Skip to main content
Glama
deenesjakoruzh
chelslava

ContextTree MCP

by chelslava
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

ContextTree MCP 🌳

Búsqueda semántica profunda de código para asistentes de IA — impulsada por análisis de AST y embeddings locales. 100 % offline.

Python License: MIT MCP README (RU)

ContextTree MCP es un servidor local de Model Context Protocol que proporciona a tu asistente de codificación una comprensión estructural de la base de código. Combina dos mundos:

  • tree-sitter analiza los archivos fuente en un AST y extrae bloques lógicos —funciones, métodos, firmas de clases con docstrings—.

  • sentence-transformers (all-MiniLM-L6-v2) incrusta cada bloque —enriquecido con la ruta del archivo, la clase contenedora, el nombre del método y el docstring— en un almacén vectorial local de ChromaDB.

El resultado: tu asistente encuentra código por significado, no solo por palabras clave, y cada resultado de búsqueda llega con la ruta exacta del archivo y los números de línea.

🔒 La privacidad es lo primero. Todo se ejecuta en tu máquina: análisis sintáctico, modelo de embeddings e índice vectorial. Sin llamadas a la nube, sin telemetría; el código nunca sale del disco en el que reside.

¿Por qué no usar una búsqueda de texto plano?

grep y la búsqueda de texto completo buscan cadenas coincidentes. Fallan justo donde más se necesita ayuda:

Tarea

Búsqueda de texto

ContextTree MCP

"¿Dónde validamos los tokens JWT?"

❌ requiere adivinar la palabra exacta

✅ encuentra AuthService.verify_token() aunque «validar» no aparezca nunca en el código

Encontrar un método cuyo nombre fue refactorizado

❌ se rompe por el renombrado

✅ el docstring y el contexto circundante siguen transmitiendo el significado

Distinguir definición frente a uso

❌ imposible sin malabares con regex

✅ separación a nivel del AST entre declaraciones y lugares de llamada

Devolver ubicaciones precisas

⚠️ solo la línea coincidente

✅ metadatos ⏰ file, class, method, start_line, end_line

Ignorar el ruido de comentarios, cadenas e imports

❌

✅ solo se indexan unidades lógicas reales

Related MCP server: Paparats MCP

Características

  • 🌲 Fragmentación consciente del AST — indexa funciones, métodos y firmas de clases mediante tree-sitter, no a través de ventanas arbitrarias de texto.

  • 🧩 Bloques lógicos enriquecidos con contexto — cada documento indexado contiene su ruta de archivo, clase propietaria, nombre de método, docstring y cuerpo, de modo que consultas como "lógica de reintento de pago" den con el método correcto.

  • ⚡ Indexación incremental — hashes SHA-256 de contenido por archivo; solo se reprocesan los archivos modificados, nuevos o eliminados.

  • 🔍 Búsqueda semántica — consulta de lengua natural → fragmentos de código clasificados con intervalos de línea exactos.

  • 📞 Localización de usos AST — encuentra los lugares reales de llamada o instanciación de una función o clase, filtrando falsos positivos como cadenas explicativas o comentarios.

  • 🗄️ Índice local persistente — ChromaDB guarda en .chroma/, sobrevive a reinicios y nunca se envía al repositorio Git.

  • 🔌 Transporto MCP de stdio — compatible con Claude Desktop, OpenCode, Cursor, Cline o cualquier cliente a aceptar MCP.

Pila tecnológica

Capa

Tecnología

Lenguaje

Python 3.12+

Protocolo

SDK oficial de mcp (transporte stdio)

Análisis AST

tree-sitter junto a enlaces para Python, TypeScript, JavaScript

Base de datos vectorial

chromadb (modo local persistente)

Embeddings

sentence-transformers · all-MiniLM-L6-v2

Instalación

Se requiere Python 3.12+. Se recomienda uv como gestor de paquetes rápido y moderno:

git clone https://github.com/<your-org>/mcp-context-tree.git
cd mcp-context-tree

# Option A — uv (recommended): resolves dependencies from pyproject.toml, locks uv.lock
uv sync

# Option B — classic pip + venv
python -m venv venv && source venv/bin/activate   # Windows: venv\Scripts\activate
pip install -r requirements.txt

💡 La primera vez en ejecución descarga el modelo de embeddings (~90 MB). PyTorch se instala como dependencia de sentence-transformers; la versión CPU es suficiente — no se necesita GPU.

