TokPort MCP

A hosted Model Context Protocol endpoint that allows coding agents to discover models, read exact parameter schemas and prices, and generate images or video using the user's API key. It supports stateless Streamable HTTP connections without requiring extra software to run.

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.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by TokPort

MCP endpoint (Streamable HTTP)

https://tokport.io/api/mcp

Vendor documentation

What you can do with it

Search the model catalog for available models and pricing
Retrieve input parameters and output shapes for specific models
Run models synchronously to generate images or video
Queue requests and check job status for asynchronous generation

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: io.tokport/tokport@1.0.0 Project website

Protocol and capabilities

Server: tokport-mcp 1.0.0
MCP protocol: 2025-06-18
Tools: 8 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

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

TokPort image and video generation. Call search_models or get_model_schema first, then run_model (sync) or submit_job + check_job + get_job_result (async). Prices are per image, per second of video, or per video clip, depending on the model.

Tools

8 advertised

search_models

Advertised by the server during the last successful anonymous check.

Search the model catalog. Returns ids, modality, tasks, pricing and links. Use before calling run_model or submit_job to pick a model id.

search_models input schema

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free-text query over id, name, vendor and tags"
    },
    "task": {
      "type": "string",
      "description": "text-to-image | image-to-image | text-to-video | image-to-video"
    },
    "modality": {
      "enum": [
        "image",
        "video"
      ],
      "type": "string",
      "description": "image or video"
    },
    "available": {
      "type": "boolean",
      "description": "Only models live on the gateway"
    }
  }
}

get_model_schema

Advertised by the server during the last successful anonymous check.

Input parameters (name, type, allowed values, defaults) and output shape for every task a model supports.

get_model_schema input schema

{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id, e.g. gpt-image-2"
    }
  }
}

get_pricing

Advertised by the server during the last successful anonymous check.

Live price per image, per second of video, or per video clip, depending on the model. Query one model or all models.

get_pricing input schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id; omit for all models"
    }
  }
}

run_model

Advertised by the server during the last successful anonymous check.

Run a model synchronously with the caller's API key. Images return URLs; videos are queued and this waits up to 60 s before returning the queue status instead.

run_model input schema

{
  "type": "object",
  "required": [
    "model",
    "input"
  ],
  "properties": {
    "task": {
      "type": "string",
      "description": "Force the task kind (inferred otherwise)"
    },
    "input": {
      "type": "object",
      "description": "Model input: prompt, size, n, image, seconds …",
      "additionalProperties": true
    },
    "model": {
      "type": "string",
      "description": "Model id"
    }
  }
}

submit_job

Advertised by the server during the last successful anonymous check.

Queue a request and return its request_id immediately. Follow with check_job / get_job_result.

submit_job input schema

{
  "type": "object",
  "required": [
    "model",
    "input"
  ],
  "properties": {
    "task": {
      "type": "string",
      "description": "Force the task kind (inferred otherwise)"
    },
    "input": {
      "type": "object",
      "additionalProperties": true
    },
    "model": {
      "type": "string",
      "description": "Model id"
    },
    "webhook": {
      "type": "string",
      "description": "Public http(s) URL to POST the result to"
    },
    "priority": {
      "enum": [
        "normal",
        "low"
      ],
      "type": "string",
      "description": "normal or low"
    }
  }
}

check_job

Advertised by the server during the last successful anonymous check.

Status of a queued request (IN_QUEUE / IN_PROGRESS / COMPLETED / FAILED / CANCELLED) with position, logs and metrics.

check_job input schema

{
  "type": "object",
  "required": [
    "model",
    "request_id"
  ],
  "properties": {
    "logs": {
      "type": "boolean"
    },
    "model": {
      "type": "string",
      "description": "Model id"
    },
    "request_id": {
      "type": "string",
      "description": "req_… id"
    }
  }
}

get_job_result

Advertised by the server during the last successful anonymous check.

Result of a completed request; waits up to `timeout` seconds (max 60) when still running.

get_job_result input schema

{
  "type": "object",
  "required": [
    "model",
    "request_id"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id"
    },
    "timeout": {
      "type": "integer",
      "maximum": 60,
      "minimum": 0
    },
    "request_id": {
      "type": "string",
      "description": "req_… id"
    }
  }
}

cancel_job

Advertised by the server during the last successful anonymous check.

Cancel a request while it is still queued.

cancel_job input schema

{
  "type": "object",
  "required": [
    "model",
    "request_id"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id"
    },
    "request_id": {
      "type": "string",
      "description": "req_… id"
    }
  }
}

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: 645 ms
95th percentile latency: 645 ms

Maintenance history

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

Nov 1, 2026, 8:59 AM UTC · probe · passed · 645 ms · metadata changed · 8 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 tokport-mcp https://tokport.io/api/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 tokport-mcp --url https://tokport.io/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable tokport-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "tokport-mcp": {
      "url": "https://tokport.io/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "tokport-mcp": {
      "type": "streamableHttp",
      "url": "https://tokport.io/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start tokport-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "tokport-mcp": {
      "type": "http",
      "url": "https://tokport.io/api/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 tokport-mcp https://tokport.io/api/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "tokport-mcp": {
      "url": "https://tokport.io/api/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": {
    "tokport-mcp": {
      "serverUrl": "https://tokport.io/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like TokPort 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

Do you run TokPort MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing