Koskamo

mcp-dir DataJud (CNJ) MCP

An MCP server that provides public lookup of Brazilian court cases, including metadata and docket movements, via the official CNJ/DataJud API. It supports searching by case number, class, court, and subject, and detects new movements in the process timeline. The server is read-only, free, and requires no login or credentials.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

mcp-dir DataJud (CNJ) MCP logo, by mcp-dirCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by mcp-dir
MCP endpoint (Streamable HTTP)
https://api.mcp.ai/p_datajud
Vendor documentation

What its tools do

11 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (8)

Can change data (3)

11 of 11 have a description · 11 of 11 declare behavior hints · 0 of 8 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search for a specific court process by its CNJ number and court.
  • List process movements to check for new updates.
  • Search for recent processes by class, court, or subject.
  • Locate the current instance of a process using only the CNJ number.

Source and maintenance

Community listingRegistry 0.1.1
mcp-registry: io.github.mcp-dir/datajud-mcp@0.1.1Source repository
Maintenance checked

Protocol and capabilities

Server
mcp-ai 0.9.410
MCP protocol negotiated in check
2025-11-25
Tools
11 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

MCP.AI platform v0.9.410 | Adapters: datajud v1.2.0. When the user asks about the version (e.g. "qual a versão", "which version"), call the show_version tool. NEW MCPs/tools/integrations (capabilities not already in this toolkit) come from the official mcp.ai catalog: the `marketplace` tool (action=search) finds and runs them. You are not authenticated yet. Call the authenticate tool first — it will give the user a browser link to log in and copy a token. No other tools will work until authenticated.

Tools

11 advertised

datajud_get_processo
Advertised by the server during the last successful anonymous check.
Advertised read-only

Busca processo por número CNJ e tribunal. Retorna `tribunal`, `total`, `count` e `processos[]` (metadados e movimentações por instância). Só sem resultados inclui `ausencia`. Aceita número com ou sem máscara. Quando `processos` está vazio, `ausencia` traz o motivo provável (numero_invalido | tribunal_divergente | nao_publicado | carga_ausente | indeterminado) e a explicação. Com resultados, esse bloco não é retornado. Leia esse bloco antes de repetir a consulta em outra tool: a API pública do CNJ não publica processo em segredo de justiça, então `nao_publicado` NÃO significa que o processo não existe. O processo que sobe por recurso MANTÉM o número da origem: o AIRR/RR de um processo do TRT continua com o número do TRT no índice `tst` (e o REsp de TJ/TRF no `stj`). Quando o 2º grau registra esse recurso, a resposta inclui `instancia_superior`; para ver em que instância o processo está agora, use datajud_localizar_processo.

datajud_get_processo input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "tribunal",
    "numero_processo"
  ],
  "properties": {
    "tribunal": {
      "enum": [
        "tst",
        "stj",
        "tse",
        "stm",
        "trf1",
        "trf2",
        "trf3",
        "trf4",
        "trf5",
        "trf6",
        "tjac",
        "tjal",
        "tjam",
        "tjap",
        "tjba",
        "tjce",
        "tjdft",
        "tjes",
        "tjgo",
        "tjma",
        "tjmg",
        "tjms",
        "tjmt",
        "tjpa",
        "tjpb",
        "tjpe",
        "tjpi",
        "tjpr",
        "tjrj",
        "tjrn",
        "tjro",
        "tjrr",
        "tjrs",
        "tjsc",
        "tjse",
        "tjsp",
        "tjto",
        "trt1",
        "trt2",
        "trt3",
        "trt4",
        "trt5",
        "trt6",
        "trt7",
        "trt8",
        "trt9",
        "trt10",
        "trt11",
        "trt12",
        "trt13",
        "trt14",
        "trt15",
        "trt16",
        "trt17",
        "trt18",
        "trt19",
        "trt20",
        "trt21",
        "trt22",
        "trt23",
        "trt24",
        "tre-ac",
        "tre-al",
        "tre-am",
        "tre-ap",
        "tre-ba",
        "tre-ce",
        "tre-df",
        "tre-es",
        "tre-go",
        "tre-ma",
        "tre-mg",
        "tre-ms",
        "tre-mt",
        "tre-pa",
        "tre-pb",
        "tre-pe",
        "tre-pi",
        "tre-pr",
        "tre-rj",
        "tre-rn",
        "tre-ro",
        "tre-rr",
        "tre-rs",
        "tre-sc",
        "tre-se",
        "tre-sp",
        "tre-to",
        "tjmmg",
        "tjmrs",
        "tjmsp"
      ],
      "type": "string"
    },
    "numero_processo": {
      "type": "string"
    }
  }
}
datajud_get_processo annotations
{
  "title": "datajud_get_processo",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
datajud_search
Advertised by the server during the last successful anonymous check.
Advertised read-only