Alta en un cliente MCP

Ejemplo de configuración (Claude Desktop / cualquier cliente compatible con servidores stdio):

{
  "mcpServers": {
    "context-tree": {
      "command": "<path-to-venv>/bin/python",
      "args": ["-m", "context_tree"],
      "env": {}
    }
  }
}

(En Windows usa <ruta-al-venv>\Scripts\python.exe).

Herramientas expuestas a la IA

Herramienta

Función

Descripción

index_workspace

(directory_path: str)

Recorre el proyecto, detecta archivos cambiados mediante hash y actualiza de forma incremental la colección de ChromaDB.

semantic_search

(query: str, limit: int = 5)

Búsqueda del lenguaje natural en el código indexado. Devuelve fragmentos enriquecidos con file, class, start_line, end_line.

find_ast_usages

(symbol_name: str)

Consulta basada en AST de los lugares reales de llamada e instanciación de una función o clase.

Proceso de uso típico:

1. index_workspace("D:/projects/my-app")
2. semantic_search("where do we handle payment retries", limit=8)
3. find_ast_usages("PaymentGateway.retry")

Lenguajes compatibles

Lenguaje

Estado

Python

✅ soportado desde el lanzamiento

TypeScript / TSX

✅ soportado desde el lanzamiento

JavaScript / JSX

✅ soportado desde el lanzamiento

Go, Java, Rust...

🗺️ en mapa de ruta — el registro de analizadores está diseñado para extenderse

Documentación

  • 🏛️ ARCHITECTURE.md — estructura del proyecto, esquema de datos de ChromaDB, lógica de extracción de AST y diseño de indexación incremental.

  • 🇷🇺 README.ru.md — documentación en ruso.

Hoja de ruta

  • Modo watch: reindexado automático al cambiar archivos (fs watcher)

  • Más lenguajes mediante enlaces tree-sitter

  • Búsqueda híbrida (BM25 + rerank de vectores)

  • Clasificación con grafo de llamadas (“¿quién llama esto?”)

  • Publicación en PyPI (context-tree-mcp)

Contribuciones

Las incidencias y las PRs son bienvenidas. Por favor, mantén los cambios coherentes con ARCHITECTURE.md.

Licencia

MIT — consulta LICENSE.

Available Tools

4 tools
find_ast_usagesA

AST-based lookup of real call sites / instantiations of a function or class. Filters out string literals, comments, and non-call occurrences.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNo
symbol_nameYes
directory_pathNo.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full behavioral burden. It does disclose a valuable filtering behavior: "Filters out string literals, comments, and non-call occurrences." However, it does not mention whether indexing is required, how missing symbols are handled, or any result behavior beyond being AST-based.

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 focused sentence that communicates the mechanism, target resource, and exclusion behavior without redundancy. Every clause adds useful information.

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 tool is simple enough that the core lookup behavior is adequately described, and an output schema exists. The main gaps are the lack of usage guidance around semantic_search/index_workspace and the absence of practical details about scoping and limit behavior, which leaves the description merely adequate rather than complete.

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 has 0% description coverage, so the description should compensate. It adds meaning for symbol_name by stating it refers to "a function or class," but it gives no guidance on directory_path or limit, such as how the directory is searched or what the limit controls. This leaves non-obvious semantics undocumented.

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 uses a specific verb plus precise resource: "AST-based lookup of real call sites / instantiations of a function or class." It also clarifies what is excluded, which distinguishes it from string or semantic search. This is far more informative than the bare tool name.

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 AST-based wording implicitly indicates this is for exact code-structure matching rather than fuzzy search, and the sibling tools suggest a semantic-search alternative. However, the description does not explicitly state when to use this tool versus semantic_search or index_workspace, nor does it mention any exclusions or preconditions.

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

go_to_definitionA

Finds the exact definition/declaration location of a symbol (function, method, class, struct, trait, interface) across workspace files.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNo
symbol_nameYes
directory_pathNo.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.5/5.0
Behavior3/5

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 adds meaningful context by stating the search is workspace-wide and targets exact definition/declaration locations. Still, it leaves important behavioral details undisclosed, such as whether an index must exist first, how missing or ambiguous symbols are handled, and whether the operation is purely read-only.

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, front-loaded sentence with no filler or redundant restatement of the tool name. It conveys the core action, target, and scope efficiently while listing relevant symbol categories without over-elaborating.

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?

Although an output schema exists and the basic action is clear, the description lacks usage guidance relative to its three sibling tools and fails to explain two of three parameters. With no annotations, this is too thin to fully support an agent in choosing and invoking the tool correctly across realistic scenarios.

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 description must compensate for bare parameter schemas. It partially clarifies symbol_name by listing supported symbol types, but it says nothing about the format of symbol_name (e.g., fully qualified vs simple name, case sensitivity). The limit and directory_path parameters are completely unaddressed in the description, leaving their semantics to inference from the schema titles and defaults.

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 uses a specific verb ('Finds') with a precise resource: the exact definition/declaration location of symbols, listing supported symbol categories and clarifying the search scope ('across workspace files'). This clearly distinguishes it from sibling tools like find_ast_usages or semantic_search, which target usages or semantically similar matches rather than exact definitions.

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 phrasing 'exact definition/declaration location' implies the tool is appropriate when precise definitions are needed, rather than usages or semantic matches. However, it does not explicitly state when to prefer this tool over semantic_search or find_ast_usages, nor does it mention any exclusions or prerequisites such as requiring an indexed workspace.

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

index_workspaceA

Walks the project, detects changed files by SHA-256 hash, and incrementally updates the persistent local ChromaDB vector store.

ParametersJSON Schema
NameRequiredDescriptionDefault
directory_pathNo.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.9/5.0
Behavior4/5

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 covers that the operation walks the project, uses SHA-256 hashing for change detection, and mutates a persistent local ChromaDB store. This is meaningful behavioral context beyond 'index workspace' though it does not mention potential costs, permissions, or failure modes.

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?

A single sentence with no filler. It front-loads the core action and packs in the hashing, incrementality, and storage target without becoming verbose.

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?

For a tool with one optional parameter and an output schema, the description covers the essential behavior: what is walked, how changes are detected, and what is updated. It is reasonably complete, though it could add an explicit note about running after source changes or before semantic_search.

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?

There is only one parameter and schema description coverage is 0%, so the description needs to clarify the parameter's meaning. It never mentions directory_path or the default of '.', forcing the agent to rely on the schema's 'Directory Path' title and default value. The description does not compensate for the low schema coverage.

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 names a specific action sequence ('Walks the project', 'detects changed files', 'updates the vector store') and a concrete resource ('persistent local ChromaDB vector store'). It is clearly distinct from the sibling tools semantic_search and find_ast_usages, which do search and AST lookup rather than indexing.

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 phrase 'incrementally updates' and 'detects changed files' implies the tool is meant to keep the index fresh after edits, but the description never explicitly says when to run it relative to semantic_search or find_ast_usages. It also does not mention exclusions or alternatives.

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. 2 tool updatesv0.4.0
    • Addedgo_to_definition
    • Changedsemantic_search2 fields changed
      • addedInput schema / properties / mode
        Added value: +{
+  "default": "hybrid",
+  "enum": [
+    "hybrid",
+    "semantic",
+    "keyword"
+  ],
+  "title": "Mode",
+  "type": "string"
+}
      • addedInput schema / properties / rerank
        Added value: +{
+  "default": false,
+  "title": "Rerank",
+  "type": "boolean"
+}
  2. 3 tool updatesv0.1.0
    • First observedfind_ast_usages
    • First observedindex_workspace
    • First observedsemantic_search
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 4 tools

Disambiguation5/5

Each tool targets a distinct part of code navigation: semantic search vs. exact definitions vs. AST usages vs. index maintenance. There is no realistic confusion between their purposes.

Naming Consistency4/5

Three of four tools use imperative verb-first names (find_ast_usages, index_workspace, go_to_definition), and all are snake_case. semantic_search breaks the pattern slightly by starting with an adjective instead of a verb, but the naming remains readable and predictable.

Tool Count5/5

With 4 tools, the server is well-scoped and each tool earns its place in the code indexing/search/navigation workflow. There is no redundancy or bloat.

Completeness4/5

The core lifecycle is covered: index the workspace, search semantically, go to definitions, and find AST usages. Minor gaps such as no explicit index status or reset operation prevent a perfect score, but agents can work around them.

Maintenance

ActivitySlowing
ResponsivenessResponsive

Resources

Related MCP Connectors

Related MCP Servers

  • CodeGrok MCP

    dondetir
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables semantic code search for AI assistants by indexing codebases with embeddings and Tree-sitter, returning relevant snippets via natural language queries.
    15
    MIT

  • Paparats MCP

    IBazylchuk
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides AI coding assistants with deep, semantic understanding of local codebases via AST-aware chunking, cross-repo symbol graphs, and architectural memory, enabling context-aware code search and dependency tracing.
    11
    MIT

  • smart-coding-mcp

    amalikn
    A
    license
    A
    quality
    D
    maintenance
    Enables AI assistants to perform intelligent semantic code search across codebases using local AI embeddings for meaning-based retrieval.
    6
    35 npm
    MIT