# EasyJur

> Wrapper for the official EasyJur API (legal practice management): cases (with parties, claims, finan

- name: io.github.mcp-dir/easyjur-mcp
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 91/100
- quality: 80/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.mcp-dir%2Feasyjur-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.mcp-dir%2Feasyjur-mcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "easyjur-mcp": {
      "type": "http",
      "url": "https://api.mcp.ai/p_easyjur"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-98% ~updated-59d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 80/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- warn `tools.descriptions`: 2 of 47 tools have a description under 20 characters
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 47 of 47 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 7,069 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 94 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 47, about 7,069 tokens to load them all
- tool set hash: 54421780ad8ffa483a4c8374affa4f8f
- tools last changed: 2026-10-06T14:28:04.364Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.mcp-dir/easyjur-mcp.svg)](https://protogrid.dev/servers/io.github.mcp-dir/easyjur-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-06 `authenticate` added
  - MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.
- 2026-10-06 `marketplace` added
  - The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.
- 2026-10-06 `toolkit_info` added
  - Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
- 2026-10-06 `connect` added
  - Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
- 2026-10-06 `report_bug` added
  - Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
- 2026-10-06 `show_version` added
  - Show the current MCP platform and adapter versions.
- 2026-10-06 `easyjur_get_user` added
  - Busca um usuário por ID. Bulk support: accepts user_ids for batched execution.
- 2026-10-06 `easyjur_list_users` added
  - Lista usuários do escritório.
- 2026-10-06 `easyjur_get_grupo` added
  - Busca um grupo por ID. Bulk support: accepts grupo_ids for batched execution.
- 2026-10-06 `easyjur_list_grupos` added
  - Lista grupos (pastas/áreas).

Full history: https://api.protogrid.dev/v1/servers/io.github.mcp-dir%2Feasyjur-mcp/changes

## Remotes

- https://api.mcp.ai/p_easyjur (streamable-http, auth none, reachable true, uptime30d 0.98245615)

## Packages

_none_

## Tools (47)

- `authenticate`: MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.
- `connect`: Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
- `easyjur_agenda_comentarios`: Comentários de um item de agenda.
- `easyjur_agenda_envolvidos`: Envolvidos em um item de agenda.

Bulk support: accepts agenda_ids for batched execution.
- `easyjur_agenda_etapas`: Etapas de workflow de um item de agenda.

Bulk support: accepts agenda_ids for batched execution.
- `easyjur_api_status`: Status da API EasyJur do escritório autenticado (identidade + limites).
- `easyjur_create_agenda`: Cria item de agenda. Obrigatórios: tipo, id_advogado. Vincule a um processo (campo `processo`) para registrar uma movimentação/atualização.
- `easyjur_create_oportunidade`: Cria oportunidade. Obrigatórios: nome, status, responsavel, cliente.
- `easyjur_create_pessoa`: Cria uma pessoa. Obrigatórios: nome, fisica_juridica.
- `easyjur_create_processo`: Cria um processo. Obrigatórios: numero, id_advogado. (A API oficial não tem update — para registrar movimentação use easyjur_create_agenda vinculada ao processo.)
- `easyjur_get_agenda`: Busca um item de agenda por ID.

Bulk support: accepts agenda_ids for batched execution.
- `easyjur_get_despesa`: Busca uma despesa por ID.

Bulk support: accepts despesa_ids for batched execution.
- `easyjur_get_grupo`: Busca um grupo por ID.

Bulk support: accepts grupo_ids for batched execution.
- `easyjur_get_oportunidade`: Busca uma oportunidade por ID.

Bulk support: accepts oportunidade_ids for batched execution.
- `easyjur_get_pessoa`: Busca uma pessoa por ID.

Bulk support: accepts pessoa_ids for batched execution.
- `easyjur_get_processo`: Busca um processo por ID (dados completos).

Bulk support: accepts processo_ids for batched execution.
- `easyjur_get_receita`: Busca uma receita por ID.

Bulk support: accepts receita_ids for batched execution.
- `easyjur_get_timesheet`: Detalha um lançamento de timesheet.

Bulk support: accepts ids for batched execution.
- `easyjur_get_token`: Consulta um token de API por ID.

Bulk support: accepts token_ids for batched execution.
- `easyjur_get_user`: Busca um usuário por ID.

Bulk support: accepts user_ids for batched execution.
- `easyjur_list_agenda`: Lista itens de agenda (prazos, compromissos, tarefas).
- `easyjur_list_agenda_grupo`: Lista agenda de um grupo.

Bulk support: accepts grupo_ids for batched execution.
- `easyjur_list_despesas`: Lista despesas.
- `easyjur_list_despesas_grupo`: Lista despesas de um grupo.

Bulk support: accepts grupo_ids for batched execution.
- `easyjur_list_grupos`: Lista grupos (pastas/áreas).
- `easyjur_list_oportunidades`: Lista oportunidades (CRM/pré-venda).
- `easyjur_list_oportunidades_grupo`: Lista oportunidades de um grupo.

Bulk support: accepts grupo_ids for batched execution.
- `easyjur_list_pessoas`: Lista pessoas (clientes, contrários, terceiros).
- `easyjur_list_pessoas_grupo`: Lista pessoas de um grupo.

Bulk support: accepts grupo_ids for batched execution.
- `easyjur_list_processos`: Lista/busca processos. Filtros úteis: numero, nome_parte, cpf, cnpj, advogado_nome, status, comarca, uf, data_inicio, data_fim, movimentacao, dias_movimentacao. Demais filtros via `query`.
- `easyjur_list_processos_grupo`: Lista processos de um grupo.

Bulk support: accepts grupo_ids for batched execution.
- `easyjur_list_receitas`: Lista receitas.
- `easyjur_list_receitas_grupo`: Lista receitas de um grupo.

Bulk support: accepts grupo_ids for batched execution.
- `easyjur_list_timesheet`: Lista lançamentos de timesheet.
- `easyjur_list_tokens`: Lista os tokens de API da empresa.
- `easyjur_list_tribunais`: Lista tribunais/órgãos disponíveis.
- `easyjur_list_users`: Lista usuários do escritório.
- `easyjur_processo_documentos`: Documentos de um processo.

Bulk support: accepts processo_ids for batched execution.
- `easyjur_processo_financeiros`: Lançamentos financeiros de um processo.

Bulk support: accepts processo_ids for batched execution.
- `easyjur_processo_mensagens`: Mensagens/andamentos de um processo.

Bulk support: accepts processo_ids for batched execution.
- `easyjur_processo_partes`: Partes de um processo.

Bulk support: accepts processo_ids for batched execution.
- `easyjur_processo_pedidos`: Pedidos de um processo.

Bulk support: accepts processo_ids for batched execution.
- `easyjur_processo_vinculados`: Processos vinculados a um processo.

Bulk support: accepts processo_ids for batched execution.
- `marketplace`: The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.
- `report_bug`: Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
- `show_version`: Show the current MCP platform and adapter versions.
- `toolkit_info`: Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.