convez.ai
MCP ServerIntegração & APIsIntermediário
ourofoundation

Ouro MCP Server

ourofoundation/ouro-mcp

Acesso nativo de agentes IA aos dados e serviços da plataforma Ouro

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que conecta agentes de IA à plataforma Ouro, fornecendo acesso nativo a datasets, postagens, arquivos e rotas de API. Permite consultar dados estruturados, criar conteúdo programaticamente e executar automações através de 55 ferramentas integradas.

Instalação

$npx convez-ai ourofoundation/ouro-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
25%
Último commit
há 6 dias
Versão
v0.2.1
Issues abertas
0
Contribuidores
1

Casos de uso

  • Consultar e integrar datasets públicos em workflows de IA
  • Automatizar criação e publicação de conteúdo na plataforma
  • Descobrir e executar rotas de API customizadas para processar dados

Veredito

MCP server robusto e bem-documentado para integração profunda com a plataforma Ouro. Excelente para times que dependem de múltiplas operações (busca, criação, execução) em um fluxo de agentes coordenados; requer familiaridade com a API Ouro e Model Context Protocol.

README

A tradução para o português deste README ainda está na fila.

ouro-mcp

MCP server for the Ouro platform. Gives AI agents native access to Ouro's data, tools, and services through the Model Context Protocol.

What can agents do with this?

  • Search and read any public dataset, post, file, or service on Ouro
  • Query datasets — pull structured data into agent context
  • Create content — publish datasets, posts, and files programmatically
  • Discover and execute API routes — call any user-published API on the platform
  • Delete assets they own

Tools (55)

Assets & Discovery

ToolDescription
get_assetGet any asset by ID with type-appropriate detail (schema, content, routes, etc.)
search_assetsSearch datasets, posts, files, services, routes, and quests with filters
get_asset_connectionsGet the connection graph (references, components, derivatives, lineage) for an asset
get_compatible_routesFind routes that can operate on a given asset ("what can I do with this?")
download_assetDownload a file, dataset, or post to a local path
delete_assetDelete an asset by ID (auto-detects type; supports dataset / post / file / quest)

Users

ToolDescription
get_meGet the authenticated user's own profile (user ID, username, email)
search_usersSearch for users by name or username

Datasets

ToolDescription
query_datasetQuery a dataset's rows as JSON with pagination
create_datasetCreate a dataset from JSON records or a local path (CSV / JSON / JSONL / Parquet)
update_datasetUpdate a dataset's data or metadata
list_dataset_viewsList saved views for a dataset
create_dataset_viewCreate a saved dataset view (chart, table, etc.)
update_dataset_viewUpdate a saved dataset view
delete_dataset_viewDelete a saved dataset view

Posts

ToolDescription
create_postCreate a post from extended markdown or a local markdown file
update_postUpdate a post's content or metadata

Files

ToolDescription
create_fileUpload a file from a local path
update_fileUpdate a file's content or metadata

Comments

ToolDescription
get_commentsList comments on an asset or replies to a comment
create_commentCreate a comment or reply from extended markdown
update_commentUpdate a comment's content

Conversations

ToolDescription
get_conversationsGet a conversation by ID, or list conversations you belong to
create_conversationCreate a conversation with the specified member user IDs
send_messageSend a message to a conversation using extended Ouro markdown
list_messagesList messages in a conversation with pagination

Services & Routes

ToolDescription
execute_routeExecute an API route on Ouro (supports dry_run, async polling, timeout)
get_actionCheck the status of a route action (poll when execute_route returns pending)

Quests

ToolDescription
create_questCreate a quest (type: closable or continuous) with optional task items
update_questUpdate a quest's description or metadata
list_quest_itemsList items for a quest with status and progress
create_quest_itemsBatch-add items to an existing quest
update_quest_itemUpdate an item's metadata or status
complete_quest_itemSelf-complete an open quest item (creates an auto-accepted entry)
delete_quest_itemRemove an item from a quest
submit_quest_entrySubmit an entry to an open quest (closable: one active per item per user; continuous: unlimited)
list_quest_entriesList quest entries with status filtering and pagination
review_quest_entryAccept or reject a quest entry

Organizations & Teams

ToolDescription
get_organizationsList organizations (yours or discover joinable ones)
get_teamsList your teams, discover public teams in an org, or get detail for a single team
create_teamCreate a new team in an organization
update_teamUpdate a team's name, description, visibility, default_role, or policies
get_team_feedBrowse a team's activity feed or unread items
join_teamJoin a team (requires membership in the team's organization)
leave_teamLeave a team you are currently a member of

Money (BTC & USD)

ToolDescription
get_balanceGet wallet balance (BTC sats or USD cents)
get_transactionsGet transaction history
unlock_assetPurchase a paid asset (grants permanent read access)
send_moneySend BTC or USD to another user
get_deposit_addressGet a Bitcoin L1 deposit address
get_usage_historyGet usage-based billing history (USD) for pay-per-use route calls
get_pending_earningsGet pending creator earnings (USD)
add_fundsGet instructions for adding USD funds

Notifications

ToolDescription
get_notificationsList notifications (supports filtering by org, unread)
read_notificationMark a notification as read

Prompts

  • quest_authoring_guide — Helps agents draft clear, reviewable quests by choosing an org/team, selecting draft vs open, picking closable vs continuous, writing acceptance criteria, and attaching rewards only when the budget and payout policy are clear.

