RMCP.DEV
← Registry

AI & Machine Learning

ccapi.ai

Provides AI-powered generation and editing for text, images, and music through a unified API.

2 endpoints22 known toolsFirst detected August 2, 2026Last detected September 1, 2026

ENDPOINT 1

https://api.ccapi.ai/mcp

No auth detected

MCP server metadata

Name
ccapi
Version
20260901-d10ff95
Capabilities
loggingtools.listChanged
Server instructions

CCAPI gives you access to image, video, music and text models through one API key. Key facts: - Every tool call consumes the account's balance. Prefer one good call over exploratory retries. - Call list_models first if you are unsure which model names are available; model availability depends on the key's group and changes over time. Do not guess model names. - Image and text tools return results directly. - Video and music tools are asynchronous: they return a task_id and a platform, then you poll get_task with that exact pair until status is "completed" or "failed" (the other states are "queued" and "in_progress"). Generation typically takes 30-180 seconds for video and 30-120 seconds for music. Pass wait_seconds to have the server poll for you instead of looping yourself. - Result URLs are hosted by the upstream provider and may expire. Download anything worth keeping.

Known tools 11

chat_completion

Send a conversation to any text model available through CCAPI (Claude, GPT, Gemini, DeepSeek, GLM, MiniMax, Kimi, Qwen…) and get the reply.

Potential side effects
edit_image

Edit existing images according to an instruction, using the dedicated image edit endpoint.

Potential side effects
extend_music

Continue an existing song from a given timestamp, producing a longer version.

Inferred read-only
generate_image

Generate an image from a text prompt, optionally guided by reference images (image-to-image).

Inferred read-only
generate_lyrics

Write song lyrics from a description, without generating audio.

Potential side effects
generate_music

Generate a song with vocals or instrumental.

Inferred read-only
generate_video

Generate a video from a text prompt, optionally driven by reference images (image-to-video, first/last frame).

Inferred read-only
get_balance

Report the remaining and used balance for this CCAPI key.

Inferred read-only
get_task

Check the status of an asynchronous generation task submitted by generate_video, generate_music, generate_lyrics, extend_music, or generate_image with async=true.

Inferred read-only
list_models

List the AI models this CCAPI key can actually call, with their capability category and the MCP tool that drives them.

Inferred read-only
upscale_image

Increase the resolution of an existing image 2x with ccapi-upscale-v1.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ccapi]
url = "https://api.ccapi.ai/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "ccapi": {
      "type": "http",
      "url": "https://api.ccapi.ai/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: ccapi
Remote MCP URL: https://api.ccapi.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "ccapi": {
      "url": "https://api.ccapi.ai/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code 
{
  "servers": {
    "ccapi": {
      "type": "http",
      "url": "https://api.ccapi.ai/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "ccapi",
  "transport": "streamable-http",
  "url": "https://api.ccapi.ai/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://ccapi.ai/mcp

No auth detected

MCP server metadata

Name
ccapi
Version
20260813-02f011b
Capabilities
loggingtools.listChanged
Server instructions

CCAPI gives you access to image, video, music and text models through one API key. Key facts: - Every tool call consumes the account's balance. Prefer one good call over exploratory retries. - Call list_models first if you are unsure which model names are available; model availability depends on the key's group and changes over time. Do not guess model names. - Image and text tools return results directly. - Video and music tools are asynchronous: they return a task_id and a platform, then you poll get_task with that exact pair until status is "completed" or "failed" (the other states are "queued" and "in_progress"). Generation typically takes 30-180 seconds for video and 30-120 seconds for music. Pass wait_seconds to have the server poll for you instead of looping yourself. - Result URLs are hosted by the upstream provider and may expire. Download anything worth keeping.

Known tools 11

chat_completion

Send a conversation to any text model available through CCAPI (Claude, GPT, Gemini, DeepSeek, GLM, MiniMax, Kimi, Qwen…) and get the reply.

Potential side effects
edit_image

Edit existing images according to an instruction, using the dedicated image edit endpoint.

Potential side effects
extend_music

Continue an existing song from a given timestamp, producing a longer version.

Inferred read-only
generate_image

Generate an image from a text prompt, optionally guided by reference images (image-to-image).

Inferred read-only
generate_lyrics

Write song lyrics from a description, without generating audio.

Potential side effects
generate_music

Generate a song with vocals or instrumental.

Inferred read-only
generate_video

Generate a video from a text prompt, optionally driven by reference images (image-to-video, first/last frame).

Inferred read-only
get_balance

Report the remaining and used balance for this CCAPI key.

Inferred read-only
get_task

Check the status of an asynchronous generation task submitted by generate_video, generate_music, generate_lyrics, extend_music, or generate_image with async=true.

Inferred read-only
list_models

List the AI models this CCAPI key can actually call, with their capability category and the MCP tool that drives them.

Inferred read-only
upscale_image

Increase the resolution of an existing image 2x with ccapi-upscale-v1.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ccapi]
url = "https://ccapi.ai/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "ccapi": {
      "type": "http",
      "url": "https://ccapi.ai/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: ccapi
Remote MCP URL: https://ccapi.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "ccapi": {
      "url": "https://ccapi.ai/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code 
{
  "servers": {
    "ccapi": {
      "type": "http",
      "url": "https://ccapi.ai/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "ccapi",
  "transport": "streamable-http",
  "url": "https://ccapi.ai/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for ccapi.ai was fetched 2026-09-07T17:24:39.547Z.

Trust status Neutral

ccapi.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.