Koskamo

Arumi MCP

An MCP server enabling AI assistants to generate images, video, and audio using Arumi's 55 models. It allows users to browse models, check prices and balances, generate content, and upload files, all while enforcing credit limits and spending controls.

Visit Arumi

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.

Arumi MCP logo, by ArumiCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Arumi
You need:API keys are a paid feature: you can create and use them while your paid credits are valid, 120 days from your latest purchase.
MCP endpoint (Streamable HTTP)
https://api.arumi.ai/mcp
Vendor documentation

What its tools do

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

Read-only (6)

Can change data (1)

Not annotated (2)

9 of 9 have a description · 7 of 9 declare behavior hints · 5 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

  • Generate images, video, and audio using AI models
  • Check generation costs and account balance before spending
  • Upload files to use as references for generation
  • List and browse available AI models

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.weidotbuild/arumi@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
arumi 1
MCP protocol negotiated in check
2025-11-25
Tools
9 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  },
  "logging": {}
}

Server-provided instructions

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

Arumi generates images, video, audio and music with many AI models, paid with the user's Arumi credits. Flow: list_models (or get_model for one model's inputs and settings) → quote → generate with max_credits at least the quoted credits → get_generation until it has succeeded or failed, no more often than every 5 seconds (10 for video, which can take several minutes) → the result is a link. To use a file of the user's as a reference: create_upload, PUT the bytes to the upload URL with the given headers, complete_upload, then pass the asset id in references. A failed generation costs nothing unless it still used the model, and then never more than the quote. Never generate without telling the user what it costs.

Tools

9 advertised

complete_upload
Advertised by the server during the last successful anonymous check.

Finish an upload after the PUT; returns the asset_id to pass in a generation's references.

complete_upload input schema
{
  "type": "object",
  "required": [
    "upload_id"
  ],
  "properties": {
    "upload_id": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
complete_upload output schema
{
  "type": "object",
  "required": [
    "asset_id",
    "kind",
    "name"
  ],
  "properties": {
    "kind": {
      "type": "string"
    },
    "name": {
      "type": "string"
    },
    "asset_id": {
      "type": "string"
    },
    "duration_seconds": {
      "type": "number"
    }
  },
  "additionalProperties": false
}
create_upload
Advertised by the server during the last successful anonymous check.

Start uploading one of the user's files to use as a reference. PUT the file's bytes to upload_url with exactly the returned headers, then call complete_upload.

create_upload input schema
{
  "type": "object",
  "required": [
    "file_name",
    "content_type",
    "size_bytes",
    "sha256"
  ],
  "properties": {
    "width": {
      "type": "integer",
      "description": "required for images: width in pixels"
    },
    "height": {
      "type": "integer",
      "description": "required for images: height in pixels"
    },
    "sha256": {
      "type": "string",
      "description": "the file's SHA-256 as 64 lower-case hex characters (shasum -a 256)"
    },
    "file_name": {
      "type": "string",
      "description": "the file's name, with its extension"
    },
    "size_bytes": {
      "type": "integer"
    },
    "content_type": {
      "type": "string",
      "description": "for example image/png, image/jpeg, video/mp4, audio/mpeg"
    }
  },
  "additionalProperties": false
}
create_upload output schema
{
  "type": "object",
  "required": [
    "upload_id",
    "upload_url",
    "headers",
    "expires_at",
    "next"
  ],
  "properties": {
    "next": {
      "type": "string"
    },
    "headers": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      }
    },
    "upload_id": {
      "type": "string"
    },
    "expires_at": {
      "type": "string"
    },
    "upload_url": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
generate
Advertised by the server during the last successful anonymous check.

