What can you do with this server?

The Jangada Docs MCP server gives AI assistants direct access to the full documentation of the jangada (jangada-ai) Python library, enabling accurate code generation based on the actual API. * jangada_indice() — Retrieve the ordered index/table of contents (best starting point for navigation). * jangada_listar_docs() — List all available documentation pages with their names and titles. * jangada_ler_doc(nome, lang) — Read the full content of a specific page by name (e.g., 'rag', 'agents', 'mcp'). Supports Portuguese (pt, default) and English (en). * jangada_buscar(termo) — Search across all documentation for a term (case-insensitive), returning matching lines grouped by page — useful for finding how to accomplish a specific task.

How do I use Jangada Docs MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Jangada Docs MCP How do I use the jangada reranking feature?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Jangada Docs MCP

by nerigleston

Overview Schema Related Servers Score Discussions

Local

Jangada Docs MCP

Servidor MCP que dá ao seu assistente de IA (Claude Code, Claude Desktop, Cursor…) acesso a toda a documentação da biblioteca jangada (jangada-ai). Assim o assistente escreve código com a API atual e correta — sem inventar nomes de função, assinaturas ou parâmetros.

Feito para desenvolvedores que constroem com o jangada. É o próprio jangada sendo um servidor MCP (serve_mcp/build_mcp_app). A doc vem embutida no pacote — self-contained, sem depender de rede em runtime.

Hospedado (HTTP) — sem instalar nada

Já há uma instância pública em https://mcp.jangada.dev.br/mcp/ (note a barra final). Conecte por HTTP:

claude mcp add jangada-mcp --transport http https://mcp.jangada.dev.br/mcp/

(roda na AWS Lambda + API Gateway — passo a passo, IaC e CI/CD em DEPLOY.md.)

Prefere local/stdio (sem depender do servidor hospedado)? Veja o uvx abaixo.

Related MCP server: MCP Vue UI Kit Server

Jeito mais fácil: `uvx` (sem clonar nada)

Como o npx do Node, o uvx roda o servidor direto do GitHub — sem clonar, sem instalar manualmente. Só precisa do uv (curl -LsSf https://astral.sh/uv/install.sh | sh).

Comando que as configurações abaixo usam:

uvx --from git+https://github.com/nerigleston/jangada-docs-mcp jangada-docs-mcp

(O uvx baixa, monta e roda o pacote numa sandbox temporária a cada uso.)

Claude Code

Em um projeto específico (escopo do projeto)

Vale só naquele projeto (ideal para times — pode commitar). Crie um .mcp.json na raiz do projeto:

{
  "mcpServers": {
    "jangada-docs": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/nerigleston/jangada-docs-mcp", "jangada-docs-mcp"]
    }
  }
}

Ou pela CLI:

claude mcp add jangada-docs --scope project -- \
  uvx --from git+https://github.com/nerigleston/jangada-docs-mcp jangada-docs-mcp

Globalmente (todos os seus projetos)

Disponível em qualquer projeto seu (escopo do usuário, fica no seu PC):

claude mcp add jangada-docs --scope user -- \
  uvx --from git+https://github.com/nerigleston/jangada-docs-mcp jangada-docs-mcp

Escopos do Claude Code: project (no .mcp.json do projeto, compartilhável) · local (só você, naquele projeto) · user (global, todos os seus projetos).

Claude Desktop (global)

Settings → Developer → Edit Config (claude_desktop_config.json):

{
  "mcpServers": {
    "jangada-docs": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/nerigleston/jangada-docs-mcp", "jangada-docs-mcp"]
    }
  }
}

Reinicie o Claude Desktop.

Cursor

Global: ~/.cursor/mcp.json · Projeto: .cursor/mcp.json

Use o mesmo bloco mcpServers acima.

Alternativa sem `uv` (clonar o repo)

git clone https://github.com/nerigleston/jangada-docs-mcp
cd jangada-docs-mcp
pip install -r requirements.txt        # = jangada-ai[mcp]

Aponte a config para o python do seu ambiente + o server:

{
  "mcpServers": {
    "jangada-docs": {
      "command": "/caminho/para/python",
      "args": ["-m", "jangada_docs_mcp.server"]
    }
  }
}

Ferramentas expostas

Ferramenta	Para que serve
`jangada_indice()`	Índice/ordem das páginas. Comece aqui.
`jangada_listar_docs()`	Lista todas as páginas (nome — título).
`jangada_ler_doc(nome, lang)`	Conteúdo completo de uma página (`pt` padrão ou `en`).
`jangada_buscar(termo)`	Procura um termo em toda a doc (trechos + página).

O assistente decide sozinho quando chamar — ex.: você pede "faça um RAG com reranking" e ele consulta jangada_ler_doc("rag") antes de escrever.

Como funciona

jangada_docs_mcp/server.py registra as funções acima como ferramentas MCP via jangada_ai.serve_mcp(...) — sobre o Server low-level do protocolo MCP (não FastMCP). Transporte stdio. A doc fica em jangada_docs_mcp/docs/ (snapshot do site da lib), empacotada no wheel.

Licença

MIT — veja LICENSE.

Available Tools

4 tools

jangada_buscarA

Procura um termo (case-insensitive) em toda a documentação PT e devolve as linhas que casam, agrupadas por página. Útil para achar 'como faço X'.

ParametersJSON Schema

Name	Required	Description	Default
`termo`	Yes
`max_resultados`	No

TDQS

A4.1/5.0

Behavior4/5

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

No annotations are provided, so the description carries full burden. It discloses case-insensitivity, full-document scope, and grouping by page, which gives clear behavioral expectations for a search tool.

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 concise, using two sentences to convey purpose, behavior, and usage hint. Every sentence adds value with no redundancy.

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 simple search tool without output schema, the description covers core functionality well. Minor gaps: no explanation of the max_resultados parameter or example output format, but overall sufficient for an AI agent to understand usage.

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 input schema has no descriptions (0% coverage), and the description does not explain the parameters beyond implying 'termo' is the search term. The optional 'max_resultados' parameter is not mentioned, leaving its purpose unclear.

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 clearly states the tool searches a term (case-insensitive) in all PT documentation and returns matching lines grouped by page. It distinguishes itself from sibling tools like jangada_indice (index) and jangada_ler_doc (read doc).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a usage hint: 'Útil para achar 'como faço X'.' This provides context for when to use the tool, but does not explicitly mention when not to use it or compare with siblings.

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

jangada_indiceA

Índice da documentação do jangada: as páginas na ordem das seções (Começando, Providers, Capacidades, Confiabilidade, etc.). Comece por aqui.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.4/5.0

Behavior4/5

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

The description discloses that the tool returns an index of pages in a defined order. No annotations are provided, but the description adequately explains the behavior without contradictions.

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, concise sentence with a colon and list, front-loading the key information. Every part is meaningful and there is no waste.

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?

Given no output schema, the description adequately indicates the return type (index of pages). For a simple, parameterless tool, this is complete enough, though it could mention the format (e.g., list of titles).

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

Parameters4/5

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

There are no parameters, and the schema coverage is 100%. The description adds value by explaining the tool's purpose beyond the schema, which is sufficient.

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 clearly states it is an index of documentation pages in section order, and explicitly says 'Comece por aqui' (Start here), distinguishing it from sibling tools like search, read, and list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this is the entry point to the documentation, guiding users to start here. It does not explicitly contrast with siblings but provides clear context for when to use it.

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

jangada_ler_docB

Conteúdo completo de uma página. nome = arquivo (com ou sem .mdx), ex.: 'rag', 'mcp', 'eval', 'agents', 'structured-output'. lang: 'pt' (padrão) ou 'en'.

ParametersJSON Schema

Name	Required	Description	Default
`lang`	No
`nome`	Yes

TDQS

B3.3/5.0

Behavior2/5

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

No annotations are provided, so the description must fully disclose behavior. It only states that it returns full content but does not specify if it is read-only, authentication needs, rate limits, or side effects. The description is insufficient for an agent to understand behavioral traits.

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 concise, consisting of one sentence with embedded parameter details. It is front-loaded with the main purpose and efficiently explains parameters. However, it could be structured with clear sections for better readability.

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?

Given the tool has 2 parameters, no output schema, and sibling tools, the description covers parameter semantics well but lacks usage guidelines and behavioral details. It is adequate for simple use but not complete for an agent to reliably select and invoke the tool without extra context.

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

Parameters4/5

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

The schema has 0% description coverage, so the description must compensate. It explains that 'nome' is a file name (with/without .mdx) and provides specific examples (rag, mcp, etc.), and explains 'lang' defaults to 'pt' with 'en' option. This adds significant meaning beyond the raw schema types.

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 'Conteúdo completo de uma página' (full content of a page), indicating it retrieves full document content. It explains the parameters with examples, making the purpose clear. However, it does not explicitly differentiate from sibling tools like jangada_listar_docs or jangada_buscar, leaving room for ambiguity.

