github / github/app

Dynamic MCP Tool Loading to Reduce Context Window Consumption

Abierto
#1,398 3 comentarios 4 reacciones 0 asignados Ver en GitHub
Requests and ideas
Lenguaje dominante
Sin datos de lenguaje
Estrellas
2.1k
Forks
153
Métricas de merge de PR
Sin PR fusionados en 30 d

Descripción

### Feature summary

Currently, all MCP tool definitions from all connected servers are included in the context window on every turn, regardless of whether they are relevant to the current task

### What problem are you trying to solve?

---

### Problem

All MCP tool definitions from all connected servers are included in the context window on every turn, regardless of whether they are relevant to the current task. In environments with multiple MCP servers, this can result in **hundreds of tool schemas consuming tens of thousands of tokens** before any conversation content is processed.

This means:
- Significantly reduced capacity for actual code, diffs, file content, and conversation history
- Earlier context truncation in long sessions
- Wasted tokens on tools that will never be invoked in a given session
- Degraded quality on complex tasks that need deep context

---

### Proposed solution

### Proposed Solution

Provide mechanisms to selectively load/unload MCP tools to minimize context window usage:

1. **Per-session tool profiles** — Allow users to define named profiles (e.g., "code-review", "incident-triage", "deployment") that only load relevant MCP servers/tools.

2. **Lazy/on-demand tool loading** — Only include a tool's full schema in context when it's first needed. Use a lightweight tool registry (name + one-line description) for discovery, expanding the full schema only when invoked.

3. **Session-scoped enable/disable** — A command to toggle MCP servers on/off mid-session without restarting.

4. **Task-based auto-selection** — Intelligently infer which MCP servers are relevant based on the user's first message and only load those.

5. **Tool grouping within servers** — Allow disabling subsets of a server's tools rather than all-or-nothing per server.

### Impact

- Frees significant context capacity for actual work content
- Improves response quality on context-heavy tasks (large code reviews, multi-file changes)
- Reduces latency (fewer tokens to process per turn)
- Better user control over their tool environment

### Workflow impact

_No response_

### Installation context

_No response_

### Additional context

_No response_

Guía de contribución

Abrir la guía de contribución

Línea de trabajo

El issue no nombra archivos, pruebas ni puntos de entrada. Empieza localizando el registro existente de herramientas MCP y el ensamblado del contexto; después, limita la propuesta a un mecanismo con criterios de aceptación explícitos para el uso de la ventana de contexto y el comportamiento de la sesión.

Escrito por el modelo de indexación a partir del texto del issue.

Evaluación

Área
ai, desktop
Tipo de issue
Nueva funcionalidad
Dificultad
5/5
Tiempo estimado
Más de una semana
Estado de actividad
Activo
Claridad
Necesita aclaración
Aptitud para principiantes
30/100

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.