Start a generation with the user's credits. It is refused, with nothing charged, when it would cost more than max_credits. Returns at once with a generation_id: call get_generation until it has succeeded or failed.

generate input schema
{
  "type": "object",
  "required": [
    "model",
    "max_credits"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "the model id from list_models"
    },
    "prompt": {
      "type": "string",
      "description": "what to make; for speech models the text to read"
    },
    "parameters": {
      "type": "object",
      "description": "the model's settings by key (get_model); any left out take the model's default",
      "additionalProperties": true
    },
    "references": {
      "type": [
        "null",
        "object"
      ],
      "properties": {
        "audio": {
          "type": [
            "null",
            "array"
          ],
          "items": {
            "type": "string"
          },
          "description": "asset ids of uploaded audio files, in the order of the model's audio slots"
        },
        "images": {
          "type": [
            "null",
            "array"
          ],
          "items": {
            "type": "string"
          },
          "description": "asset ids of uploaded images (complete_upload), in the order of the model's image slots"
        },
        "videos": {
          "type": [
            "null",
            "array"
          ],
          "items": {
            "type": "string"
          },
          "description": "asset ids of uploaded videos, in the order of the model's video slots"
        }
      },
      "description": "uploaded files the model works from",
      "additionalProperties": false
    },
    "max_credits": {
      "type": "integer",
      "description": "the most credits the user agreed to spend on this generation; it is refused when the quote is higher"
    },
    "idempotency_key": {
      "type": "string",
      "description": "optional, 16-128 characters [A-Za-z0-9._:-]: repeating a call with the same key returns the same generation instead of making another"
    }
  },
  "additionalProperties": false
}
generate output schema
{
  "type": "object",
  "required": [
    "generation_id",
    "model",
    "modality",
    "status",
    "progress",
    "created_at",
    "credits"
  ],
  "properties": {
    "tip": {
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "error": {
      "type": [
        "null",
        "object"
      ],
      "required": [
        "code",
        "message",
        "retryable"
      ],
      "properties": {
        "code": {
          "type": "string"
        },
        "message": {
          "type": "string"
        },
        "retryable": {
          "type": "boolean"
        }
      },
      "additionalProperties": false
    },
    "model": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "description": "queued, processing, succeeded, failed or unknown"
    },
    "credits": {
      "type": "object",
      "required": [
        "reserved",
        "charged",
        "state"
      ],
      "properties": {
        "state": {
          "type": "string",
          "description": "reserved while it runs; settled when charged; released when nothing was charged"
        },
        "charged": {
          "type": "integer"
        },
        "reserved": {
          "type": "integer"
        }
      },
      "additionalProperties": false
    },
    "outputs": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "object",
        "required": [
          "url",
          "kind"
        ],
        "properties": {
          "url": {
            "type": "string"
          },
          "kind": {
            "type": "string"
          },
          "duration_ms": {
            "type": "integer"
          }
        },
        "additionalProperties": false
      }
    },
    "modality": {
      "type": "string"
    },
    "progress": {
      "type": "integer"
    },
    "created_at": {
      "type": "string"
    },
    "generation_id": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
generate annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
get_balance
Advertised by the server during the last successful anonymous check.
Advertised read-only

The user's Arumi credits: available, held by running generations, and owed. 1 credit = 0.01 USD.

get_balance input schema
{
  "type": "object",
  "additionalProperties": false
}
get_balance output schema
{
  "type": "object",
  "additionalProperties": {
    "type": "integer"
  }
}
get_balance annotations
{
  "readOnlyHint": true,
  "idempotentHint": false
}
get_generation
Advertised by the server during the last successful anonymous check.
Advertised read-only

A generation's status; once it has succeeded, links to its results, and what it charged.

get_generation input schema
{
  "type": "object",
  "required": [
    "generation_id"
  ],
  "properties": {
    "generation_id": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
get_generation output schema
{
  "type": "object",
  "required": [
    "generation_id",
    "model",
    "modality",
    "status",
    "progress",
    "created_at",
    "credits"
  ],
  "properties": {
    "tip": {
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "error": {
      "type": [
        "null",
        "object"
      ],
      "required": [
        "code",
        "message",
        "retryable"
      ],
      "properties": {
        "code": {
          "type": "string"
        },
        "message": {
          "type": "string"
        },
        "retryable": {
          "type": "boolean"
        }
      },
      "additionalProperties": false
    },
    "model": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "description": "queued, processing, succeeded, failed or unknown"
    },
    "credits": {
      "type": "object",
      "required": [
        "reserved",
        "charged",
        "state"
      ],
      "properties": {
        "state": {
          "type": "string",
          "description": "reserved while it runs; settled when charged; released when nothing was charged"
        },
        "charged": {
          "type": "integer"
        },
        "reserved": {
          "type": "integer"
        }
      },
      "additionalProperties": false
    },
    "outputs": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "object",
        "required": [
          "url",
          "kind"
        ],
        "properties": {
          "url": {
            "type": "string"
          },
          "kind": {
            "type": "string"
          },
          "duration_ms": {
            "type": "integer"
          }
        },
        "additionalProperties": false
      }
    },
    "modality": {
      "type": "string"
    },
    "progress": {
      "type": "integer"
    },
    "created_at": {
      "type": "string"
    },
    "generation_id": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
get_generation annotations
{
  "readOnlyHint": true,
  "idempotentHint": false
}
get_model
Advertised by the server during the last successful anonymous check.
Advertised read-only

