Skip to main content
Glama
enesjakozh
crisschan

MCP-Repo2LLM

by crisschan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

MCP-Repo2LLM

Descripción general

mcp-repo2llm es un servidor MCP que transforma repositorios de código a formatos compatibles con LLM. Una potente herramienta que transforma repositorios de código a formatos compatibles con LLM, acortando la distancia entre las bases de código tradicionales y los modelos de lenguaje de IA modernos. Este repositorio se basa en RepoToTextForLLMs , que proporciona la funcionalidad esencial para convertir repositorios a formatos compatibles con LLM.

Related MCP server: SRC (Structured Repo Context)

Motivación

A medida que la IA y los Grandes Modelos de Lenguaje (LLM) adquieren mayor importancia en el desarrollo de software, aumenta la necesidad de comunicar eficazmente nuestras bases de código a estos modelos. Los repositorios de código tradicionales no están optimizados para el procesamiento de LLM, lo que puede generar resultados deficientes al utilizar herramientas de IA para el análisis y la generación de código.

Problema resuelto

Este proyecto aborda varios desafíos críticos:

  • Dificultad para procesar grandes bases de código con LLM

  • Pérdida de contexto y estructura al introducir código en los modelos de IA

  • Manejo ineficiente de metadatos y documentación del repositorio

  • Formato inconsistente en diferentes lenguajes de programación

Características principales

  • Escaneo inteligente de repositorios : procesa de forma inteligente bases de código completas mientras mantiene la integridad estructural

  • Preservación del contexto : mantiene información contextual importante y relaciones entre archivos de código

  • Compatibilidad con varios idiomas : maneja varios lenguajes de programación con optimizaciones específicas del lenguaje.

  • Mejora de metadatos : enriquece el código con metadatos relevantes para una mejor comprensión del LLM

  • Procesamiento eficiente : optimizado para manejar grandes repositorios con un uso mínimo de recursos

Instalación

Para instalar mcp-repo2llm mediante uv:

"mcp-repo2llm-server": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "--with-editable",
        "/mcp-repo2llm",
        "mcp",
        "run",
        "/mcp-repo2llm/mcp-repo2llm-server.py"
      ],
      "env":{
          "GITHUB_TOKEN":"your-github-token",
          "GITLAB_TOKEN":"your-gitlab-token"
      }
    }

GITHUB_TOKEN: tu token de Github GITLAB_TOKEN: tu token de Gitlab

Herramientas

obtener_repositorio_de_gitlab

  • Procesar y devolver el código de una rama del repositorio de GitLab como texto

  • Aporte:

    • repo_url (cadena): la URL del repositorio de gitlab

    • rama (cadena): el nombre de la rama, el valor predeterminado es master

  • Devuelve (cadena): toda la información y la estructura del proyecto desde el repositorio como texto.

obtener_repositorio_de_github

  • Procesar y devolver el código de una rama del repositorio de Github como texto

  • Aporte:

    • repo_url (cadena): la URL del repositorio de github

    • rama (cadena): el nombre de la rama, el valor predeterminado es master

  • Devuelve (cadena): toda la información y la estructura del proyecto desde el repositorio como texto.

obtener_repositorio_local

  • Procesar y devolver el código de una rama del repositorio de GitLab como texto

  • Aporte:

    • repo_url (cadena): la ruta del repositorio

  • Devuelve (cadena): toda la información y la estructura del proyecto desde el repositorio como texto.

Available Tools

3 tools
get_github_repoC

Process and return the code from a GitHub repository branch as text

ParametersJSON Schema
NameRequiredDescriptionDefault
repo_urlYes
branchNomaster

TDQS

C2.8/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions processing and returning code as text, which implies a read-only operation, but lacks details on permissions, rate limits, error handling, or what 'process' entails (e.g., formatting, filtering). This is a significant gap for a tool with potential complexity.

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 a single, efficient sentence with zero waste. It's front-loaded and appropriately sized for the tool's apparent simplicity, making it easy to parse quickly.

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

Completeness2/5

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

Given no annotations, 0% schema coverage, no output schema, and two parameters, the description is incomplete. It doesn't explain return values, error cases, or behavioral nuances, making it inadequate for an AI agent to use the tool confidently without additional context.

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

Parameters2/5

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

Schema description coverage is 0%, so the schema provides no parameter details. The description mentions 'GitHub repository branch' but doesn't explain the 'repo_url' or 'branch' parameters beyond what's obvious from the names. It fails to add meaningful semantics, such as URL format or branch defaults, leaving parameters poorly documented.

