3vl",
"SJTU_REQUEST_TIMEOUT": "180"
}
}
}
}Usa esto si solo quieres el servidor para el proyecto actual y no quieres confirmar la configuración.
claude mcp add sjtu --scope local -- python -m sjtu_mcp.serverLuego añade los mismos valores env a la entrada de configuración de MCP correspondiente.
Usa esto si quieres que sjtu esté disponible en todos tus proyectos de Codex en esta máquina.
codex mcp add sjtu -- python -m sjtu_mcp.serverLuego:
abre tu propio ~/.codex/config.toml
copia el contenido de examples/codex-config.toml
reemplaza your-api-key con tu clave real
guarda y recarga Codex o recarga MCP
Verificar:
codex mcp listSi ya gestionas ~/.codex/config.toml directamente, puedes usar esta plantilla:
[mcp_servers.sjtu]
command = "python"
args = ["-m", "sjtu_mcp.server"]
[mcp_servers.sjtu.env]
SJTU_API_BASE_URL = "https://models.sjtu.edu.cn/api/v1"
SJTU_API_KEY = "your-api-key"
SJTU_DEFAULT_TEXT_MODEL = "deepseek-chat"
SJTU_DEFAULT_REASONING_MODEL = "deepseek-reasoner"
SJTU_DEFAULT_VISION_MODEL = "qwen3vl"
SJTU_REQUEST_TIMEOUT = "180"sjtu_models
sjtu_text
sjtu_vision
sjtu_cheap_task
请调用 sjtu_vision 分析图片里面的内容 .assets/test.png
deepseek-chat
predeterminado para resúmenes, reescrituras, limpieza y tareas de texto de bajo riesgo
minimax o glm-5
útil para reescritura ligera, clasificación o extracción
deepseek-reasoner
mejor para tareas que realmente necesitan razonamiento de varios pasos
qwen3vl
un punto de partida sólido para capturas de pantalla, extracción estilo OCR y comprensión de imágenes
qwen3coder
útil para tareas de utilidad relacionadas con el código
Este servidor asume actualmente que el endpoint de SJTU admite /models y /chat/completions compatibles con OpenAI.
Las imágenes locales se codifican como URLs de datos antes de enviarse.
Si tu endpoint del campus tiene peculiaridades específicas del modelo, extiende el enrutamiento en src/sjtu_mcp/server.py.
Route common low-risk jobs like summarize, rewrite, classify, and extract.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | ||
| content | Yes | ||
| image_path | No | ||
| image_url | No | ||
| model | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only says 'low-risk jobs,' which hints at safety but does not disclose actual behavioral traits like idempotency, side effects, or permission requirements.
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 sentence, concise but lacking structure. It is front-loaded with the main purpose, but does not expand on important details, making it minimally adequate.
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 5 parameters with no descriptions and no annotations, the description is incomplete. It does not specify valid task types, content format, or how image path/url are used, which is insufficient for correct invocation.
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%, and the description adds no meaning to any of the 5 parameters (task, content, image_path, etc.). It fails to explain valid values or parameter purposes beyond what the schema already shows.
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 routes common low-risk jobs like summarize, rewrite, classify, and extract, giving a specific verb and resource. It distinguishes from sibling tools by implying a generic task router, though it could be more precise.
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?
No explicit guidance on when to use this tool versus alternatives. The description only lists example jobs, lacking when-not-to-use or comparisons with siblings like sjtu_text or sjtu_vision.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List available models from the SJTU endpoint.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only states the action (list) but does not explain that it is a read-only operation, any potential side effects, or required permissions. The agent has no additional context beyond the basic purpose.
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 unnecessary words. It conveys the core functionality efficiently.
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 has no parameters, the description is somewhat adequate but lacks usage context. It does not explain how the output schema relates to usage or provide hints for integration with sibling tools. The presence of an output schema mitigates the need for return value details, but the description could be more helpful by mentioning use cases.
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 no parameters, so schema coverage is trivially 100%. The description adds no parameter info, which is acceptable as there is nothing to describe. Baseline 4 for zero parameters is appropriate.
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), resource (available models), and source (SJTU endpoint). It effectively differentiates from sibling tools like sjtu_cheap_task, sjtu_text, and sjtu_vision, which target different operations.
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?
No guidance provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or conditions for using sjtu_models.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a plain text task against the SJTU OpenAI-compatible API.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| model | No | ||
| system_prompt | No | ||
| temperature | No | ||
| max_tokens | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as idempotency, side effects, rate limits, or cost. The tool's safety profile (read vs. write) is unclear.
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 sentence but lacks necessary detail. It is under-specified rather than appropriately concise.
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 5 parameters, no annotations, and an output schema not described, the description fails to provide a complete picture. The tool's return value and parameter usage are left unspecified.
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%, and the description adds no meaning beyond the parameter names. It does not explain the role of model, system_prompt, temperature, or max_tokens.
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 states the verb 'run' and resource 'plain text task' against a specific API. It distinguishes from vision tasks but does not clarify what 'plain text task' entails compared to the sibling sjtu_cheap_task.
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?
No guidance on when to use this tool versus alternatives like sjtu_cheap_task or sjtu_vision. No context on cost, speed, or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run an image understanding task against the default vision model.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| image_path | No | ||
| image_url | No | ||
| model | No | ||
| system_prompt | No | ||
| temperature | No | ||
| max_tokens | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It only states that the tool runs an image understanding task, but does not explain side effects, authentication needs, return type, or limitations. The minimal description is insufficient for safe usage.
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 short sentence with no extraneous content. However, it sacrifices clarity for brevity; it could be more informative without adding much length.
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 7 parameters, no annotations, and an existing but undescribed output schema, the description is too minimal. It does not explain parameter interplay (e.g., image_path vs image_url) or output format, leaving significant gaps for effective invocation.
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 must compensate. It adds no explanation for parameters such as prompt, image_path, image_url, model, system_prompt, temperature, or max_tokens, leaving their semantics entirely to interpretation from 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 states 'Run an image understanding task against the default vision model', which clearly indicates a verb and resource. However, 'image understanding task' is vague and does not specify the exact capability (e.g., captioning, VQA), and it fails to distinguish from sibling tools like sjtu_cheap_task or sjtu_text.
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?
There is no guidance on when to use this tool over alternatives like sjtu_cheap_task or sjtu_text. No prerequisites or exclusions are mentioned, leaving the agent to guess appropriate contexts.
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.
v0.1.1sjtu_cheap_tasksjtu_modelssjtu_textsjtu_visionScored across 4 tools
sjtu_cheap_task and sjtu_text both handle text tasks, creating potential confusion. sjtu_cheap_task specifies common low-risk jobs, but the boundary with sjtu_text is unclear. sjtu_models and sjtu_vision are distinct.
All tools share the consistent 'sjtu_' prefix and snake_case naming, but the pattern varies between adjective_noun (sjtu_cheap_task) and noun-only (sjtu_models, sjtu_text, sjtu_vision), which is mostly consistent with minor deviations.
Four tools is well-scoped for the SJTU endpoint, covering essential capabilities (listing models, text, vision, and a cheap task option) without unnecessary bloat.
The set covers core functionalities, but the overlap between sjtu_cheap_task and sjtu_text suggests redundancy; missing streaming or embeddings are minor gaps for basic use.
MCP server for GLM chat completions using Zhipu AI models via AceDataCloud
Synap (pool.linkrra.com/v1), Linkrra's OpenAI-compatible LLM API, as an MCP server.
MCP server for AI dialogue using various LLM models via AceDataCloud
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