One model's prompt limit, the reference files it takes, and its settings with their allowed values and defaults.

get_model input schema
{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "the model id from list_models"
    }
  },
  "additionalProperties": false
}
get_model output schema
{
  "type": "object",
  "required": [
    "id",
    "name",
    "maker",
    "modality",
    "settings"
  ],
  "properties": {
    "id": {
      "type": "string"
    },
    "name": {
      "type": "string"
    },
    "maker": {
      "type": "string"
    },
    "prompt": {
      "type": "object",
      "additionalProperties": true
    },
    "modality": {
      "type": "string"
    },
    "settings": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "object",
        "required": [
          "key",
          "name"
        ],
        "properties": {
          "key": {
            "type": "string"
          },
          "max": {
            "type": [
              "null",
              "number"
            ]
          },
          "min": {
            "type": [
              "null",
              "number"
            ]
          },
          "help": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "type": {
            "type": "string"
          },
          "values": {
            "type": [
              "null",
              "array"
            ],
            "items": true
          },
          "default": true,
          "optional": {
            "type": "boolean",
            "description": "left out unless given"
          },
          "required": {
            "type": "boolean"
          },
          "only_when": {
            "type": "string"
          }
        },
        "additionalProperties": false
      }
    },
    "reference_inputs": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "object",
        "required": [
          "name",
          "kind",
          "min",
          "max"
        ],
        "properties": {
          "max": {
            "type": "integer"
          },
          "min": {
            "type": "integer"
          },
          "kind": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "role": {
            "type": "string"
          },
          "max_bytes": {
            "type": "integer"
          },
          "file_types": {
            "type": [
              "null",
              "array"
            ],
            "items": {
              "type": "string"
            }
          }
        },
        "additionalProperties": false
      },
      "description": "in order: references of one kind fill these slots in turn"
    }
  },
  "additionalProperties": false
}
get_model annotations
{
  "readOnlyHint": true,
  "idempotentHint": false
}
list_generations
Advertised by the server during the last successful anonymous check.
Advertised read-only

The user's latest generations, newest first, made on the site or through any of their keys.

list_generations input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "description": "how many, newest first (1–20, default 10)"
    }
  },
  "additionalProperties": false
}
list_generations output schema
{
  "type": "object",
  "additionalProperties": {
    "type": [
      "null",
      "array"
    ],
    "items": {
      "type": "object",
      "required": [
        "generation_id",
        "model",
        "modality",
        "status",
        "progress",
        "created_at",
        "credits"
      ],
      "properties": {
        "tip": {
          "type": "string"
        },
        "text": {
          "type": "string"
        },
        "error": {
          "type": [
            "null",
            "object"
          ],
          "required": [
            "code",
            "message",
            "retryable"
          ],
          "properties": {
            "code": {
              "type": "string"
            },
            "message": {
              "type": "string"
            },
            "retryable": {
              "type": "boolean"
            }
          },
          "additionalProperties": false
        },
        "model": {
          "type": "string"
        },
        "prompt": {
          "type": "string"
        },
        "status": {
          "type": "string",
          "description": "queued, processing, succeeded, failed or unknown"
        },
        "credits": {
          "type": "object",
          "required": [
            "reserved",
            "charged",
            "state"
          ],
          "properties": {
            "state": {
              "type": "string",
              "description": "reserved while it runs; settled when charged; released when nothing was charged"
            },
            "charged": {
              "type": "integer"
            },
            "reserved": {
              "type": "integer"
            }
          },
          "additionalProperties": false
        },
        "outputs": {
          "type": [
            "null",
            "array"
          ],
          "items": {
            "type": "object",
            "required": [
              "url",
              "kind"
            ],
            "properties": {
              "url": {
                "type": "string"
              },
              "kind": {
                "type": "string"
              },
              "duration_ms": {
                "type": "integer"
              }
            },
            "additionalProperties": false
          }
        },
        "modality": {
          "type": "string"
        },
        "progress": {
          "type": "integer"
        },
        "created_at": {
          "type": "string"
        },
        "generation_id": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
  }
}
list_generations annotations
{
  "readOnlyHint": true,
  "idempotentHint": false
}
list_models
Advertised by the server during the last successful anonymous check.
Advertised read-only