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 the action ('process and return') and resource ('code from a GitHub repository branch'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'get_gitlab_repo' or 'get_local_repo' beyond specifying GitHub, which is somewhat implied by the tool name. This prevents a perfect score.

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 'get_gitlab_repo' or 'get_local_repo', nor does it mention any prerequisites or exclusions. It only states what it does, leaving usage context entirely to inference.

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

get_gitlab_repoC

Process and return the code from a GitLab repository branch as text

ParametersJSON Schema
NameRequiredDescriptionDefault
repo_urlYes
branchNomaster

TDQS

C2.4/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'process and return... as text', which implies a read operation, but fails to detail critical aspects such as authentication requirements, rate limits, error handling, or what 'process' entails (e.g., formatting, filtering). This leaves significant gaps in understanding the tool's behavior.

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

Conciseness4/5

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

The description is a single, straightforward sentence that efficiently conveys the core action and output. It is front-loaded with the main purpose and avoids unnecessary elaboration, making it easy to parse quickly. However, it could be slightly more structured to include key details without sacrificing brevity.

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

Completeness2/5

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

Given the tool's complexity (involves external GitLab access), lack of annotations, 0% schema description coverage, and no output schema, the description is insufficient. It omits essential context such as authentication, error cases, return format details beyond 'as text', and how it differs from siblings, making it incomplete for reliable agent use.

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

Parameters2/5

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

The schema description coverage is 0%, meaning parameters are undocumented in the schema. The description does not explain the parameters (repo_url, branch) beyond what's implied by the tool name and context. It adds no semantic details about parameter formats, constraints, or usage, failing to compensate for the lack of schema documentation.

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

Purpose3/5

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

The description states the tool 'Process and return the code from a GitLab repository branch as text', which provides a clear verb ('process and return') and resource ('code from a GitLab repository branch'). However, it doesn't explicitly distinguish this from its sibling tools (get_github_repo, get_local_repo) beyond mentioning 'GitLab', leaving some ambiguity about when to choose this specific tool over 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?

The description offers no guidance on when to use this tool versus its siblings (get_github_repo, get_local_repo) or any other alternatives. It simply states what the tool does without indicating specific contexts, prerequisites, or exclusions, which limits its utility for an AI agent making selection decisions.

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

get_local_repoC

Process and return the code from a local repository as text

ParametersJSON Schema
NameRequiredDescriptionDefault
repo_pathYes

TDQS

C2.8/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'Process and return' but doesn't specify what processing entails (e.g., formatting, filtering, or error handling), the return format details, or any constraints like file size limits or authentication needs. This leaves significant gaps in understanding the tool's behavior.

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 extremely concise with a single sentence that directly states the tool's purpose. It is front-loaded and wastes no words, making it easy to parse quickly without unnecessary detail.

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

Completeness2/5

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

Given the tool's complexity (processing and returning code), lack of annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't explain what 'Process' involves, the return format, error conditions, or how it differs from sibling tools, making it inadequate for an AI agent to use effectively without guesswork.

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

Parameters2/5

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

The schema description coverage is 0%, with one parameter (repo_path) undocumented in the schema. The description adds no information about this parameter, such as what 'repo_path' should be (e.g., a file system path, relative or absolute) or any examples. It fails to compensate for the low schema coverage, leaving the parameter meaning unclear.

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 the action ('Process and return') and resource ('code from a local repository as text'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like get_github_repo or get_gitlab_repo, which likely handle remote repositories instead of local ones.

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 offers no guidance on when to use this tool versus its siblings (get_github_repo, get_gitlab_repo) or any alternatives. It lacks context about prerequisites, such as needing a valid local repository path, and doesn't mention exclusions or specific use cases.

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. 3 tool updates
    • First observedget_github_repo
    • First observedget_gitlab_repo
    • First observedget_local_repo
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

C2.9/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose targeting a different repository source: GitHub, GitLab, and local repositories. The descriptions explicitly differentiate them by source, leaving no ambiguity about which tool to use for each scenario.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with 'get_' prefix and descriptive suffixes indicating the repository source. The naming is uniform and predictable across all three tools.

Tool Count2/5

With only 3 tools, the server feels thin for its apparent scope of repository code retrieval. While it covers three repository sources, the functionality is limited to a single 'get' operation without supporting related actions like searching, filtering, or managing repositories.

Completeness2/5

The tool surface is severely incomplete for repository interaction. It only provides retrieval operations without any create, update, delete, search, or management capabilities. Even within retrieval, there are no options for filtering, pagination, or handling different file types beyond returning 'code as text'.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches