# LegalOne

> Wrapper for the official LegalOne API (Thomson Reuters / Novajus, Premium package): lawsuits and lit

- name: io.github.mcp-dir/legalone-mcp
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 90/100
- quality: 88/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.mcp-dir%2Flegalone-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.mcp-dir%2Flegalone-mcp/tools

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

## Connection (mcpServers)

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


## Trust

- hygiene: 100
- liveness: 98
- freshness: 85
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-95% ~updated-60d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (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: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- 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`: 45 of 45 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 7,493 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no 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: 45, about 7,493 tokens to load them all
- tool set hash: 6a7b0f61d0f252a703fe33a6cf6c169b
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.mcp-dir/legalone-mcp.svg)](https://protogrid.dev/servers/io.github.mcp-dir/legalone-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://api.mcp.ai/p_legalone (streamable-http, auth none, reachable true, uptime30d 0.94736844)

## Packages

_none_

## Tools (45)

- `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.
- `legalone_create_appointments`: Cria um(a) Compromissos/agenda (OData POST /Appointments). `data` = corpo da entidade conforme a API oficial.
- `legalone_create_contacts`: Cria um(a) Contatos (pessoas físicas/jurídicas: clientes, partes, advogados) (OData POST /Contacts). `data` = corpo da entidade conforme a API oficial.
- `legalone_create_lawsuits`: Cria um(a) Processos judiciais com os campos próprios do módulo (valor da causa, partes, pedidos) (OData POST /Lawsuits). `data` = corpo da entidade conforme a API oficial.
- `legalone_create_litigations`: Cria um(a) Processos/litígios, visão consolidada do contencioso (OData POST /Litigations). `data` = corpo da entidade conforme a API oficial.
- `legalone_create_tasks`: Cria um(a) Tarefas/providências (o prazo vem no campo deadLine) (OData POST /Tasks). `data` = corpo da entidade conforme a API oficial.
- `legalone_create_updates`: Cria um(a) Andamentos/publicações/atualizações do processo (OData POST /Updates). `data` = corpo da entidade conforme a API oficial.
- `legalone_customfield_options`: Opções de um campo personalizado (/CustomFieldsDefinitions/{id}/options), resolve o texto por trás dos valores listItemId que aparecem em customFields.

Bulk support: accepts ids for batched execution.
- `legalone_get_appointments`: Busca um(a) Compromissos/agenda por id (OData /Appointments/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_appointmentstasks`: Busca um(a) Agenda unificada: compromissos e tarefas na mesma lista por id (OData /AppointmentsTasks/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_areas`: Busca um(a) Áreas de atuação por id (OData /Areas/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_contacts`: Busca um(a) Contatos (pessoas físicas/jurídicas: clientes, partes, advogados) por id (OData /Contacts/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_customfielddefinitions`: Busca um(a) Definições de campos personalizados por id (OData /CustomFieldsDefinitions/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_documents`: Busca um(a) Documentos (GED) por id (OData /Documents/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_lawsuits`: Busca um(a) Processos judiciais com os campos próprios do módulo (valor da causa, partes, pedidos) por id (OData /Lawsuits/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_litigations`: Busca um(a) Processos/litígios, visão consolidada do contencioso por id (OData /Litigations/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_servicetypes`: Busca um(a) Tipos de serviço/processo por id (OData /ServiceTypes/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_tasks`: Busca um(a) Tarefas/providências (o prazo vem no campo deadLine) por id (OData /Tasks/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_updates`: Busca um(a) Andamentos/publicações/atualizações do processo por id (OData /Updates/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_get_users`: Busca um(a) Usuários/responsáveis do escritório por id (OData /Users/{id}). Use $expand para sub-recursos.

Bulk support: accepts ids for batched execution.
- `legalone_list_appointments`: Lista Compromissos/agenda (OData /Appointments). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_appointmentstasks`: Lista Agenda unificada: compromissos e tarefas na mesma lista (OData /AppointmentsTasks). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_areas`: Lista Áreas de atuação (OData /Areas). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_contacts`: Lista Contatos (pessoas físicas/jurídicas: clientes, partes, advogados) (OData /Contacts). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_customfielddefinitions`: Lista Definições de campos personalizados (OData /CustomFieldsDefinitions). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_documents`: Lista Documentos (GED) (OData /Documents). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_lawsuits`: Lista Processos judiciais com os campos próprios do módulo (valor da causa, partes, pedidos) (OData /Lawsuits). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_litigations`: Lista Processos/litígios, visão consolidada do contencioso (OData /Litigations). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_servicetypes`: Lista Tipos de serviço/processo (OData /ServiceTypes). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_tasks`: Lista Tarefas/providências (o prazo vem no campo deadLine) (OData /Tasks). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_updates`: Lista Andamentos/publicações/atualizações do processo (OData /Updates). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_list_users`: Lista Usuários/responsáveis do escritório (OData /Users). Filtre com $filter/$top/$skip/$orderby/$expand.
- `legalone_metadata`: Metadados da conexão: escopos que a Thomson Reuters liberou para este escritório, produtos da API, base da API e as coleções disponíveis com as tools de cada uma. Chame antes de montar uma consulta, e depois de um 403 (403 quase sempre é escopo fora do contrato do escritório, não credencial errada).
- `legalone_odata_get`: GET genérico em qualquer coleção/recurso OData do LegalOne. Informe `entity` (ex.: "Litigations") e opcionalmente `id`; suporta $filter/$expand/$select/$top/$skip/$orderby. Use isto para entidades não cobertas por uma tool nomeada.

Bulk support: accepts ids for batched execution.
- `legalone_request`: Escape hatch: chamada OData crua. `method` (GET/POST/PATCH/PUT/DELETE) + `path` (ex.: "/Litigations/2479") + `query`/`body` opcionais. Cobre endpoints/ações fora das tools nomeadas.
- `legalone_update_appointments`: Atualiza um(a) Compromissos/agenda (OData PATCH /Appointments/{id}). `data` = campos a alterar.

Bulk support: accepts ids for batched execution.
- `legalone_update_contacts`: Atualiza um(a) Contatos (pessoas físicas/jurídicas: clientes, partes, advogados) (OData PATCH /Contacts/{id}). `data` = campos a alterar.

Bulk support: accepts ids for batched execution.
- `legalone_update_lawsuits`: Atualiza um(a) Processos judiciais com os campos próprios do módulo (valor da causa, partes, pedidos) (OData PATCH /Lawsuits/{id}). `data` = campos a alterar.

Bulk support: accepts ids for batched execution.
- `legalone_update_litigations`: Atualiza um(a) Processos/litígios, visão consolidada do contencioso (OData PATCH /Litigations/{id}). `data` = campos a alterar.

Bulk support: accepts ids for batched execution.
- `legalone_update_tasks`: Atualiza um(a) Tarefas/providências (o prazo vem no campo deadLine) (OData PATCH /Tasks/{id}). `data` = campos a alterar.

Bulk support: accepts 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.