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 description provides parameter examples and default values, implying usage context. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., when to read a doc vs search or list), and no exclusions or prerequisites are mentioned.

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

jangada_listar_docsA

Lista todas as páginas de documentação (nome do arquivo — título).

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A3.9/5.0

Behavior3/5

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

No annotations are provided, so the description carries the burden. It states the tool lists all pages, but does not disclose potential behaviors like authentication requirements, rate limits, ordering, or pagination. It is adequate but lacks depth.

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 concise sentence that efficiently conveys purpose and output. No wasted words; it is front-loaded and clear.

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?

Given no output schema and no annotations, the description is minimal. It covers basic output but lacks details such as ordering, completeness guarantee, or prerequisites. Could be more complete (e.g., 'Alphabetical list of all documentation pages').

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

Parameters4/5

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

The tool has zero parameters, and the schema coverage is 100% vacuously. The description adds meaning by specifying the output format (file name — title), which is helpful context beyond the empty schema.

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 clearly states the tool lists all documentation pages and specifies the output format (name and title). It distinguishes from sibling tools like jangada_buscar (search), jangada_indice (index), and jangada_ler_doc (read specific doc).

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 description implies usage when a user wants a full list, but it does not explicitly state when to use this tool versus alternatives or provide any exclusions. Usage guidance is only implicit.

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

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Disambiguation5/5

Each tool has a distinct purpose: searching, listing index, reading a specific document, and listing all documents. There is no overlap or ambiguity.

Naming Consistency5/5

All tools follow the pattern `jangada_<action>` in snake_case (buscar, indice, ler_doc, listar_docs), with consistent formatting and clear verb/noun usage.

Tool Count5/5

Four tools is a reasonable count for a documentation server, covering search, navigation, and reading without being too few or too many.

Completeness4/5

The tool set covers essential documentation operations (search, index, read, list). A minor gap might be the absence of a tool to retrieve table of contents or metadata for a page, but core workflows are well-supported.

Maintenance

ActivityActive

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

docfork-mcp
ai.smithery
@latest documentation and code examples to 9000+ libraries for LLMs and AI code editors in a singl…
Documentation Access Developer Tools Code Analysis
2488
llmref A
org.llmref
Versioned documentation registry and semantic search for AI tools and coding assistants.
Documentation Access Search Developer Tools
42
ref-tools-ref-tools-mcp
ai.smithery
Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
Documentation Access Developer Tools Code Analysis
21,164
developer-toolkit-mcp A
io.github.mjaskolski
The documentation, as a tool your agent can call: 950+ AI-dev guides. Search + fetch tools.
AI & Machine Learning Search
21

Related MCP Servers

MCP Server for Up-to-Date
Documentation Access AI & Machine Learning Developer Tools
AmirUpSkill
F
license
A
quality
D
maintenance
Provides Large Language Models with real-time access to the latest documentation for Python libraries like Langchain, LlamaIndex, and OpenAI, enabling accurate and up-to-date code suggestions.
Updated a year ago (2025-05-04 17:43 UTC)
1
MCP Vue UI Kit Server
Developer Tools Documentation Access
TeodorDre
F
license
Not graded
quality
C
maintenance
Enables AI assistants to access documentation of Vue UI components, including props, events, and slots, for generating correct usage code.
Updated 8 months ago (2025-12-19 22:33 UTC)
7
mcp-dalamud
Documentation Access Developer Tools
MelkyWay
F
license
Not graded
quality
D
maintenance
Exposes the Dalamud plugin API documentation to AI assistants, enabling them to answer questions about services, types, and methods for writing FFXIV Dalamud plugins.
Updated 5 months ago (2026-04-12 17:53 UTC)
1
mcp-library-docs
Developer Tools Documentation Access
roznet
A
license
Not graded
quality
D
maintenance
Provides AI assistants with access to design documentation across multiple code libraries, enabling discovery of existing utilities and patterns to avoid reimplementation.
Updated 6 months ago (2026-02-27 13:29 UTC)
2
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nerigleston/jangada-docs-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

Jangada Docs MCP

Hospedado (HTTP) — sem instalar nada

Jeito mais fácil: uvx (sem clonar nada)

Claude Code

Em um projeto específico (escopo do projeto)

Globalmente (todos os seus projetos)

Claude Desktop (global)

Cursor

Alternativa sem uv (clonar o repo)

Ferramentas expostas

Como funciona

Licença

Available Tools

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

Jeito mais fácil: `uvx` (sem clonar nada)

Alternativa sem `uv` (clonar o repo)