The models the user can generate with, by kind (image, video, audio, text). get_model gives one model's inputs and settings.

list_models input schema
{
  "type": "object",
  "properties": {
    "modality": {
      "type": "string",
      "description": "only this kind: image, video, audio or text"
    }
  },
  "additionalProperties": false
}
list_models output schema
{
  "type": "object",
  "additionalProperties": {
    "type": [
      "null",
      "array"
    ],
    "items": {
      "type": "object",
      "required": [
        "id",
        "name",
        "maker",
        "modality",
        "takes"
      ],
      "properties": {
        "id": {
          "type": "string"
        },
        "name": {
          "type": "string"
        },
        "maker": {
          "type": "string"
        },
        "takes": {
          "type": "string"
        },
        "featured": {
          "type": "boolean"
        },
        "modality": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
  }
}
list_models annotations
{
  "readOnlyHint": true,
  "idempotentHint": false
}
quote
Advertised by the server during the last successful anonymous check.
Advertised read-only

What a generation would cost, in credits, without making it. Tell the user before generating.

quote input schema
{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "the model id from list_models"
    },
    "prompt": {
      "type": "string",
      "description": "what to make; for speech models the text to read"
    },
    "parameters": {
      "type": "object",
      "description": "the model's settings by key (get_model); any left out take the model's default",
      "additionalProperties": true
    },
    "references": {
      "type": [
        "null",
        "object"
      ],
      "properties": {
        "audio": {
          "type": [
            "null",
            "array"
          ],
          "items": {
            "type": "string"
          },
          "description": "asset ids of uploaded audio files, in the order of the model's audio slots"
        },
        "images": {
          "type": [
            "null",
            "array"
          ],
          "items": {
            "type": "string"
          },
          "description": "asset ids of uploaded images (complete_upload), in the order of the model's image slots"
        },
        "videos": {
          "type": [
            "null",
            "array"
          ],
          "items": {
            "type": "string"
          },
          "description": "asset ids of uploaded videos, in the order of the model's video slots"
        }
      },
      "description": "uploaded files the model works from",
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}
quote output schema
{
  "type": "object",
  "required": [
    "model",
    "credits",
    "estimated_credits",
    "exact",
    "usd"
  ],
  "properties": {
    "usd": {
      "type": "string",
      "description": "credits in US dollars at 1 credit = 0.01 USD"
    },
    "exact": {
      "type": "boolean",
      "description": "true when the price is fixed; false when the model decides part of it and only up to credits is charged"
    },
    "model": {
      "type": "string"
    },
    "credits": {
      "type": "integer",
      "description": "what is reserved; for a fixed price also what is charged"
    },
    "estimated_credits": {
      "type": "integer"
    }
  },
  "additionalProperties": false
}
quote annotations
{
  "readOnlyHint": true,
  "idempotentHint": 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
610 ms
95th percentile latency
610 ms

Maintenance history

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

  • · probe · passed · 610 ms · metadata changed · 9 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 arumi-mcp https://api.arumi.ai/mcp

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 arumi-mcp --url https://api.arumi.ai/mcp

Cursor

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

Cline

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

VS Code

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

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 arumi-mcp https://api.arumi.ai/mcp

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.arumi.ai/mcp

Windsurf

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

Let your agent find its tools

Find servers like Arumi 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 5,557