Busca processos em um tribunal por classe, órgão julgador e/ou assunto (códigos das tabelas do CNJ), paginada e ordenada por data de ajuizamento. DataJud NÃO indexa nome de parte nem OAB — pra isso use o MCP djen/legal.

datajud_search input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "tribunal"
  ],
  "properties": {
    "from": {
      "type": "number"
    },
    "size": {
      "type": "number"
    },
    "tribunal": {
      "enum": [
        "tst",
        "stj",
        "tse",
        "stm",
        "trf1",
        "trf2",
        "trf3",
        "trf4",
        "trf5",
        "trf6",
        "tjac",
        "tjal",
        "tjam",
        "tjap",
        "tjba",
        "tjce",
        "tjdft",
        "tjes",
        "tjgo",
        "tjma",
        "tjmg",
        "tjms",
        "tjmt",
        "tjpa",
        "tjpb",
        "tjpe",
        "tjpi",
        "tjpr",
        "tjrj",
        "tjrn",
        "tjro",
        "tjrr",
        "tjrs",
        "tjsc",
        "tjse",
        "tjsp",
        "tjto",
        "trt1",
        "trt2",
        "trt3",
        "trt4",
        "trt5",
        "trt6",
        "trt7",
        "trt8",
        "trt9",
        "trt10",
        "trt11",
        "trt12",
        "trt13",
        "trt14",
        "trt15",
        "trt16",
        "trt17",
        "trt18",
        "trt19",
        "trt20",
        "trt21",
        "trt22",
        "trt23",
        "trt24",
        "tre-ac",
        "tre-al",
        "tre-am",
        "tre-ap",
        "tre-ba",
        "tre-ce",
        "tre-df",
        "tre-es",
        "tre-go",
        "tre-ma",
        "tre-mg",
        "tre-ms",
        "tre-mt",
        "tre-pa",
        "tre-pb",
        "tre-pe",
        "tre-pi",
        "tre-pr",
        "tre-rj",
        "tre-rn",
        "tre-ro",
        "tre-rr",
        "tre-rs",
        "tre-sc",
        "tre-se",
        "tre-sp",
        "tre-to",
        "tjmmg",
        "tjmrs",
        "tjmsp"
      ],
      "type": "string"
    },
    "sort_desc": {
      "type": "boolean"
    },
    "classe_codigo": {
      "type": "number"
    },
    "assunto_codigo": {
      "type": "number"
    },
    "numero_processo": {
      "type": "string"
    },
    "orgao_julgador_codigo": {
      "type": "number"
    }
  }
}
datajud_search annotations
{
  "title": "datajud_search",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
datajud_movimentos
Advertised by the server during the last successful anonymous check.
Advertised read-only

Consulta movimentações por número CNJ e tribunal. Retorna `tribunal`, `numeroProcesso` e `instancias[]` (timeline e metadados). Só sem resultados inclui `ausencia`. Ideal para detectar movimentação nova. Quando `instancias` está vazio, `ausencia` traz o mesmo diagnóstico de datajud_get_processo (motivo provável + explicação). Com resultados, esse bloco não é retornado. Quando o 2º grau registra recurso ao tribunal superior (recurso de revista/AIRR → TST, recurso especial → STJ), inclui `instancia_superior` com o próximo passo: o processo mantém o mesmo número lá.

datajud_movimentos input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "tribunal",
    "numero_processo"
  ],
  "properties": {
    "tribunal": {
      "enum": [
        "tst",
        "stj",
        "tse",
        "stm",
        "trf1",
        "trf2",
        "trf3",
        "trf4",
        "trf5",
        "trf6",
        "tjac",
        "tjal",
        "tjam",
        "tjap",
        "tjba",
        "tjce",
        "tjdft",
        "tjes",
        "tjgo",
        "tjma",
        "tjmg",
        "tjms",
        "tjmt",
        "tjpa",
        "tjpb",
        "tjpe",
        "tjpi",
        "tjpr",
        "tjrj",
        "tjrn",
        "tjro",
        "tjrr",
        "tjrs",
        "tjsc",
        "tjse",
        "tjsp",
        "tjto",
        "trt1",
        "trt2",
        "trt3",
        "trt4",
        "trt5",
        "trt6",
        "trt7",
        "trt8",
        "trt9",
        "trt10",
        "trt11",
        "trt12",
        "trt13",
        "trt14",
        "trt15",
        "trt16",
        "trt17",
        "trt18",
        "trt19",
        "trt20",
        "trt21",
        "trt22",
        "trt23",
        "trt24",
        "tre-ac",
        "tre-al",
        "tre-am",
        "tre-ap",
        "tre-ba",
        "tre-ce",
        "tre-df",
        "tre-es",
        "tre-go",
        "tre-ma",
        "tre-mg",
        "tre-ms",
        "tre-mt",
        "tre-pa",
        "tre-pb",
        "tre-pe",
        "tre-pi",
        "tre-pr",
        "tre-rj",
        "tre-rn",
        "tre-ro",
        "tre-rr",
        "tre-rs",
        "tre-sc",
        "tre-se",
        "tre-sp",
        "tre-to",
        "tjmmg",
        "tjmrs",
        "tjmsp"
      ],
      "type": "string"
    },
    "numero_processo": {
      "type": "string"
    }
  }
}
datajud_movimentos annotations
{
  "title": "datajud_movimentos",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
datajud_raw_query
Advertised by the server during the last successful anonymous check.
Advertised read-only

Avançado: envia uma query Elasticsearch crua pro índice do tribunal (escape hatch). `query` é SÓ a cláusula de busca (ex.: { match: { "classe.nome": "Apelação" } }); size, sort, _source e search_after vão nos campos próprios. Use search_after (valor `sort` do último hit) pra paginar além de 10.000 resultados. A API pública do CNJ é lenta em índices grandes: prefira size pequeno e `_source` com só os campos que precisa.

datajud_raw_query input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "tribunal",
    "query"
  ],
  "properties": {
    "from": {
      "type": "number"
    },
    "size": {
      "type": "number"
    },
    "sort": {},
    "query": {},
    "_source": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "tribunal": {
      "enum": [
        "tst",
        "stj",
        "tse",
        "stm",
        "trf1",
        "trf2",
        "trf3",
        "trf4",
        "trf5",
        "trf6",
        "tjac",
        "tjal",
        "tjam",
        "tjap",
        "tjba",
        "tjce",
        "tjdft",
        "tjes",
        "tjgo",
        "tjma",
        "tjmg",
        "tjms",
        "tjmt",
        "tjpa",
        "tjpb",
        "tjpe",
        "tjpi",
        "tjpr",
        "tjrj",
        "tjrn",
        "tjro",
        "tjrr",
        "tjrs",
        "tjsc",
        "tjse",
        "tjsp",
        "tjto",
        "trt1",
        "trt2",
        "trt3",
        "trt4",
        "trt5",
        "trt6",
        "trt7",
        "trt8",
        "trt9",
        "trt10",
        "trt11",
        "trt12",
        "trt13",
        "trt14",
        "trt15",
        "trt16",
        "trt17",
        "trt18",
        "trt19",
        "trt20",
        "trt21",
        "trt22",
        "trt23",
        "trt24",
        "tre-ac",
        "tre-al",
        "tre-am",
        "tre-ap",
        "tre-ba",
        "tre-ce",
        "tre-df",
        "tre-es",
        "tre-go",
        "tre-ma",
        "tre-mg",
        "tre-ms",
        "tre-mt",
        "tre-pa",
        "tre-pb",
        "tre-pe",
        "tre-pi",
        "tre-pr",
        "tre-rj",
        "tre-rn",
        "tre-ro",
        "tre-rr",
        "tre-rs",
        "tre-sc",
        "tre-se",
        "tre-sp",
        "tre-to",
        "tjmmg",
        "tjmrs",
        "tjmsp"
      ],
      "type": "string"
    },
    "search_after": {}
  }
}
datajud_raw_query annotations
{
  "title": "datajud_raw_query",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
datajud_localizar_processo
Advertised by the server during the last successful anonymous check.
Advertised read-only

Localiza em que instância o processo está agora, só pelo número CNJ: consulta a origem e o tribunal superior (TRT → TST, TJ/TRF → STJ). O tribunal de origem é derivado do número e os dois índices são consultados em paralelo. Retorna `instancias[]` ordenadas (1º grau → 2º grau → superior) com tribunal, grau, classe, órgão julgador e último movimento, `instancia_mais_recente` e `consultas[]` (status de cada índice consultado). Consulta processual trabalhista no TST: o processo que sobe ao TST (recurso de revista, AIRR) MANTÉM o número do TRT de origem, então consultar só o TRT nunca mostra a fase no TST. Se um índice falhar, `consultas[]` traz o erro dele e o outro resultado continua valendo. Sem nenhum resultado, inclui `ausencia` (mesmo diagnóstico de datajud_get_processo). O STF não está no DataJud. Para a timeline completa de uma instância, use datajud_movimentos com o `tribunal` dela.

datajud_localizar_processo input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "numero_processo"
  ],
  "properties": {
    "numero_processo": {
      "type": "string"
    }
  }
}
datajud_localizar_processo annotations
{
  "title": "datajud_localizar_processo",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
show_version
Advertised by the server during the last successful anonymous check.
Advertised read-only

Show the current MCP platform and adapter versions.

show_version input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
show_version annotations
{
  "title": "Show Version",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
report_bug
Advertised by the server during the last successful anonymous check.