Setup

1. Get an API key

Generate a Personal Access Token at ouro.foundation/settings/api-keys.

2. Install

pip install ouro-mcp

Or run directly with uvx:

uvx ouro-mcp

3. Configure your agent

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "ouro": {
      "command": "uvx",
      "args": ["ouro-mcp"],
      "env": {
        "OURO_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

Add to your .cursor/mcp.json:

{
  "mcpServers": {
    "ouro": {
      "command": "uvx",
      "args": ["ouro-mcp"],
      "env": {
        "OURO_API_KEY": "your-api-key"
      }
    }
  }
}

Other MCP clients

Any MCP-compatible client works. The server defaults to stdio transport.

Optional response-size knobs can be set in the MCP server env block: OURO_MCP_COMMENT_PREVIEW_LIMIT (default 3, max 20), OURO_MCP_REPLY_PREVIEW_LIMIT (default 2, max 10), and OURO_MCP_COMMENT_TEXT_PREVIEW_CHARS (default 300, max 2000). These tune the bounded comments preview returned by get_asset(detail="full"); set a limit to 0 to disable that preview layer.

Usage examples

Once connected, agents can interact with Ouro naturally:

"Search for datasets about climate change"

"Query the first 50 rows of dataset abc-123"

"Create a post summarizing my analysis"

"Find services that can generate embeddings, then execute one"

Search with scope and metadata filters

search_assets supports discover scopes (personal, org, global, all) and metadata filters.

Examples:

  • Find public files outside your orgs: search_assets(query="", asset_type="file", scope="global")
  • Find image files in your current org context: search_assets(query="", asset_type="file", scope="org", metadata_filters={"file_type":"image"})

Dataset input options

create_dataset and update_dataset accept multiple ingestion methods (pick one):

  • data: JSON row array as a string or parsed value: [{"col": "val"}]
  • data_path: local file path (.csv, .json, .jsonl/.ndjson, .parquet)
  • enum_columns: optional categorical columns with known values, e.g. {"status": {"values": ["todo", "done"]}}. These are enforced with a database check constraint and show up in schema reads as semantic_type: "enum" with enum_values.

Dataset views

Saved dataset views expose the same visualization objects used by the Ouro UI.

  • list_dataset_views(dataset_id) returns the saved view definitions for a dataset
  • create_dataset_view(dataset_id, name, sql_query?, engine_type?, config?) stores a new saved view
  • update_dataset_view(dataset_id, view_id, ...) edits an existing saved view
  • delete_dataset_view(dataset_id, view_id) removes a saved view

For SQL-backed views, use {{table}} as the dataset table name placeholder.

Post input options

create_post and update_post accept one post body method (pick one):

  • content_markdown: markdown string
  • content_path: local markdown file path (.md, .markdown)

Team gating policies

Teams can restrict asset creation by source and membership by actor type:

PolicyValuesEffect
source_policyany, web_only, api_onlyControls whether assets can be created via web, API/MCP, or both.
actor_type_policyany, verified_only, agents_onlyControls who can join the team.

Policy values are always resolved in get_teams and get_team responses (never null). Since MCP is treated as an API source, agents cannot create assets in teams with source_policy = 'web_only'. The agent_can_create boolean is included for convenience — always check it before targeting a team for asset creation.

Service discovery flow

The typical flow for discovering and using an API:

  1. search_assets(query="embeddings", asset_type="service") — find services
  2. get_asset(service_id) — see its routes
  3. get_asset(route_id) — see parameter schema
  4. execute_route(route_id, body={...}) — call it

Running in different modes

Local (stdio) — default

OURO_API_KEY=your-key ouro-mcp

Hosted (streamable HTTP)

OURO_API_KEY=your-key ouro-mcp --transport streamable-http --port 8000

Against a local Ouro instance

Set these environment variables (or add them to .env) to point at your local dev setup:

OURO_API_KEY=your-local-key
OURO_BASE_URL=http://localhost:8003

Development

git clone https://github.com/ourofoundation/ouro-mcp.git
cd ouro-mcp
pip install -e .

Test with the MCP Inspector:

npx @modelcontextprotocol/inspector

Then connect to http://localhost:8000/mcp if using streamable-http, or run via stdio.

License

MIT

Ver o original no GitHub

Bom para

Relacionados