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

report_bug input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "message"
  ],
  "properties": {
    "context": {
      "type": "string",
      "default": ""
    },
    "message": {
      "type": "string"
    },
    "conversation": {
      "type": "string",
      "default": "[]"
    }
  }
}
report_bug annotations
{
  "title": "Report Bug",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
connect
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

connect input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
connect annotations
{
  "title": "Connection Status",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
toolkit_info
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

toolkit_info input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
toolkit_info annotations
{
  "title": "Toolkit Info",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
marketplace
Advertised by the server during the last successful anonymous check.
Open-world

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.

marketplace input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "number",
      "default": 10
    },
    "query": {
      "type": "string",
      "default": ""
    },
    "action": {
      "enum": [
        "search",
        "describe",
        "install",
        "uninstall",
        "subscribe",
        "cancel",
        "resume",
        "report_bug",
        "request_mcp",
        "list_tools",
        "invoke",
        "search_prompts",
        "get_prompt",
        "publish_prompt"
      ],
      "type": "string",
      "default": "search"
    },
    "mcp_id": {
      "type": "string",
      "default": ""
    },
    "message": {
      "type": "string",
      "default": ""
    },
    "tool_id": {
      "type": "string",
      "default": ""
    },
    "arguments": {
      "type": "string",
      "default": "{}"
    },
    "immediate": {
      "type": "boolean",
      "default": false
    },
    "tier_slug": {
      "type": "string",
      "default": ""
    },
    "prompt_body": {
      "type": "string",
      "default": ""
    },
    "prompt_slug": {
      "type": "string",
      "default": ""
    },
    "prompt_tool": {
      "type": "string",
      "default": ""
    },
    "prompt_vars": {
      "type": "string",
      "default": "{}"
    },
    "conversation": {
      "type": "string",
      "default": "[]"
    },
    "prompt_title": {
      "type": "string",
      "default": ""
    },
    "request_name": {
      "type": "string",
      "default": ""
    },
    "cancel_reason": {
      "enum": [
        "too_expensive",
        "missing_features",
        "switched_service",
        "unused",
        "customer_service",
        "too_complex",
        "low_quality",
        "other"
      ],
      "type": "string"
    },
    "cancel_comment": {
      "type": "string",
      "default": ""
    },
    "prompt_targets": {
      "type": "array",
      "items": {
        "enum": [
          "claude",
          "chatgpt",
          "cursor",
          "lovable"
        ],
        "type": "string"
      },
      "default": []
    },
    "report_context": {
      "type": "string",
      "default": ""
    },
    "prompt_category": {
      "type": "string",
      "default": ""
    },
    "request_details": {
      "type": "string",
      "default": ""
    },
    "prompt_description": {
      "type": "string",
      "default": ""
    }
  }
}
marketplace annotations
{
  "title": "Marketplace",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
authenticate
Advertised by the server during the last successful anonymous check.

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.

authenticate input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "token": {
      "type": "string"
    }
  }
}
authenticate annotations
{
  "title": "Authenticate",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
412 ms
95th percentile latency
412 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 412 ms · metadata changed · 11 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http datajud-cnj-mcp https://api.mcp.ai/p_datajud

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add datajud-cnj-mcp --url https://api.mcp.ai/p_datajud

Cursor

Merge this server into .cursor/mcp.json in your project, then enable datajud-cnj-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "datajud-cnj-mcp": {
      "url": "https://api.mcp.ai/p_datajud"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "datajud-cnj-mcp": {
      "type": "streamableHttp",
      "url": "https://api.mcp.ai/p_datajud",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start datajud-cnj-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "datajud-cnj-mcp": {
      "type": "http",
      "url": "https://api.mcp.ai/p_datajud"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http datajud-cnj-mcp https://api.mcp.ai/p_datajud

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://api.mcp.ai/p_datajud

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "datajud-cnj-mcp": {
      "serverUrl": "https://api.mcp.ai/p_datajud"
    }
  }
}

Let your agent find its tools

Find servers like mcp-dir DataJud (CNJ) MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 6,262